31–40 of 91 posts
Vibe coding is the opposite, not just depending on the chessboard, but depending on a couple of Gflops to even think.
Blindfolded programming would be the programming we do in the shower
Earlier quoted context omitted.
You learn a lot more by reading code than writing it. So reading the output i believe is an immensely big gift by an LLM, because if you actually take note - and of course know your skills - then ot becomes such a great pal to work with. I like reading what the LMM gives me, not always, but a lot of times.
> You learn a lot more by reading code than writing it. "You learn a lot more by reading trigonometry than by doing problems" See how ridiculous that sounds?
As long as the literature contains insights a reader isn't aware about, reading the literature is low-hanging fruit compared to having to derive all the things yourself.
As soon as the literature no longer contains insights, it becomes more productive to explore mathematics oneself by trial and error.
Organized education will model this on a topic by topic basis: during class you're handed the more valuable insights on a silver platter, during an exam you are prevented from looking at your textbook.
Every time you read a chapter and do the exercises it's a small simulacrum of catching low hanging fruit followed by making sure you can derive similar statements with trial and error for fixing any gaps. The trial and error while you do problems does improve your intuition, but only trial and error is like having every student redevelop the frontier starting from antiquity.
I'm not completely convinced by this comparison between blind chess and prompting LLMs. In blind chess you get deterministic information about the state of the board: each mental update to your board model can be precise, and you have the full state at every point in time. LLMs are notoriously non-deterministic, and even at temperature zero you still can't predict exactly where the weights will take you next. I suppo…
LLMs are notoriously non-deterministic, and even at temperature zero you still can't predict exactly where the weights will take you next. An LLM can be made to be completely deterministic. I use them in this mode so I can reproduce test cases. Of course it requires complete control over the model, etc. but this myth that a computer program is non-deterministic needs to end. You can 100% predict where the weights “wi…
Earlier quoted context omitted.
You learn a lot more by reading code than writing it. So reading the output i believe is an immensely big gift by an LLM, because if you actually take note - and of course know your skills - then ot becomes such a great pal to work with. I like reading what the LMM gives me, not always, but a lot of times.
> You learn a lot more by reading code than writing it. Really? In my experience it's been the opposite. It's like how you can learn more about art by trying to recreate it than just looking.
Earlier quoted context omitted.
LLMs are notoriously non-deterministic, and even at temperature zero you still can't predict exactly where the weights will take you next. An LLM can be made to be completely deterministic. I use them in this mode so I can reproduce test cases. Of course it requires complete control over the model, etc. but this myth that a computer program is non-deterministic needs to end. You can 100% predict where the weights “wi…
Floating point matrix calculations are non-deterministic. You need to invent new hardware, that doesn't use floating point math, first. [0] [0] https://arxiv.org/html/2506.09501
Is there anything new in this article? Yes, experts use AI better than non-experts for tasks in their domain. See LLMs reward expertise [1] and Terrance Taos conversation with LLM [2]. [1] https://www.seangoedecke.com/llms-reward-expertise/ [2] https://chatgpt.com/share/6a5fdc7a-d6f8-83e8-bbea-8deb42cfed...
I think the need for expertise is also going away. For example, when Claude made progress on the Riemann conjecture, > Jarred's input was mostly limited to sending Claude messages of encouragement (mostly variants of “keep going” or “believe in yourself”).2 This seems to have helped Claude overcome some initial skepticism that it could make meaningful progress. https://www.anthropic.com/research/riemann-zeta The full…
No, experts are still needed
Earlier quoted context omitted.
You learn a lot more by reading code than writing it. So reading the output i believe is an immensely big gift by an LLM, because if you actually take note - and of course know your skills - then ot becomes such a great pal to work with. I like reading what the LMM gives me, not always, but a lot of times.
> You learn a lot more by reading code than writing it. "You learn a lot more by reading trigonometry than by doing problems" See how ridiculous that sounds?
For most of us, writing code is the way to carve out intuition into an artifact. But, I have noticed some people are able to read deeply - and by that I mean, reverse the code to understand the intuition that brought it to life. This is a rare skill and I dont have it, but some do. Not just for code, but also for any book - fiction or non-fiction - some are able to deconstruct the scenarios much better than others, and in that sense understand what they read.
Earlier quoted context omitted.
I think the need for expertise is also going away. For example, when Claude made progress on the Riemann conjecture, > Jarred's input was mostly limited to sending Claude messages of encouragement (mostly variants of “keep going” or “believe in yourself”).2 This seems to have helped Claude overcome some initial skepticism that it could make meaningful progress. https://www.anthropic.com/research/riemann-zeta The full…
> Two mathematicians at Anthropic studied and validated Claude’s paper, and produced an informal note for experts stating Claude’s proof concisely. No, experts are still needed
You may notice that humans only checked the work and explained. You may also see that that the person prompting the AI, Jared of bun.js fame, is not a noted expert in mathematics.
This article reads like it was written by prompting AI for connections between two loosely connected things.
I'm not completely convinced by this comparison between blind chess and prompting LLMs. In blind chess you get deterministic information about the state of the board: each mental update to your board model can be precise, and you have the full state at every point in time. LLMs are notoriously non-deterministic, and even at temperature zero you still can't predict exactly where the weights will take you next. I suppo…
>you're going to end up with a system you don't 100% understand very quickly This has been my experience with all software projects. Even if I wrote all the code, my understanding of how everything works and fits together decays. ( See the Forgetting Curves https://en.wikipedia.org/wiki/Hermann_Ebbinghaus )
I guess the key thing is that you need to be able to demonstrate to yourself that you understand the code at least once, because that means you should be able to revise how it works in the future.
You also can't evaluate if a solution is fit for purpose if you don't understand it.