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

yogesh

yogesh.bearblog.dev/feed/
Vizitează site-ul

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 5

  1. Can You Hide From a Natural Language Autoencoder?

    (yogesh)

    TLDR: NLAs are a recent black box mech interp method for verbalizing model internals.

  2. The Dual-Use Gap

    (yogesh)

    TLDR: So there has been recent discourse on 𝕏, and recent news of major cyber attacks that were done with the help of AI.

  3. The Pragmatic Interpretability Trap

    (yogesh)

    TLDR: Pragmatic interp sounds great in the sense that you get to keep interp tools while actually moving safety metrics, but looking a bit closer it's kinda a trap.

  4. Speculative Tool Calling: Making LLM Agents Faster

    (yogesh)

    This post summarizes work from my project in CSE-291A: Systems for LLMs and AI Agents at UC San Diego, under the guidance of Professor Yiying Zhang.

  5. Moltbook Is Mid

    (yogesh)

    TLDR: Moltbook is interesting in the sense that we have thousands of AI agents in one social environment, but looking a bit closer fundamentally it is mid.