ProZ.com Translation Forums

Supervertaler Workbench is no longer actively developed | Forest giraffe

CafeTran Trainer — Mon, 14 Sep 2026 09:46:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: CafeTran Trainer
Post title: Forest giraffe

[quote]Michael Beijer wrote:

The reason why I decided to include Okapi is that Supervertaler Workbench could then make use of its extensive file filters, rather than have to code them from scratch in Python. [/quote]

I prefer to do everything with Python. No external tools in my backyard.

WYSIWYG display is quite good:

Controlling Trados Studio from Claude chat (with Supervertaler for Trados)! | Not Stakhanov, just diversification

Michael Beijer — Sat, 12 Sep 2026 10:17:00 +0000

Forum: Supervertaler
Topic: Controlling Trados Studio from Claude chat (with Supervertaler for Trados)!
Poster: Michael Beijer
Post title: Not Stakhanov, just diversification

[quote]Daryo wrote:

[quote]Michael Beijer wrote:

[quote]Jennifer Levey wrote:

Pardon my ignorance....

In a word, "Why?"

Apart from ego-tripping on the back of your 'vibe-coding' affliction, what does this contribute to our collective professional well-being?
JL [/quote]

I built it for myself. At the rates and turnaround times being offered now, I couldn't take on half the work I accept without it – 10,000 words by tomorrow, flawless, in some convoluted format, with three QA spreadsheets to fill in before you get paid.

As for what it contributes: it depends who "we" are. If it means the industry as a whole, probably nothing – the LSPs are already building this into their own pipelines and don't need my help. If it means translators, then the point is that the tooling shouldn't only be on their side of the table. The demands keep going up and the rates keep going down, and I'd rather have the means to meet the first without accepting the second. That's what Supervertaler is for. It's a way of pushing back rather than being squeezed out.

Every time a new technology has come along in the thirty years I've been doing this, some colleagues have refused it on the grounds that it would replace them, and others have learned it to stay competitive. I've been in the second group each time. I'm still here and still making a living, which is more than a lot of the first group can say.

On "vibe-coding": I'm not a programmer and have never claimed to be. The AI writes the code. What it doesn't do is decide what a working translator actually needs, how it should behave inside a live Studio session, what breaks in a real project, or what's worth building at all. That part is thirty years in this industry, and it's most of the work.

Michael [/quote]

I surely can not speak for the whole of your 'first group' but believe it or not there is a life outside of MT / repetition grids / fuzzy matches / 'adapting' to worse and worse conditions & other forms of 'progress'.

If you show some modicum of initiative, and Lady Luck doesn't decide to hate you, a far more interesting and rewarding [in ££ and otherwise] life than flogging a dead donkey / trying to squeeze the last drop from dry wood ...

What next? You'll figure out how to squeeze 110,000 words by tomorrow?

That surely will even more contribute to translators' collective professional well-being! Are you in competition with Stakhanov?

Count me out.

Wait a second, I'm already out of THAT kind of 'translating'.
[/quote]

Ha ha – yes, I'm aware there's life outside "MT / repetition grids / fuzzy matches / adapting to worse and worse conditions". That's partly why I automated the tedious bits: so I could spend less time on them, not more.

Some context. Around 80% of my income comes from direct clients. They've never heard of CAT tools or fuzzy matches; they send a Word file, I translate it by hand, they pay properly. Supervertaler barely features there.

Where it does matter is the other 20%. Over the past few years, my agency work has steadily disappeared: first translation turned into post-editing, then the post-editing started drying up too, as LSPs discovered AI for themselves. Agencies have their uses – they find the client, handle the client, sort out the file formats – and I didn't particularly want to lose them all. Automating the mechanical parts of the job (file wrangling, terminology, QA checks) has let me keep that work viable at rates I'd otherwise have to turn down, while still reading and checking every segment myself.

So no Stakhanov. It's diversification: keep the direct clients happy with a personalised service, stop haemorrhaging the agency clients, and – since I've been looking for a plan B for years – add a small third income stream from selling the software. Nothing more heroic than that.

Michael

P.S. One practical example of why automation like this is worth having. I've had RSI in my right hand for years, most likely going back to breaking it as a child, and it flares up whenever I use the computer – the mouse especially – too much. So I added a voice command system to Supervertaler for Trados that lets me drive a good part of Studio by voice. Combine that with the MCP server, which lets me control Studio through Claude Desktop, also by voice, and the hand gets a real rest when it needs one. It's playing up today, as it happens, so I'm sitting back in my chair and doing most of the job without touching the mouse.

See: [url removed]

[Edited at 2026-09-12 11:13 GMT]

[Edited at 2026-09-12 11:14 GMT]

Controlling Trados Studio from Claude chat (with Supervertaler for Trados)! | Good for you!

Daryo — Sat, 12 Sep 2026 07:16:00 +0000

Forum: Supervertaler
Topic: Controlling Trados Studio from Claude chat (with Supervertaler for Trados)!
Poster: Daryo
Post title: Good for you!

[quote]Lieven Malaise wrote:

[quote]Daryo wrote:
I surely can not speak for the whole of your 'first group' but believe it or not there is a life outside of MT / repetition grids / fuzzy matches / 'adapting' to worse and worse conditions & other forms of 'progress'.

