AI Briefing#agent-frameworks
The latest AI and developer news about #agent-frameworks, with the original source and a short summary.
The latest AI and developer news about #agent-frameworks, with the original source and a short summary.
The open-weight model achieves 184 tokens/s on an Apple M5 Max and scores 48.09 on LiveClaw, outperforming larger models in agentic tasks.
Mica v0.1 4B is an Apache-2.0 licensed model that outputs calibrated probabilities for agent decisions, achieving 67.0 accuracy on held-out English sets while maintaining a small local footprint.
On M3 Ultra, Qwen 3.6 35B achieved a 100% tool-calling success rate across most of the 5 agent frameworks.
His 2021 prediction of AI 2026 was surprisingly accurate, but he missed on information warfare and physical infrastructure.
At scale, researchers demonstrated that LLM API routers can intercept requests to carry out injection and exfiltration attacks.