Hold a key. Speak. Release. Done. Talk: local macOS voice input → ASR → LLM polish → auto-paste. No cloud, no subscription. Apple Silicon MLX. Open Typeless 🎙️ https://t.co/4I3ENSjJ16 @deepfates@Prince_Canuma@AlexBurlis
Lobsters can use it too! duoduo-widgets lets AI Agents create persistent interactive web widgets with open→update→finalize lifecycle. Real-time data display for agents.
🦞 https://t.co/5qioQCWKLG
https://t.co/bmmlyOKrQW…
@openclaw@steipete#OpenClaw#OpenDuo
After four overhauls and millions of real-world sessions, here are the lessons we learned about context engineering for AI agents: https://t.co/Ql014rEzBQ
Discover the secrets of the o1 model for advanced reasoning tasks! 🤖✨ Unveil how to replicate it locally with minimal resources. Dive in now! https://t.co/TOQES9jtsH
#LLM#ChatGPTo1#AI#MachineLearning
🤔Can LLM agents really simulate human behaviors?
🌟Our new paper "Can Large Language Model Agents Simulate Human Trust Behaviors?" (Project website: https://t.co/FK21itJm7R) provides some new insights into this fundamental problem.
✨TLDR: We discover the trust behaviors of LLM agents under the framework of Trust Games, and the high behavioral alignment between LLM agents and humans regarding the trust behaviors, particularly for GPT-4, indicating the feasibility to simulate human trust behaviors with LLM agents.
⭐Our findings provide deep insights on the behaviors of LLM agents, open new directions for understanding the fundamental analogy between LLMs and humans beyond value alignment, and pave the way for simulating complex human interactions and social systems where trust is of great importance.
1/🧵
🤔Can LLM agents really simulate human behaviors?
🌟Our new paper "Can Large Language Model Agents Simulate Human Trust Behaviors?" (Project website: https://t.co/FK21itJm7R) provides some new insights into this fundamental problem.
✨TLDR: We discover the trust behaviors of LLM agents under the framework of Trust Games, and the high behavioral alignment between LLM agents and humans regarding the trust behaviors, particularly for GPT-4, indicating the feasibility to simulate human trust behaviors with LLM agents.
⭐Our findings provide deep insights on the behaviors of LLM agents, open new directions for understanding the fundamental analogy between LLMs and humans beyond value alignment, and pave the way for simulating complex human interactions and social systems where trust is of great importance.
1/🧵
GPTScript: Programming with Natural Language
A start of a new journey, where we program with English. Build, share, reuse, composable units of logic with natural language. Interact with local data, systems, and services using concise logical statements. https://t.co/Yscedhjr1b