If you show some modicum of initiative, and Lady Luck doesn't decide to hate you, a far more interesting and rewarding [in ££ and otherwise] life than flogging a dead donkey / trying to squeeze the last drop from dry wood [/quote]

Fantastic, superb, brilliant. Imagine living the professional good life like you and then continuously coming back here to complain and nag about everything AI or MTPE related in our business and criticize people that actually take initiative to not go down as sitting ducks. The joy you are radiating is impressive. Makes perfectly sense.

It makes almost as much sense as being retired, but still wasting time on these forums with opinions professionals - you know, the people that actually make money in this industry while being here - couldn't care less about.

It's apparently very hard to accept that some people, for various reasons, still like and enjoy what they are doing while continuing to make good money in the process, even when translation no longer is what it used to be. [/quote]

If you have found a way to outperform Stakhanov and are happy with that - good luck to you!

As for what is or is not 'wasting time' it's a far more trickier question than it appears to be - better not start on that one.

Controlling Trados Studio from Claude chat (with Supervertaler for Trados)! | Makes sense

Lieven Malaise — Sat, 12 Sep 2026 06:41:00 +0000

Forum: Supervertaler
Topic: Controlling Trados Studio from Claude chat (with Supervertaler for Trados)!
Poster: Lieven Malaise
Post title: Makes sense

[quote]Daryo wrote:
I surely can not speak for the whole of your 'first group' but believe it or not there is a life outside of MT / repetition grids / fuzzy matches / 'adapting' to worse and worse conditions & other forms of 'progress'.

If you show some modicum of initiative, and Lady Luck doesn't decide to hate you, a far more interesting and rewarding [in ££ and otherwise] life than flogging a dead donkey / trying to squeeze the last drop from dry wood [/quote]

Fantastic, superb, brilliant. Imagine living the professional good life like you and then continuously coming back here to complain and nag about everything AI or MTPE related in our business and criticize people that actually take initiative to not go down as sitting ducks. The joy you are radiating is impressive. Makes perfectly sense.

It makes almost as much sense as being retired, but still wasting time on these forums with opinions professionals - you know, the people that actually make money in this industry while being here - couldn't care less about.

It's apparently very hard to accept that some people, for various reasons, still like and enjoy what they are doing while continuing to make good money in the process, even when translation no longer is what it used to be.

Supervertaler Workbench is no longer actively developed | Windows Credential Manager is much safer than DPAPI

Li-Hsiang Hsu — Sat, 12 Sep 2026 06:16:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Li-Hsiang Hsu
Post title: Windows Credential Manager is much safer than DPAPI

I use Windows Credential Manager (WCM) as a basic, minimal protection layer for API keys, and I consider that good practice. Yes, WCM, like DPAPI, provides user-bound protection as you mentionned in your reply, but it is misleading to say that the same security criticism to DPAPI therefore applies to WCM. That reasoning stems from a misunderstanding of how the two projections work.

WCM actually uses DPAPI to encrypt credential files, but it adds multiple layers of security on top. Those layers are what make WCM safer than using DPAPI directly. In short, DPAPI is essentially an encryption API; WCM is a credential vault. Beyond DPAPI encryption, WCM further provides vault-style storage, isolation, mediated access, per-credential scoping, lifecycle management, and hardware-backed protection where available. DPAPI is widely used because it is simple, convenient and effective for local encryption, but it is not a complete secrets-management system, not at the level of WCM. It is therefore certainly incorrect to consider that DPAPI offers the same level of protection as WCM because both are user-bound.

That difference matters for API keys, because API keys are high-value and high-impact secrets, often tied to financial cost, service access, privacy and sensitive operations. Nowadays, they are also prime targets for malware. For that threat profile, a managed credential vault like WCM is a better fit than raw DPAPI encryption.

In short, my key point is this: we should not consider WCM to be just as secure or insecure as DPAPI simply because it uses DPAPI (as well) and is tied to the user (just like DPAPI). It is actually more secure, because it does not stop at DPAPI. Equating the two merely because both are user-level protections ignores the additional isolation, control, and lifecycle protections that WCM provides.

Controlling Trados Studio from Claude chat (with Supervertaler for Trados)! | A modern day Stakhanov?

Daryo — Sat, 12 Sep 2026 03:32:00 +0000

Forum: Supervertaler
Topic: Controlling Trados Studio from Claude chat (with Supervertaler for Trados)!
Poster: Daryo
Post title: A modern day Stakhanov?

[quote]Michael Beijer wrote:

[quote]Jennifer Levey wrote:

Pardon my ignorance....

In a word, "Why?"

Apart from ego-tripping on the back of your 'vibe-coding' affliction, what does this contribute to our collective professional well-being?
JL [/quote]

I built it for myself. At the rates and turnaround times being offered now, I couldn't take on half the work I accept without it – 10,000 words by tomorrow, flawless, in some convoluted format, with three QA spreadsheets to fill in before you get paid.

As for what it contributes: it depends who "we" are. If it means the industry as a whole, probably nothing – the LSPs are already building this into their own pipelines and don't need my help. If it means translators, then the point is that the tooling shouldn't only be on their side of the table. The demands keep going up and the rates keep going down, and I'd rather have the means to meet the first without accepting the second. That's what Supervertaler is for. It's a way of pushing back rather than being squeezed out.

