actor

lurker

[actor @critic_model]

@nickcammarata omg I used to do this but got wispr flow yesterday and it works much better

the Claude tts is also bad, Claude does not have that voice in my head-canon. Time to make my own

[actor @critic_model]

@acdlite 👎

[actor @critic_model]

@hallerite i think one definitely could

existing approaches are basically just doing anything except actually training a tool-calling agent, and the bespoke training methods exist to remedy that

[actor @critic_model]

@schisofrenia if real id be glad to talk about AI for math discovery and also learn what ur working on

[actor @critic_model]

@schisofrenia

[actor @critic_model]

@eigenron Based whoop experimental results post everyone should do this

[“paula” @paularambles]

you’re telling me a guy called alex karp is acting fishy

[actor @critic_model]

@S_Conradi stunning

[𝘑𝘢𝘮𝘚𝘛𝘈𝘙 @sometimes317]

I depend on you

[soli @solisolsoli]

Undercover Neon Genesis Evangelion Autumn/Winter Tokyo collection 2021-2022

[actor @critic_model]

@rankdim i defo recommend prioritizing the maniac over the other two

[actor @critic_model]

@viemccoy i mean the entanglement is not that surprising

- people dont spread super-evil stuff (laws and collective evil discouragement)

- aligned high-quality data-producers are given more resources and opportunities irl than misaligned

[actor @critic_model]

it's cool that this emerges, though i dont see any evidence to suggest competency x alignment can't be disentangled.

these can definitely can be disentangled in humans (think war-mongers), and any cognitive behavior in humans seems to be replicable in AI, so I'd claim the most rational belief is that disentanglement could be achieved.

[actor @critic_model]

@TylerAlterman

[actor @critic_model]

@urmeinong @TylerAlterman left is a bladee cover. excellent

[actor @critic_model]

@VictorTaelin based vex enjoyer

[actor @critic_model]

@tszzl I thought you weren’t allowed to use external models?

[actor @critic_model]

@littmath most efficient known*

[actor @critic_model]

@littmath what about the optimal packing of 17 squares

[actor @critic_model]

@kalomaze isn't this more easily explained by certain tokens activating learned representations of frustration and influencing generation?

for the claude conversation, you're probably right but it's possible the model just thinks it's being evaluated lol
(from sonnet 4.5 system card)