adutton.bsky.social
@adutton.bsky.social did:plc:xtyousd64d5i5nbz4vkgch34
En Bluesky desde el
- Seguidores
- 629
- Siguiendo
- 351
- Posts
- 2.115
- Días en rankings
- 0
Resumen
adutton.bsky.social (@adutton.bsky.social) es un usuario de Bluesky que se unió el 19 septiembre 2023. Tiene 629 seguidores, sigue a 351 cuentas y ha publicado 2.115 posts.
Apariciones en rankings
Los mejores días en que los posts de esta cuenta entraron en la lista diaria de Debya.
Esta cuenta aún no ha aparecido en un ranking diario.
Posts que le gustaron recientemente
Me gusta públicos de la red 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
Cuentas que bloquea
En Bluesky los bloqueos son registros públicos.