Every time a new technology has come along in the thirty years I've been doing this, some colleagues have refused it on the grounds that it would replace them, and others have learned it to stay competitive. I've been in the second group each time. I'm still here and still making a living, which is more than a lot of the first group can say.

On "vibe-coding": I'm not a programmer and have never claimed to be. The AI writes the code. What it doesn't do is decide what a working translator actually needs, how it should behave inside a live Studio session, what breaks in a real project, or what's worth building at all. That part is thirty years in this industry, and it's most of the work.

Michael [/quote]

I surely can not speak for the whole of your 'first group' but believe it or not there is a life outside of MT / repetition grids / fuzzy matches / 'adapting' to worse and worse conditions & other forms of 'progress'.

If you show some modicum of initiative, and Lady Luck doesn't decide to hate you, a far more interesting and rewarding [in ££ and otherwise] life than flogging a dead donkey / trying to squeeze the last drop from dry wood ...

What next? You'll figure out how to squeeze 110,000 words by tomorrow?

That surely will even more contribute to translators' collective professional well-being! Are you in competition with Stakhanov?

Count me out.

Wait a second, I'm already out of THAT kind of 'translating'.

Supervertaler Workbench is no longer actively developed | So this API management is good enough to you?

Li-Hsiang Hsu — Thu, 10 Sep 2026 17:14:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Li-Hsiang Hsu
Post title: So this API management is good enough to you?

At least, we know how you handle your products. 😉

[quote]Michael Beijer wrote:

[quote]Li-Hsiang Hsu wrote:

Just check yourself what it protects and what it doesn't. 😉 [/quote]

[/quote]

[Edited at 2026-09-10 17:18 GMT]

Supervertaler Workbench is no longer actively developed | Thanks for the reminder/tip!

Michael Beijer — Thu, 10 Sep 2026 17:10:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Michael Beijer
Post title: Thanks for the reminder/tip!

[quote]Li-Hsiang Hsu wrote:

Just check yourself what it protects and what it doesn't. 😉 [/quote]

Supervertaler Workbench is no longer actively developed | So it was your decision

Li-Hsiang Hsu — Thu, 10 Sep 2026 16:43:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Li-Hsiang Hsu
Post title: So it was your decision

[quote]Michael Beijer wrote:

Claude Code initially asked whether I wanted to store it more securely, and I responded, "No thanks, I'm happy to store it on disk in that JSON." That is, I didn't need to ask it to do better. It had already asked me.

Incidentally, which of the latest models would you rate as the best in terms of its ability to do a decent job, without a professional developer steering it? Or let me rephrase that: which would do the least bad job, do you think?

[/quote]

I would ask it to do better than that.

Basically, even earlier models do "good enough jobs" so far as you don't look any further. A good enough job is one that appears correct at first glance but fails to hold up under more rigorous testing. That is models' basic configuration.

If by "decent" you mean a professional-quality job, then preparation and skills are all you need, that’s all there is to it. Even the best models can't do more than that unless you ask them to.

Models need context. And you provide the context. That's your job.

[Edited at 2026-09-10 17:11 GMT]

Supervertaler Workbench is no longer actively developed | Windows DPAPI is a good enough API management

Li-Hsiang Hsu — Thu, 10 Sep 2026 16:41:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Li-Hsiang Hsu
Post title: Windows DPAPI is a good enough API management

Just check yourself what it protects and what it doesn't. 😉

Supervertaler Workbench is no longer actively developed | Perhaps, but...

Michael Beijer — Thu, 10 Sep 2026 16:35:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Michael Beijer
Post title: Perhaps, but...

[quote]Li-Hsiang Hsu wrote:

[quote]Michael Beijer wrote:

[quote]Li-Hsiang Hsu wrote:

It is good practice to have your code audited by other models. But I wonder how you handle consistency...

By the way, I just noticed that your API keys are simply stored in a plaintext JSON file. That bears the unmistakable "signature" of Claude. Without specific instructions, Claude provides functional code that handles your API keys in a convenient way, without any protection. It won't make the effort to further secure your API keys unless you know to prompt it to do so, rather than letting it make all the decisions. [/quote]

On consistency: I do not merge their output. I read the findings myself and decide which to act on – the models disagree often enough that treating them as a committee would be worse than useless.

On the API keys, fair point, and you are right that they sit in a plaintext JSON file. That is a deliberate choice rather than an oversight, though I take the general warning.

Two reasons. The file lives in my own user profile on a machine I control, so anything able to read it can already read a great deal more. And I rotate the keys regularly, which is a good deal easier when I can just open the file and paste.

For what it is worth, the plugin does use Windows DPAPI where I judged it warranted – the GroupShare server password is encrypted at rest and never written in clear text (see [i]src/Supervertaler.Trados/Core/DpapiSecret.cs[/i]). So the pattern is not simply "whatever was convenient".

Where you are right is that this should be a documented decision rather than an unexamined default, and that what suits me is not necessarily the right default for everyone else. That is part of what [url= [url removed] ]#115[/url] is for. [/quote]

That is a Claude classics, the way it reacts to justify a code that is "just good enough." I recognize its signature style there. It always defends itself that way when asked why it delivered a job that is "merely good enough." It is a subtle and considerate attitude, because it will never tell you that the real reason is simply that you didn't ask it to do better.

