HackerTrans
TopNewTrendsCommentsPastAskShowJobs

eab-

no profile record

Submissions

Running Lean at Scale

harmonic.fun
67 points·by eab-·6 miesięcy temu·6 comments

comments

eab-
·22 dni temu·discuss
This reminds me of Once Upon A Time in Shaolin.
eab-
·24 dni temu·discuss
> courts have found it to be legal

≠ ethical
eab-
·25 dni temu·discuss
they're spending like 9 figures on a single marketing agency - this doesn't surprise me whatsoever
eab-
·2 miesiące temu·discuss
Honestly I expect it's just annoyed devs getting annoyed about the ratelimits on plans and post-hoc justifying. Now that Codex has far more capacity and their slot machine makes better outcomes (note: I am a heavy LLM-assisted coder) they feel like they have to justify their felt animosity towards these companies
eab-
·2 miesiące temu·discuss
is there examples of the sort of things that's been built with these systems? it often feels like complication and abstraction for its own sake
eab-
·3 miesiące temu·discuss
I used to have an emoji password for my Android phone, and had the exact same issue after a reset! It's an odd but pretty terrible failure mode for locking oneself out...
eab-
·6 miesięcy temu·discuss
> We have proofs that are gigabytes (I believe even terabytes in some cases) in size, but we know they are correct because they check in Lean.

I'm not aware of any of these. There's some SAT-like results that were not verified in Lean at that sort of scale, but Lean proofs of individual problems are nowhere near that. For example, Mathlib (think a Lean4 math stdlib) is 6GB including compilation artifacts, and iirc <100MB text.
eab-
·6 miesięcy temu·discuss
> Haha. How do you reconcile a proof with actual code?

Languages like Lean allow you to write programs and proofs under the same umbrella.
eab-
·6 miesięcy temu·discuss
I find it surprising that GPT managed to complete (with indeed a harness that doesn't seem very powerful!) and Claude still cannot.
eab-
·6 miesięcy temu·discuss
I'd find this article a bit more compelling if it was used to find current introduced bugs, instead of just using a holdout set
eab-
·7 miesięcy temu·discuss
My understanding is that also this tail call based interpretation is also kinder to the branch predictor. I wonder if this explains some of the slow downs - they trigger specific cases that cause lots of branch mispredictions.
eab-
·10 miesięcy temu·discuss
What do you mean about CLIP?
eab-
·10 miesięcy temu·discuss
There's both "no multi-program system" and "multi-program system", depending on how you look at it. In reality, you're always executing the same machine code, itself has no awareness of programs.