Deschide articolul original într-un tab nou Schimbarea acestei opțiuni se aplică imediat și reîncarcă pagina.
LECTURA
Înapoi la articole →

I've been thinking

burtonye.github.io/index.xml
Vizitează site-ul

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 6

  1. I Wrote "NEVER STOP" and Went to Bed

    (I've been thinking)

    Karpathy has been posting about AutoResearch — pointing an agent at a research question, not a task list, and letting the experimental loop run.

  2. Which Models Actually Benefit From Prompt-Injected Experiences?

    (I've been thinking)

    The previous experiment ended with an unresolved anomaly.

  3. Can a Model Teach Itself With Prompts Instead of Gradients?

    (I've been thinking)

    The question I’ve been thinking about: can a LLM model, a stateless machine, teach itself?

  4. Hard Examples Are All You Need for GRPO

    (I've been thinking)

    This post summarizes a paper I co-authored with Benjamin Pikus and Pratyush Ranjan Tiwari.

  5. Reward Hacking in RLHF: What Can Go Wrong

    (I've been thinking)

    Reinforcement Learning from Human Feedback (RLHF) has become the dominant paradigm for aligning language models with human preferences.

  6. What is OpenAI's Operator Good For?

    (I've been thinking)

    Mar 2026 Update: Computer Use has gotten a lot better.