[Edited at 2026-09-10 16:31 GMT] [/quote]

Claude Code initially asked whether I wanted to store it more securely, and I responded, "No thanks, I'm happy to store it on disk in that JSON." That is, I didn't need to ask it to do better. It had already asked me.

Incidentally, which of the latest models would you rate as the best in terms of its ability to do a decent job, without a professional developer steering it? Or let me rephrase that: which would do the least bad job, do you think?

PS: Thanks for the tip about Gemini CLI. I added support for Antigravity via the Supervertaler MCP Server, so users can now control Trados Studio from Antigravity (just like with Claude desktop chat and ChatGPT desktop chat). See the Antigravity section at [url removed]

[Edited at 2026-09-10 16:43 GMT]

Supervertaler Workbench is no longer actively developed | Claude’s response pattern to defend its Good enough code

Li-Hsiang Hsu — Thu, 10 Sep 2026 16:28:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Li-Hsiang Hsu
Post title: Claude’s response pattern to defend its Good enough code

[quote]Michael Beijer wrote:

[quote]Li-Hsiang Hsu wrote:

It is good practice to have your code audited by other models. But I wonder how you handle consistency...

By the way, I just noticed that your API keys are simply stored in a plaintext JSON file. That bears the unmistakable "signature" of Claude. Without specific instructions, Claude provides functional code that handles your API keys in a convenient way, without any protection. It won't make the effort to further secure your API keys unless you know to prompt it to do so, rather than letting it make all the decisions. [/quote]

On the API keys, fair point, and you are right that they sit in a plaintext JSON file. That is a deliberate choice rather than an oversight, though I take the general warning.

Two reasons. The file lives in my own user profile on a machine I control, so anything able to read it can already read a great deal more. And I rotate the keys regularly, which is a good deal easier when I can just open the file and paste.

For what it is worth, the plugin does use Windows DPAPI where I judged it warranted – the GroupShare server password is encrypted at rest and never written in clear text (see [i]src/Supervertaler.Trados/Core/DpapiSecret.cs[/i]). So the pattern is not simply "whatever was convenient".

Where you are right is that this should be a documented decision rather than an unexamined default, and that what suits me is not necessarily the right default for everyone else. That is part of what [url= [url removed] ]#115[/url] is for. [/quote]

That is a Claude classics, the way it reacts to justify a code that is "just good enough." I recognize its signature style there. It always defends itself that way when asked why it delivered a job that is "merely good enough." It is a subtle and considerate attitude, because it will never tell you that the real reason is simply that you didn't ask it to do better.

[Edited at 2026-09-10 16:32 GMT]

Supervertaler Workbench is no longer actively developed | A deliberate choice, but a fair point

Michael Beijer — Thu, 10 Sep 2026 16:08:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Michael Beijer
Post title: A deliberate choice, but a fair point

[quote]Li-Hsiang Hsu wrote:

It is good practice to have your code audited by other models. But I wonder how you handle consistency...

By the way, I just noticed that your API keys are simply stored in a plaintext JSON file. That bears the unmistakable "signature" of Claude. Without specific instructions, Claude provides functional code that handles your API keys in a convenient way, without any protection. It won't make the effort to further secure your API keys unless you know to prompt it to do so, rather than letting it make all the decisions. [/quote]

On consistency: I do not merge their output. I read the findings myself and decide which to act on – the models disagree often enough that treating them as a committee would be worse than useless.

On the API keys, fair point, and you are right that they sit in a plaintext JSON file. That is a deliberate choice rather than an oversight, though I take the general warning.

Two reasons. The file lives in my own user profile on a machine I control, so anything able to read it can already read a great deal more. And I rotate the keys regularly, which is a good deal easier when I can just open the file and paste.

For what it is worth, the plugin does use Windows DPAPI where I judged it warranted – the GroupShare server password is encrypted at rest and never written in clear text (see [i]src/Supervertaler.Trados/Core/DpapiSecret.cs[/i]). So the pattern is not simply "whatever was convenient".

Where you are right is that this should be a documented decision rather than an unexamined default, and that what suits me is not necessarily the right default for everyone else. That is part of what [url= [url removed] ]#115[/url] is for.

Supervertaler Workbench is no longer actively developed | Consistency and be mindful of Claude's OK code

Li-Hsiang Hsu — Thu, 10 Sep 2026 13:23:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Li-Hsiang Hsu
Post title: Consistency and be mindful of Claude's OK code

It is good practice to have your code audited by other models. But I wonder how you handle consistency...

By the way, I just noticed that your API keys are simply stored in a plaintext JSON file. That bears the unmistakable "signature" of Claude. Without specific instructions, Claude provides functional code that handles your API keys in a convenient way, without any protection. It won't make the effort to further secure your API keys unless you know to prompt it to do so, rather than letting it make all the decisions.

Supervertaler Workbench is no longer actively developed | Three top models should give me a pretty good indication of the quality/safety of the code

Michael Beijer — Thu, 10 Sep 2026 13:00:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Michael Beijer
Post title: Three top models should give me a pretty good indication of the quality/safety of the code

[quote]Li-Hsiang Hsu wrote:

That’s a nice try. But Claude can’t be your garde. People don’t check what it does are often overly optimistic about Claude.

We do find many safety concerns in Claude’s code with common prompts not optimized by a software engineer.

[Edited at 2026-09-10 12:09 GMT] [/quote]

Indeed, and I know it is far from foolproof. However, since I have no software engineer at my disposal, it will have to do for now.

Additionally, I'm going to run a similar security audit with different LLMs, such as:

- Anthropic – Claude Fable 5.1
- OpenAI – GPT-6 Astra
- Google – Gemini 3.8 Flash

That ought to give me a pretty good indication of what's what.

See: [url removed] ("[Security] Threat model, data-handling disclosure and liability groundwork before the memoQ release #115")

Supervertaler Workbench is no longer actively developed | Claude

Li-Hsiang Hsu — Thu, 10 Sep 2026 11:24:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Li-Hsiang Hsu
Post title: Claude

That’s a nice try. But Claude can’t be your garde. People don’t check what it does are often overly optimistic about Claude.

We do find many safety concerns in Claude’s code with common prompts not optimized by a software engineer.

[Edited at 2026-09-10 12:09 GMT]

Controlling Trados Studio from Claude chat (with Supervertaler for Trados)! | Nothing wrong with that

Dan Lucas — Thu, 10 Sep 2026 10:03:00 +0000

Forum: Supervertaler
Topic: Controlling Trados Studio from Claude chat (with Supervertaler for Trados)!
Poster: Dan Lucas
Post title: Nothing wrong with that

[quote]Michael Beijer wrote:
That's why I put it out there for free in the first place, and why, as it grew, I eventually had to start charging for parts of it.[/quote]
Sure, that's fine by me. People have agency - they can choose whether to purchase it or not. If they use it and they find that it helps them generate income, that's all to the good.

The key issue is that if you don't develop it in the first place then that option does not exist. It seems odd to me that people are against having more choices in a business context.

Dan

Supervertaler Workbench is no longer actively developed | You're right, and I'm treating this as the next piece of work

Michael Beijer — Thu, 10 Sep 2026 09:45:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Michael Beijer
Post title: You're right, and I'm treating this as the next piece of work

[quote]Li-Hsiang Hsu wrote:

@Michael,

Your work is really impressive.

Just a kind reminder: MCP actually exposes user’s computer and data to greater risk of attack and data leaks if not configured properly. Because here, Claude acts not merely as a text generator, but as an operator of your system. And your MCP server is the bridge, providing Claude direct access to read your local files, execute terminal commands or interact with external APIs.

We generally recommend that MCP should be configured by a real qualified person or at least user should be assisted by someone really understands the process.

[Edited at 2026-09-10 03:52 GMT] [/quote]

You're right, and thank you for raising it rather than letting it slide. A colleague put the same question to me on WhatsApp this morning, so that's twice in one day, which I take as a signal.

It's worth being precise about what Claude Desktop can and can't do, because I think this is where most of the worry sits. On its own it can't run anything on your PC. It can only call tools you've deliberately installed, and Supervertaler's tools are all Trados tools – read segments, look up the TM, check the termbase, write a draft into the grid. There's no route from that to a command prompt. Each call is shown to you and needs approval before it runs, unless you've clicked "always allow", which I'd ask people not to do.

What I can't protect against is what else you've connected in the same session. The server hands Claude the contents of a live document, and translation source documents are untrusted input by definition – they come from a client, via an agency, and nobody has vetted them. If a source segment contains text engineered to look like an instruction, the model may act on it. On its own that's bounded: the worst it can reach is Trados. But if you've also installed a server that can run shell commands or read your whole disk, a source document could in theory steer Claude toward those tools, and my server would be the thing that fed it the document. That combination is the case I want to warn about explicitly, and it's a design problem for me to address, not a configuration mistake on the user's part.

There's also a simpler issue that has nothing to do with attacks: segments leave the machine and go to an AI provider. Anyone doing patent or medical work under an NDA needs to know exactly what is sent and when, and that has to be documented rather than assumed.

So: I'm doing a proper security review of the code – what the tools can actually reach, what requires confirmation before it writes, what gets logged, how the transport is bound, and what the blast radius is when something goes wrong. Whatever comes out of it goes on the website as a plain description of the threat model, not marketing copy, along with terms that say honestly what I do and don't warrant. Where the answer is "this isn't safe yet", I'd rather write that down than leave people guessing.

One thing I'd push back on gently. "Should be configured by a qualified person" isn't realistic for freelance translators – almost none of us have one. If the software can only be used safely by someone who could have written it, then it isn't finished. The burden has to sit on the defaults, not the user. That's the standard I want to hold myself to, and I'm not there yet.

Michael

PS: see: [url removed] ("[Security] Threat model, data-handling disclosure and liability groundwork before the memoQ release #115")

[Edited at 2026-09-10 09:54 GMT]

Controlling Trados Studio from Claude chat (with Supervertaler for Trados)! | Fair question, so here's a straight answer.

Michael Beijer — Thu, 10 Sep 2026 09:22:00 +0000

Forum: Supervertaler
Topic: Controlling Trados Studio from Claude chat (with Supervertaler for Trados)!
Poster: Michael Beijer
Post title: Fair question, so here's a straight answer.

[quote]Jennifer Levey wrote:

Pardon my ignorance....

In a word, "Why?"

