New Paper: Stanford researcher (@joon_s_pk) discovers how to clone human personalities and inject them into AI Agents đź§
This builds on last year's paper which put 1000's of fully automated agents in a simulated town.
The results are wild. 👇 https://t.co/IpG4R9sfcQ
Chat with LLMs to analyze your internal data 🤯
Simply connect your database to SOTA LLMs like GPT-4o, Claude Opus, Google Gemini or Llama-3 and generate for on-the-fly dashboards.
Best part? Access all of these LLMs in a single playground with just $10 a month. https://t.co/LOiJvXvo9K
IMO @AnthropicAI is very close to making a breakthrough in productizable interpretability.
For ~4 years all we've had to really control LLMs is temperature/top_p and logit bias. We recently got `seed` and constrained structured output, with `interactive=false` on the way.
But now Claude... See more
Arc is making a whole new layer on top of the internet. Super interesting stuff
“we auto create APIs based on structured data from webpages and applications. "if you can see it then we can create an API for it."”
Great little write-up on Copilot Workspace that really differentiates from the rest of the market: https://t.co/bfvbYjpEa0
> Among all the talk of “agents”, this need to design for this repeated AI-human divergence and alignment can be lost. If the AI is going to take steps towards a solution, it must “take the human... See more
1/ I finally read Leopold Aschenbrenner's essay series on AI: Situational Awareness
Everyone, regardless of your interest in AI, should read this.
I took notes, they're sloppy but figured I'd share.
Welcome to the future: https://t.co/8WmDNvylrz