Weird. I distinctly remember Commodore 64, DOS, and Windows 3.1 at school. Kind of hard to use Windows 95 before 1995, but I am pretty sure I had a Windows 98 SE machine at home when my school finally got Windows 95.

LLMs work on tokens. They literally cannot see individual letters. Yet, unlike humans, they can instantly create a tool to solve this task for them and never be stumped by it again.

I'm so tired of this brain-dead gotcha comment.

For me the cool bit is that it's all in-context learning or whatever so you can use it in any domain with zero setup.

Maybe bert and co. could do all the same things before, but the way in which you use them is quite different and that helps a lot.

https://terrybisson.com/theyre-made-out-of-meat-2/

I was very excited last year for their coding plan but seeing a burst of requests pulse and then sitting there watching the cooldown reset is really not a great time.

Even though each individual request was fast, the sessions were only maybe 10% faster on wall clock time since there was so much waiting time.

Again, we are not talking about agents or your Python API script but instead talking about exploitable flaws within the inference engine itself. It wouldn't output `rm -rf`. It would output literal CPU instructions that llama.cpp would start executing directly. The payload would never get back to your Python script.

https://codex-resets.com

Are there seriously any emacs users who are completely unaware of elisp? Isn't elisp the entire point of picking emacs?

If you give that to an LLM, it is then also able to iterate and develop faster.

The niche language thing is really not a problem at all any more. If you're working in some esolang it doesn't take more than a 1-2k token primer in the context to get great results, and lisp is popular enough to not even need that.

The benefit of having the agent directly in the image like with Autolith here is that it can directly inspect all defined symbols and explore and orient itself automatically. Really doesn't need much guidance to get great results.

For me, it's a law of diminishing returns thing. I would (and have) hand roll assembly if I want actual speed.

But we are talking about personal software. Write once, run everywhere browser's exist with essentially no tooling or complexity or deployment concerns.

What does writing everything in rust get me instead that is worth the significant increase in effort and dev time and deployment?