Apart from ego-tripping on the back of your 'vibe-coding' affliction, what does this contribute to our collective professional well-being?
JL [/quote]

I built it for myself. At the rates and turnaround times being offered now, I couldn't take on half the work I accept without it – 10,000 words by tomorrow, flawless, in some convoluted format, with three QA spreadsheets to fill in before you get paid.

As for what it contributes: it depends who "we" are. If it means the industry as a whole, probably nothing – the LSPs are already building this into their own pipelines and don't need my help. If it means translators, then the point is that the tooling shouldn't only be on their side of the table. The demands keep going up and the rates keep going down, and I'd rather have the means to meet the first without accepting the second. That's what Supervertaler is for. It's a way of pushing back rather than being squeezed out.

Every time a new technology has come along in the thirty years I've been doing this, some colleagues have refused it on the grounds that it would replace them, and others have learned it to stay competitive. I've been in the second group each time. I'm still here and still making a living, which is more than a lot of the first group can say.

On "vibe-coding": I'm not a programmer and have never claimed to be. The AI writes the code. What it doesn't do is decide what a working translator actually needs, how it should behave inside a live Studio session, what breaks in a real project, or what's worth building at all. That part is thirty years in this industry, and it's most of the work.

Michael

Controlling Trados Studio from Claude chat (with Supervertaler for Trados)! | Thanks for your kind words!

Michael Beijer — Thu, 10 Sep 2026 09:13:00 +0000

Forum: Supervertaler
Topic: Controlling Trados Studio from Claude chat (with Supervertaler for Trados)!
Poster: Michael Beijer
Post title: Thanks for your kind words!

[quote]Dan Lucas wrote:

[quote]Jennifer Levey wrote:
In a word, "Why?"[/quote]
In two words, "Why not?"

Michael has built something and it may help other people. He is offering it, as far as I can see, for free.

Some people here are still working, but in a fading industry like this one it makes sense to pursue greater efficiency. Many of us are looking to invest resources in areas other than translation, and want to reduce our commitments of time and energy to the minimum.

Others are not working, and therefore their comments are no longer grounded in any kind of firsthand experience of today’s market.

Still others are not tool users, and will never make use of mechanisms like the one Michael has developed to help improve efficiency. That's fine - nobody is forcing them to engage.

I don't think I see this in other industries. Some carpenters find a way to retain the use of hand tools in their process, but there are very few carpentry businesses that don't have a table saw and a router somewhere in the mix. It doesn't appear to me that we look down on those carpenters in the way translators look down on users of CAT tools or AI.

On the one hand, some users of this forum praise Michael while at the same time making patronizing comments about the need for qualified people to be involved.

On the other hand, you get people like yourself, apparently struggling to restrain their contempt for those who try to improve their workflows, who accuse Michael of ego-tripping.

It seems to me that he can't win.

Has either side considered that Michael enjoys creating things, and that he might just be cheerfully trying to help others with the result of his efforts?

He's not hurting anybody.

Regards,
Dan
[/quote]

Thanks Dan. Indeed, it seems I can't really win. Luckily I have fairly thick skin, so I'll carry on regardless.

One small correction: Supervertaler Workbench is free and open source, but Supervertaler for Trados is a paid plugin. I'm about to release Supervertaler for memoQ, which will also be paid – although a Supervertaler licence will cover both. I'm not introducing a separate licence for the memoQ version. I should also admit that I'm putting less time into the free Workbench these days, simply because I can't justify spending that much time on something I don't charge for. I work on Supervertaler seven days a week – before, during and after my actual translation work – so at some point I had to start asking for something in return.

And you're right that I enjoy tinkering. I do. But it isn't only that. Supervertaler started as a private project, and I quickly noticed it was genuinely speeding up my own work and helping me earn more. More to the point, it's what has kept me viable in an industry facing real difficulties. I've been doing this a long time, and I can remember getting €0.20 a word, no questions asked. Now I see €0.01 and €0.02 offered here on ProZ, which is frightening – and they don't just want 10,000 words by tomorrow morning, they want them flawless, in the most convoluted file formats imaginable, with three or four QA spreadsheets to fill in afterwards before you get paid. First it was machine translation, then MTPE, now AI, and at every step the LSPs have used it to push rates down further and add more hurdles. Without Supervertaler I couldn't take on half the work I accept these days, and I'd have lost a lot of it.

That's why I put it out there for free in the first place, and why, as it grew, I eventually had to start charging for parts of it.

Michael

Controlling Trados Studio from Claude chat (with Supervertaler for Trados)! | Why the sourness?

Dan Lucas — Thu, 10 Sep 2026 06:48:00 +0000

Forum: Supervertaler
Topic: Controlling Trados Studio from Claude chat (with Supervertaler for Trados)!
Poster: Dan Lucas
Post title: Why the sourness?

[quote]Jennifer Levey wrote:
In a word, "Why?"[/quote]
In two words, "Why not?"

Michael has built something and it may help other people. He is offering it, as far as I can see, for free.

Some people here are still working, but in a fading industry like this one it makes sense to pursue greater efficiency. Many of us are looking to invest resources in areas other than translation, and want to reduce our commitments of time and energy to the minimum.

Others are not working, and therefore their comments are no longer grounded in any kind of firsthand experience of today’s market.

Still others are not tool users, and will never make use of mechanisms like the one Michael has developed to help improve efficiency. That's fine - nobody is forcing them to engage.

