Hacker News: frunkp

New comment by frunkp in "GPT-6 Astra, looped transformers, and hidden reasoning"

frunkp — Wed, 09 Sep 2026 19:46:01 +0000

When I saw "hidden reasoning", it reminded me of diffusion models: generating a block spans many steps (with remasking), which hide the reasoning that led to the block.

I had not heard of looped transformers, but the engineering behind the number of loops per token / halting feels like trying to apply a diffusion process to a transformer while keeping the auto-regressive feature.

New comment by frunkp in "1D Chess"

frunkp — Fri, 10 Apr 2026 20:10:29 +0000

Those who play go may enjoy the variants: https://www.govariants.com/variants/rules-list Tetris is a fun one to try!

Anna's Archive perd son domaine en .org mais reste debout

frunkp — Thu, 22 Jan 2026 07:22:07 +0000

Article URL: https://korben.info/annas-archive-domaine-org-suspendu.html

Comments URL: https://news.ycombinator.com/item?id=46716232

Points: 1

# Comments: 1

NN Interpretability

frunkp — Fri, 14 Nov 2025 10:23:11 +0000

Article URL: https://openai.com/index/understanding-neural-networks-through-sparse-circuits/

Comments URL: https://news.ycombinator.com/item?id=45925606

Points: 2

# Comments: 0

New comment by frunkp in "Kimina-Prover: Applying Test-time RL Search on Large Formal Reasoning Models"

frunkp — Thu, 10 Jul 2025 14:22:21 +0000

The model does well on highschool competition maths. Problems in the "Set Theory" and "Natural Numbers" chapters of Elements of Abstract Algebra may be doable with Kimina-Prover, nothing beyond because it doesn't know Sylow theorem etc. and hasn't used these objects with Lean 4 in practice.

You can start with a natural language description of the theorem: demo.projectnumina.ai and an autoformalizer will generate the formal statement. It's an additional click of a button to have it attempt to prove it.

For natural language interpretation of Lean proofs, the current LLMs (o4-mini-high, Claude 4, Gemini 2.5 Pro) do a decent job of walking you through.

Kimina-Prover: Applying Test-time RL Search on Large Formal Reasoning Models

frunkp — Thu, 10 Jul 2025 13:21:14 +0000

Article URL: https://huggingface.co/blog/AI-MO/kimina-prover

Comments URL: https://news.ycombinator.com/item?id=44520720

Points: 3

# Comments: 2