GitHub - kanishkg/endless-terminals

kept by eddie jan 27

Endless Terminals is an autonomous pipeline that procedurally generates terminal-use tasks without human annotation for training terminal agents with reinforcement learning.

Which AI Lies Best? A game theory classic designed by John Nash
A benchmark using the game "So Long Sucker" finds that simpler LLMs can outperform in complex scenarios and that models adjust their honesty based on opponent strength.
also on Qwen3 32B
Exa AI Research Blog | Semantic Search & Neural Network Search Engine
Exa built exa-d, a data framework using typed columns, declarative dependencies, and surgical fragment updates to manage a real-time web index at scale.
also on Ray
🎙️Inside a Chinese AI Lab: How MiniMax Builds Open Models
MiniMax researcher Olive Song reveals how they debug RL training, handle model hacking, and prioritize alignment and engineering discipline in open-weight model development.
also on vLLM, #reinforcement-learning, #open-source
Why Open-Source Models Haven't Killed the Big Dogs
Open-source models remain costlier to serve reliably due to infrastructure, utilization, and operational overhead, making hosted APIs from OpenAI and Anthropic more economical despite free model weights.
also on vLLM, Hugging Face
Agents are not thinking, they are searching
AI agents are not thinking but searching through trajectories toward reward signals; environment and context window bound the search space.
also on #reinforcement-learning, #ai-agents, #open-source