I don't think I see this in other industries. Some carpenters find a way to retain the use of hand tools in their process, but there are very few carpentry businesses that don't have a table saw and a router somewhere in the mix. It doesn't appear to me that we look down on those carpenters in the way translators look down on users of CAT tools or AI.

On the one hand, some users of this forum praise Michael while at the same time making patronizing comments about the need for qualified people to be involved.

On the other hand, you get people like yourself, apparently struggling to restrain their contempt for those who try to improve their workflows, who accuse Michael of ego-tripping.

It seems to me that he can't win.

Has either side considered that Michael enjoys creating things, and that he might just be cheerfully trying to help others with the result of his efforts?

He's not hurting anybody.

Regards,
Dan

Supervertaler Workbench is no longer actively developed | Security concerns with MCP

Li-Hsiang Hsu — Thu, 10 Sep 2026 03:51:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Li-Hsiang Hsu
Post title: Security concerns with MCP

@Michael,

Your work is really impressive.

Just a kind reminder: MCP actually exposes user’s computer and data to greater risk of attack and data leaks if not configured properly. Because here, Claude acts not merely as a text generator, but as an operator of your system. And your MCP server is the bridge, providing Claude direct access to read your local files, execute terminal commands or interact with external APIs.

We generally recommend that MCP should be configured by a real qualified person or at least user should be assisted by someone really understands the process.

[Edited at 2026-09-10 03:52 GMT]

Controlling Trados Studio from Claude chat (with Supervertaler for Trados)! | @Michael

Jennifer Levey — Thu, 10 Sep 2026 00:09:00 +0000

Forum: Supervertaler
Topic: Controlling Trados Studio from Claude chat (with Supervertaler for Trados)!
Poster: Jennifer Levey
Post title: @Michael

Pardon my ignorance....

In a word, "Why?"

Apart from ego-tripping on the back of your 'vibe-coding' affliction, what does this contribute to our collective professional well-being?
JL

Supervertaler Workbench is no longer actively developed | Thanks!

Michael Beijer — Wed, 09 Sep 2026 23:20:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Michael Beijer
Post title: Thanks!

[quote]Li-Hsiang Hsu wrote:

That is a good sign of continuous improvement of your work!

Yes, save it as a permanent instruction to Claude (CLAUDE.md, AGENTS.md, project instructions, etc.) will certainly help, making future runs less likely to fail.

But it is not a silver bullet. We can't expect it to be magic, either. Some software engineers do that to prevent repeated mistakes but models, even the strongest ones, still struggle.

Because even with these guardrails, models like Fable, Opus or Sonnet can still repeat mistakes. There’s no guarantee. Skilled human’s oversight is still the most important part of that coding process.

Because here, LLMs reach their real limits - runtimes, executions, effects, outcomes, interactions, causal relations - dynamic patterns and temporal complexities of real-world execution are what they struggle to learn. They don’t learn from where they fail. They don’t know what really happens in a living world. They capture static patterns in text and code, but they don't truly grasp how that code behaves in a live, dynamic environment. And they are not close to learn that!

Sometimes, introducing another model, like Sol to review Fable or Opus’s code could be helpful but be mindful of inconsistencies introduced after review and correction. That will cause the code to break.

Faced with the limitations of LLMs, I believe that for the time being, the only viable way to ensure a reliable, long-term result is checks by qualified and skilled humans. I see no other alternative.

Contrary to all the marketing pitches that Anthropic and OpenAI are trying to sell us, even their strongest models aren't reliable enough to bypass human oversight.
[/quote]

I'm hoping to one day be able to hire an actual developer to help me. But for the time being, it's just me and Claude. Incidentally, I made a quick screencast showing how powerful the new Supervertaler MCP server is: I can now completely control Trados Studio from inside Claude chat, even from my mobile phone!

[url removed] + [url removed]

Controlling Trados Studio from Claude chat (with Supervertaler for Trados)!

Michael Beijer — Wed, 09 Sep 2026 22:55:00 +0000

Forum: Supervertaler
Topic: Controlling Trados Studio from Claude chat (with Supervertaler for Trados)!
Poster: Michael Beijer

I've just put up a screencast (9 minutes) showing the [b]Supervertaler MCP Server[/b] in action: Trados Studio 2026 driven from Claude's chat window. I'll hopefully be making better videos soon, but for now this will have to do.

MCP is the open standard that lets an AI application call tools inside another program. What makes this one different is that it talks to a [i]live[/i] Studio editing session rather than to project files sitting on disk, so you can ask about the document you actually have open – what is left to do, how you translated something before, what your termbase says for a term – and have it write drafts back into the grid for you to review.

The server itself runs on your own PC – there is no Supervertaler cloud in the middle, and nothing gets uploaded in advance. Claude only sees the parts it asks for, when you ask a question, exactly as if you had pasted them in yourself. Claude Desktop is the easiest client because there is a one-click extension for it, but ChatGPT's desktop app, Claude Code and Mistral's Vibe CLI all work.

And as I mentioned at the end of the video: you can do the same thing from your phone! Below is the same project, same document, asked from Claude's Android app, with Studio still running back at the desk.

