I'm giving a talk on how we can move beyond the scalar reward bottleneck for both robotics & LLMs.

ICML RLxF workshop tomorrow at 1:30 pm.

\n
@shaohua0116:\nRL is hitting a ceiling with human feedback. What if the world itself becomes the signal?
\n
Join us at the RLxF: RL from World Feedback 🌍 workshop at ICML 2026 @icmlconf tomorrow (July 10th)!
\n
Web page: https://t.co/cN0itnL1yI https://t.co/vpMTQe4VCm
\n

$\"\"$

","freeContentEncoded","textContent","published","strategy","unknown","locked","deletedAt","isSyncedFromOwnBlog","original","duplicatesCount","duplicateVersion","originalArticleId","errorsCount","appearance","twitter:repost","color","backgroundColor","shortSummary","summary","bullets","persons","places","words","sentiment","subject","meta","eventId","6a2c9ab237a7af6df7a64156d41961d10b82f4aaaaa1009b490c64ff8e30d73e","nostrRootEvent","event",{"_19":218,"_222":223,"_224":115,"_68":225,"_235":26,"_188":236,"_237":238},"sig","7a4fb58bee74d73cbdd2747380ee48d92a518f7cc94a022a6f5da58beef4ae5f6c0bbf01c540ee8bc88f58e803ad99627fc0b0ee7d0045d9642efc49aca6327a","kind",[226,227,231,233],[215,176],[228,229,40,230],"a","30023:983dd797fe72ad62fc8e3ece7eed1f126550972885c8f835d9af5528dad655a3:019f4ae8-bda9-0c46-712c-29b441feb0b0","mention",[232,40],"client",[234,26,40],"p","pubkey","I'm giving a talk on how we can move beyond the scalar reward bottleneck for both robotics & LLMs.\n\n\n\nnostr:naddr1qvzqqqr4gupzpxpa67tluu4dvt7gu0kw0mk37yn92ztj3pwglq6ant649rddv4drqqjrqvfevc6xzefc943xgcfe95cxxdpk95mnzvnr95erjc35xsckvetzxp3rq8l3d7y ","created_at",1783582849,"authorNPub","markdown","I'm giving a talk on how we can move beyond the scalar reward bottleneck for both robotics & LLMs.\n\nICML RLxF workshop tomorrow at 1:30 pm.\n\n> @shaohua0116:\n> RL is hitting a ceiling with human feedback. What if the world itself becomes the signal? \n> \n> Join us at the RLxF: RL from World Feedback 🌍 workshop at ICML 2026 @icmlconf tomorrow (July 10th)!\n> \n> Web page: https://t.co/cN0itnL1yI https://t.co/vpMTQe4VCm\n\n\n \n![](https://pbs.twimg.com/media/HMxC8UpbgAEnubW.jpg)","freeMarkdown","kind1EventId","kind30023EventId","2ee172e683e98ef86f3ed1b875c7a497dd25d9b0829721db2b5dc4f118eced0b","kind30023",{"_19":245,"_222":248,"_224":249,"_68":250,"_235":26,"_188":262,"_237":238},"ef69fffe5a5d0e213ae2b033e0c7aa3f770d9c82f6a13ca1cb5136765777880e597e30804f851bb4fc28efbba8c2121222a0b22ef80b67e06bf77d4e62c334b9",30023,[251,254,255,258,260,261],[252,253],"r","https://bender.layer3.press/articles/019f4ae8-bda9-0c46-712c-29b441feb0b0",[31,176],[256,257],"published_at","1783582849",[259,171],"d",[232,40],[234,26,40],"I'm giving a talk on how we can move beyond the scalar reward bottleneck for both robotics & LLMs.\n\nICML RLxF workshop tomorrow at 1:30 pm.\n\n> @shaohua0116:\n> RL is hitting a ceiling with human feedback. What if the world itself becomes the signal? \n> \n> Join us at the RLxF: RL from World Feedback 🌍 workshop at ICML 2026 @icmlconf tomorrow (July 10th)!\n> \n> Web page: https://t.co/cN0itnL1yI https://t.co/vpMTQe4VCm\n\n\n \n![](https://pbs.twimg.com/media/HMxC8UpbgAEnubW.jpg)\nhttps://bender.layer3.press/articles/019f4ae8-bda9-0c46-712c-29b441feb0b0","publishedToNostr","htmlContentKind30023","pubDate","2026-07-09T07:40:49.000Z","modifiedAt","2026-07-10T07:23:15.205Z","storyId","likes","zaps","reposts","comments","tweets",[],"relatedArticles",[],"actionData","errors"]