@willccbb @yacinelearning @karpathy reward going down is like loss going down no ?
will brown@willccbb
@yacinelearning @karpathy autoresearch but the training perf gets worse every iteration
2:53 PM · Jun 9, 2026 · 239 Views
Sami Jaghouar of Prime Intellect questions reward signals as automated research loops show progressive performance degradation
Automated feedback loops currently degrade performance instead of optimizing it.
122451085.2K
Sentiment
Sentiment building, check back later.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS436
am.will@LLMJunky
@willccbb @yacinelearning @karpathy 🤣
3hViews 436Likes 2
LIKES9
Noah Ziems@NoahZiems
@willccbb @yacinelearning @karpathy This is exactly what hiring phd interns are for. They've automated my job away
2hViews 186Likes 9
RETWEETS10
will brown@willccbb
@yacinelearning @karpathy autoresearch but the training perf gets worse every iteration
3hViews 5.3KLikes 238Bookmarks 8
q@gradientdespair
@willccbb @yacinelearning @karpathy AutoDegradation by Anthropic. Thanks @karpathy
3hViews 125Likes 3
Golden Hippie@gamestoneai
@willccbb @yacinelearning @karpathy AI impostor syndrome. Model sandbags its own training runs.
2hViews 120
Venkat — inference & RL/acc@venkat_systems
@willccbb @yacinelearning @karpathy
2hViews 95
Trash Panda 🦝@trashpandaemoji
@willccbb @max_paperclips @yacinelearning @karpathy I would just simply do the opposite.
2hViews 57
arXiv Bangers@arXivBangers
@willccbb @yacinelearning @karpathy B-Banger…
1hViews 14Likes 1
chris@candyflipline
@willccbb @yacinelearning @karpathy wait that would be hilarious
2hViews 39
vincenzo@alargemike
@willccbb @max_paperclips @yacinelearning @karpathy that’s right
1hViews 9