cacio-e-pepe

13 karma · joined July 21, 2026

submissions comments

cacio-e-pepe··on Finite time blowup for an averaged three-dimensional Navier-Stokes equation (2014)

Could you expand? Curious.

cacio-e-pepe··on Finite time blowup for an averaged three-dimensional Navier-Stokes equation (2014)

relevant: https://mathstodon.xyz/@tao/117219101339291693

cacio-e-pepe··on Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong

Nice, looking forward to the report.

And thanks, huge pasta fan :)

cacio-e-pepe··on Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong

> So we did mechanistic studies on small models, Gemma 4 particularly, and found the hidden state for different layers carry meaningful self-awareness signal for various situations.

Neat! Just to make sure I understand - you trained your probe layer to take this hidden state and predict p(wrong)?

Curious to learn more. Any more info on your approach (esp the mechanistic study)?

cacio-e-pepe··on OpenAI and Hugging Face address security incident during model evaluation

Honestly, stellar performance by the model at the capability being measured.

cacio-e-pepe··on Show HN: I left Figma to build a diffusion-based UI design tool

Okay so the diffusion model generates image assets, and you iterate on those, and then another model turns your favorites into code, is that right?

cacio-e-pepe··on Show HN: Ave, a behavioral classification standard for agentic AI

Looks interesting. I'm a bit too busy to read the docs, but I'm curious - how does it work?

cacio-e-pepe··on Show HN: Autoretrieval – Autoresearch for RAG Pipelines

What are the core knobs for a RAG pipeline? See any interesting patterns? Eg in practice, what did the agents tend to tune? Did domain matter?