conv.

← The whole story
AI
Sean Goedecke debunks "superhuman" LLM weight-editing claims

Goedecke argues the results are not genuinely superhuman

1 Nov 2 3:00 PM · 5d ago · 1 article · 1 source · development 1 of 2

Sean Goedecke publishes a technical analysis rejecting the paper's framing. He argues that identifying games from activation heatmaps is straightforward visual pattern-matching, and that Astra's weight-editing approach—using steering and ablation—matches the standard methodology any competent ML researcher would deploy.

“A smart human ML researcher could perform all of these tasks.”

Sean Goedecke

Sean Goedecke ML researcher and analystGPT-6 Astra Frontier LLM model

The whole story articlesposts the bright band is this development · numbered dots are the others · click one to jump

Peak 3 pieces in two hours at Nov 3, 8 AM; 15 pieces over 6 days (2 articles · 3 posts · 10 comments) Nov 2, 2 PM — 2 pieces · 2 articles — Newswires 2Nov 2, 4 PM — 2 pieces · 2 posts — Hacker News 1, Mastodon 1Nov 2, 6 PM — quietNov 2, 8 PM — 2 pieces · 2 comments — Hacker News 2Nov 2, 10 PM — 1 piece · 1 comment — Hacker News 1Nov 3, 12 AM — quietNov 3, 2 AM — quietNov 3, 4 AM — quietNov 3, 6 AM — quietNov 3, 8 AM — 3 pieces · 3 comments — Hacker News 3Nov 3, 10 AM — 3 pieces · 1 post · 2 comments — Hacker News 2, Bluesky 1Nov 3, 12 PM — 1 piece · 1 comment — Hacker News 1Nov 3, 2 PM — quietNov 3, 4 PM — quietNov 3, 6 PM — quietNov 3, 8 PM — quietNov 3, 10 PM — quietNov 4, 12 AM — quietNov 4, 2 AM — quietNov 4, 4 AM — quietNov 4, 6 AM — quietNov 4, 8 AM — quietNov 4, 10 AM — quietNov 4, 12 PM — quietNov 4, 2 PM — 1 piece · 1 comment — Hacker News 1Nov 4, 4 PM — quietNov 4, 6 PM — quietNov 4, 8 PM — quietNov 4, 10 PM — quietNov 5, 12 AM — quietNov 5, 2 AM — quietNov 5, 4 AM — quietNov 5, 6 AM — quietNov 5, 8 AM — quietNov 5, 10 AM — quietNov 5, 12 PM — quietNov 5, 2 PM — quietNov 5, 4 PM — quietNov 5, 6 PM — quietNov 5, 8 PM — quietNov 5, 10 PM — quietNov 6, 12 AM — quietNov 6, 2 AM — quietNov 6, 4 AM — quietNov 6, 6 AM — quietNov 6, 8 AM — quietNov 6, 10 AM — quietNov 6, 12 PM — quietNov 6, 2 PM — quietNov 6, 4 PM — quietNov 6, 6 PM — quietNov 6, 8 PM — quietNov 6, 10 PM — quietYesterday, 12 AM — quietYesterday, 2 AM — quietYesterday, 4 AM — quietYesterday, 6 AM — quietYesterday, 8 AM — quietYesterday, 10 AM — quietYesterday, 12 PM — quietYesterday, 2 PM — quietYesterday, 4 PM — quietYesterday, 6 PM — quietYesterday, 8 PM — quietYesterday, 10 PM — quietToday, 12 AM — quietToday, 2 AM — quietToday, 4 AM — quietToday, 6 AM — quietToday, 8 AM — quiet 1–2
1–2Goedecke argues the results are not…
Nov 3Nov 4Nov 5Nov 6yesterdaynow · 9:15 AM ET

What was reported 1 claim about this development

  1. 1 outlet MIT Researchers Show LLMs Can Read and Edit Neural Network Weights Without Retraining

    first by AIM, 5d ago

    1 more headline

All 2 developments of Sean Goedecke debunks "superhuman" LLM weight-editing claims →

NewswiresHacker NewsMastodonBluesky