Generative AI

AgentBench: Evaluating LLMs as Agents

Evaluating Large Language Models (LLMs) as agents in interactive environments, highlighting the performance gap between API-based and open-source models, and introducing the AgentBench benchmark.

arxiv.org

DDarren LI

AgentBench: Evaluating LLMs as Agents

ElevenLabs || Prime Voice AI

beta.elevenlabs.io

sari

Because we are each an individual, infinitely complex being, our different physiological, environmental, and cultural variations bring us to infinite different endpoints. Like it or not, we all see the world slightly differently and our creative expressions reflect this.

View Profile • The A.I. Lie

SShachaf Rodberg

using AI should help us feel more human

The AI Unbundling

Ben Thompson stratechery.com

sari

"AI for wonder": An interview with Michelle Huang, artist

Michelle Huang newsletter.mem.ai

Jason Shen

Rytr · Best AI Writer, Content Generator & Writing Assistant

rytr.me

sari

Hassan Ragab | حسن رجب @hsnrgb

instagram.com

ssari

super interesting artist working in generative AI

Datasets as Imagination

Lila Shroff joinreboot.org

Sarah Drinkwater

There is an all out war for search supremacy right now between two trillion dollar companies, with one having everything to win and the other everything to lose. In those circumstances a standard VC model of buying growth does not work even if you have a huge war chest, as you will be outspent no matter how big your investors are.

As a founder of a... See more

Article

Peter Hagen