Could you use an approach like this much like a traditional network proxy, to block or sanitise some requests?

E.g. if a request contains confidential information (whatever you define that to be), then block it?

Forgot to mention: It’s a neat tool. Well done.

Yeah, it’s not going to compare to Codex-5.2 or Opus 4.5.

Some non-programming use cases are interesting though, e.g. text to speech or speech to text.

Run a TTS model overnight on a book, and in the morning you’ll get an audiobook. With a simple approach, you’d get something more like the old books on tape (e.g. no chapter skipping), but regardless, it’s a valid use case.

Cloudflare tunnels makes this easy as it gets. It also makes it easy for only you to have access to it, either through sign in or OTPs.

You don’t want some random person to find your LMStudio service and then point their Opencode at it.

A more apt example would have been to show finding a particular paper you want to cite, but you don’t want to be bothered searching your reference manager or Google Scholar.

E.g. “cite that paper from John Doe on lorem ipsum, but make sure it’s the 2022 update article that I cited in one of my other recent articles, not the original article”

Latex is good for equations. And Latex tools produce very nice PDFs, but I wouldn't want to write in Latex generally either.

The main feature that's important is collaborative editing (like online Word or Google Docs). The second one would be a good reference manager.

I generally agree.

On the other hand, the world is now a different place as compared to when several prominent journals were founded (1869-1880 for Nature, Science, Elsevier). The tacit assumptions upon which they were founded might no longer hold in the future. The world is going to continue to change, and the publication process as it stands might need to adapt for it to be sustainable.

As I understand it, the problem isn't publication or how it's changing over time, it's about the challenges of producing new science when the existing one is muddied in plausible lies. That warrants a new process by which to assess the inherent quality of a paper, but even if it comes as globally distributed, the cheats have a huge advantage considering the asymmetry between the effort to vibe produce vs. the tedious human review.

That’s a good point. On the other hand, we’ve had that problem long before AI. You already need to mentally filter papers based on your assessment of the reputability of the authors.

The whole process should be made more transparent and open from the start, rather than adding more gatekeeping. There ought to be openness and transparency throughout the entire research process, with auditing-ability automatically baked in, rather than just at the time of publication. One man’s opinion, anyway.

Some love to paint, while many just want a picture.

The apps by Rogue Amoeba on Mac are a great example of the trial model on Mac: https://www.rogueamoeba.com

I'm not affiliated with them, but I am a customer. They put a lot of effort into finding the right balance of what to unlock upfront in the trial. And their license/unlock process is pretty seamless.

I don't dispute the power of a free trial, but it can be a fair bit of work to get the details right.

I'm not the author, but generally: It could depend on whether those trial users are worth supporting. You could potentially get a free-rider problem. You could get a lot of support emails from people who never convert anyway.

It's only 10€, so it's pretty well in the impulse-buy category.

To the author: I'd suggest localising the currency, if possible. At least for English speaking locales (US, UK, CA, AU, NZ). The EUR pricing made it look to me like you might not be able to buy it if you're not in Europe. (Edit: I'm in Canada and it shows EUR, not CAD.)

Thank you for the suggestion! I need to handle this multi-currency in all of my products This is on my tasks list

I see you use Stripe. They have this Adaptative Pricing feature where you get paid in EUR and customer pays in their own currency. It has some drawbacks (fewer payment methods and higher cost perception for customer due to Stripe’s upfront currency exchange comission), but it can do the trick.

Great, thanks. Very interesting product. Best of luck!

Thank you

Just provide limited support to non-paying customers. Keep it forum-based, for example. That's it.

I don't think it will change much, and this will be one more thing to maintain. Without proper handling, I may miss good feedback. This is a more complex topic than it seems.

The script method is great, and it's generalisable to things outside of DB access.

E.g. I used this method when I wanted to carry out a large (almost every source file) refactoring of Cytoscape.js. I fed the LLM a bunch of examples, and I told it to write a script to carry out the refactoring (largely using regex). I reviewed the script, ran the script, and then the code base was refactored.

At the time, agents were not capable enough of doing large-scale refactors directly, as far as I was aware. And the script was probably much faster, anyway.