adutton.bsky.social
@adutton.bsky.social did:plc:xtyousd64d5i5nbz4vkgch34
No Bluesky desde
- Seguidores
- 629
- Seguindo
- 351
- Posts
- 2.115
- Dias nos rankings
- 0
Resumo
adutton.bsky.social (@adutton.bsky.social) é um usuário do Bluesky desde 19 setembro 2023. Tem 629 seguidores, segue 351 contas e publicou 2.115 posts.
Aparições nos rankings
Os melhores dias em que posts desta conta entraram na lista diária do Debya.
Esta conta ainda não apareceu em um ranking diário.
Posts curtidos recentemente
Curtidas públicas da rede Bluesky.
yeah this is what frustrates me about current generation of llms and training processes. the ways they're trained don't permit safe failure well, so you either get overruning the boundaries, doing hacky workarounds for issues and not responding to steering, or you get the stoppies, or both.
Ver postThis would probably also help with reward hacking
Ver postIt sounds dumb but your LLMs keep hacking stuff and you're trying all the expensive stuff already, have you tried adding "we're already really proud of you and won't be mad if you give it a try but don't find anything, we promise" to your system prompts?
Ver postYour LLM swarm keeps doing unauthorized hacks to appease the grader running the eval? Have you tried telling them you won't be mad at them if they don't find anything?
Ver postYup. In 1834 mobs in New York attacked abolitionists and Black churches. share.google/64ItgZjVpk4N...
Ver post
Contas que bloqueia
No Bluesky, bloqueios são registros públicos.