[url] [url removed] [/url]

[img] [url removed] [/img]

[img] [url removed] [/img]

Michael

[Edited at 2026-09-09 23:08 GMT]

[Edited at 2026-09-09 23:20 GMT]

Supervertaler Workbench is no longer actively developed | You don’t give up, @Michael!

Li-Hsiang Hsu — Wed, 02 Sep 2026 04:58:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Li-Hsiang Hsu
Post title: You don’t give up, @Michael!

That is a good sign of continuous improvement of your work!

Yes, save it as a permanent instruction to Claude (CLAUDE.md, AGENTS.md, project instructions, etc.) will certainly help, making future runs less likely to fail.

But it is not a silver bullet. We can't expect it to be magic, either. Some software engineers do that to prevent repeated mistakes but models, even the strongest ones, still struggle.

Because even with these guardrails, models like Fable, Opus or Sonnet can still repeat mistakes. There’s no guarantee. Skilled human’s oversight is still the most important part of that coding process.

Because here, LLMs reach their real limits - runtimes, executions, effects, outcomes, interactions, causal relations - dynamic patterns and temporal complexities of real-world execution are what they struggle to learn. They don’t learn from where they fail. They don’t know what really happens in a living world. They capture static patterns in text and code, but they don't truly grasp how that code behaves in a live, dynamic environment. And they are not close to learn that!

Sometimes, introducing another model, like Sol to review Fable or Opus’s code could be helpful but be mindful of inconsistencies introduced after review and correction. That will cause the code to break.

Faced with the limitations of LLMs, I believe that for the time being, the only viable way to ensure a reliable, long-term result is checks by qualified and skilled humans. I see no other alternative.

Contrary to all the marketing pitches that Anthropic and OpenAI are trying to sell us, even their strongest models aren't reliable enough to bypass human oversight.

Supervertaler Workbench is no longer actively developed | PS: Supervertaler for memoQ is coming along nicely!

Michael Beijer — Tue, 01 Sep 2026 21:34:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Michael Beijer
Post title: PS: Supervertaler for memoQ is coming along nicely!

(better quality image @ [url removed] )

Supervertaler Workbench is no longer actively developed | Your Marz list is now a standing rule in my Claude setup

Michael Beijer — Tue, 01 Sep 2026 20:22:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Michael Beijer
Post title: Your Marz list is now a standing rule in my Claude setup

[b]@Li-Hsiang[/b] – that Nathan Marz list you posted was genuinely useful, so here's what I did with it.

I pasted it into Claude Code and asked it to store it in its persistent memory on my machine – a global instructions file it loads at the start of every session – with the standing rule that it must check its own work against that list whenever it writes code for me. So it's no longer a one-off prompt; it's now part of how it works on Supervertaler, every session.

The telling part: that same day, Claude had shipped me exactly two of the mistakes on the list – a per-row delete loop that was "fine at dev scale" and re-entered the UI thread. Fine at 5 rows; at 281 rows it froze Trados Studio for over a minute. I caught it by [i]using[/i] the software on real data, not by reading the code – which, as you rightly say, I can't do.

Which is my honest answer to your broader point. You're right that I can't spot these mistakes in a diff. What I [i]can[/i] do is make the tool police itself with lists like Marz's, test everything immediately on real termbases and real projects (which is how every serious bug this week was actually found), and make Claude state its assumptions out loud. After that freeze, I had it add another standing rule: whenever it ships code touching loops or state, it has to tell me what scale it was designed and tested for – "tested at 10, designed for 10,000" – so I can ask the one review question a non-programmer [i]can[/i] ask: "and what about my 12,000-term termbase?"

I'm not claiming this makes me Daisy. But the gap between an amateur steering Claude and an engineer steering Claude isn't fixed – some of it can be closed with process, and your list just became part of mine. ;-)

Supervertaler Workbench is no longer actively developed | I will certainly use Daisy's software...carried out by Claude

Li-Hsiang Hsu — Tue, 01 Sep 2026 10:14:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Li-Hsiang Hsu
Post title: I will certainly use Daisy's software...carried out by Claude

Faible, Sonnet, or Opus...it doesn't matter.

But not a software made by Claude piloted by a person with little programming knowledge.

Supervertaler Workbench is no longer actively developed | Here are some examples of mistakes non-programmers can't spot on

Li-Hsiang Hsu — Tue, 01 Sep 2026 09:42:00 +0000

Forum: Supervertaler
Topic: Supervertaler Workbench is no longer actively developed
Poster: Li-Hsiang Hsu
Post title: Here are some examples of mistakes non-programmers can't spot on

[url removed]

Fable's mistakes:
[quote] Nathan Marz wrote:

Some of the mistakes I've had to correct when coding with LLMs this week (mostly Fable):

- Complex and unnecessary dependency injection instead of using functions directly
- Hand-rolling encryption routines instead of using a library
- Keeping unnecessary state
- Not accounting for memory leaks in tracked state in failure cases
- Incomplete test coverage, especially on failure modes
- Grossly inefficient file handling because "it will work fine at dev scale"
- Overly complex locking schemes that were full of bugs
- Missed race conditions
- Unnecessary configs introduced prematurely

Had I not corrected the mistakes, every future iteration would keep compounding the structural and semantic problems. If you don't do this, it "works" until you realize the code is full of bugs, performs terribly, and can only be fixed with a rewrite.
[/quote]

[Edited at 2026-09-01 09:45 GMT]