I think it's a cool idea and I personally find using LLMs as a teaching tool to still be the most rewarding way of interacting with them, if done right.
Your obvious first port of call IMO is correctness of material, where there's room for improvement [1]. I deliberately picked Gleam because it's still a less known language.
For what it's worth, prompting Opus 4.6 in chat got me this result [2]. Sonnet 4.6 via the Workbench also got it right.
Agree with other comments about UX and design, and maybe also some of those around improving teaching style or gamification aspects, but the above is more important.
Yes, at the moment it's an issue of cost. I can't use the best models because it is not affordable. Hopefully as performance improves over the years this will become less of an issue. Maybe I can build in a websearch to verify info though...
I hear you. Yes, I think "seeding" an LLM with docs or other learning material is one of the fundamentals of effectively and efficiently using it for learning, maybe you can build more in that direction?
Yeah I actually started there. Https://dev.rebrain.gg has the old version up.
You upload a source and it generates questions from it. However when showing it to friends I found that the barrier to usage was too high as most people don’t have a source ready. But I think adding it as an option would be pretty cool and doable
If you are not using iCloud, you could try activating it (you get 5 gigs for free IIRC) and switching off everything besides the Voice Memos app. Then you should see the recording on your Mac, and should be able to export it from there. Definitely a shitty workaround, but you might be able to make it work?
Just ask LLM to write one on top of OpenRouter, AI SDK and Bun
To take your .md input file and save outputs as md files (or whatever you need)
Take https://github.com/T3-Content/auto-draftify as example
Yeah I’ve wondered about the same myself… My evals are also a pile of text snippets, as are some of my workflows. Thought I’d have a look to see what’s out there and found Promptfoo and Inspect AI. Haven’t tried either but will for my next round of evals
Great idea, great execution on your landing page (the onboarding experience is really well done) and great job on answering questions in this thread. Also, +1 on building a Firefox version.
Since I also have to use Chrome for an extension I'm developing, I pinned Tweeks and will likely reach for it every so often to actually test how well it does, but the demos definitely impressed me.
Out of curiosity, how much, if any, of this did you vibe code?
> Great idea, great execution on your landing page (the onboarding experience is really well done)
Thank you! As others pointed out here, we admittedly didn't invest much in the "landing page" aspect, but I did work hard to make a great onboarding experience. Glad it shined through
> Since I also have to use Chrome for an extension I'm developing
We're in the same boat, I wouldn't be using chrome if not for this extension. Great to see HN has a strong cohort of Firefox users!
> Out of curiosity, how much, if any, of this did you vibe code?
A lot of the elements of the extension, backend, and even the onboarding page integrations push at the boundaries of what tools like codex and claude code can do right now.
We do believe in the tech (in some regards, the extension is powered by similar tech), and we are power users of both, but we also know when claude code has said "You're absolutely right" one too many times and we need to dig in and get our hands dirty.
reply