Hacker Newsnew | past | comments | ask | show | jobs | submit | ImJasonH's commentslogin

Checkpoints sounds like an interesting idea, and one I think we'll benefit from if they can make it useful.

I tried a similar(-ish) thing last year at https://github.com/imjasonh/cnotes (a Claude hook to write conversations to git notes) but ended up not getting much out of it. Making it integrated into the experience would have helped, I had a chrome extension to display it in the GitHub UI but even then just stopped using it eventually.


Ah you were 7mo ahead of me doing the same and also coming to a similar conclusion. The idea holds value but in practice it isnt felt.

https://github.com/eqtylab/y


What are they actually “checkpointing”? Git already “checkpoints” your code and they can’t time travel your LLM conversation.

I thought the use of AI in the Secret Invasion title sequence was actually really appropriate, even "meta", maybe even a bit ahead of its time.

The seemingly purposeful AI style made it seem unnatural (on purpose), and like a facsimile of an otherwise trustworthy thing (on purpose), which was exactly in line with the idea of the show.

The execution of that show and that idea was pretty bad, but one of the few positives of it was, to me, an example of using AI art overtly, and leaning into its untrustworthy nature.


Early in one of the conversations Gemini actually proposed a Lisp-like language with S-expressions. I don't remember why it didn't follow that path, but I suspect it would have been happy there.


I hope I didn't give the impression that I thought this language was ready to be put into commercial planes. :)

This was the result of an afternoon/evening exploring a problem space, and I thought it was interesting enough to share.


The comment was sarcastic, hence the "/s" at the end of the first sentence.

Everything else was a thought experiment to show how the idea of LLMs on everything including commercial planes is a very bad idea and would give regulators a hard time.

The point is: just because you can (build and run anything) does not mean you should (put it on commercial planes).


I don't disagree at all. :)

This was mainly an exercise in exploration with some LLMs, and I think I achieved my goal of exploring.

Like I said, if this topic is interesting to you and you'd like to explore another way to push on the problem, I highly recommend it. You may come up with better results than I did by having a better idea what you're looking for as output.


I tried a thread, I got that both LLMs and humans optimize for the same goal, working programs, and the key is verifiability. So it recommended Rust or Haskell combined with formal verification and contracts. So I think the conclusion of the post holds up - "the things that make an LLM-optimized language useful also happen to make them easier for humans!"


Fixed the loom link!


Yeah fwiw I agree. I was impressed at how well the agents were able to understand and write their invented language, but fundamentally they're only able to do that because they've been trained on "similar" code in many other languages.


I just want to say I love this idea and execution. Great work, please make more :)


The Shining, by Steven King

It's one of my favorites of his, and I can see why he's miffed that Kubrick's adaptation gets all the praise when the source material is just as good.

There's nothing like a slow creeping horror descent into madness to make winter time feel cozy.



Comments moved thither. Thanks!


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: