@thdxr I would do this. Although have to say zero impact would be harder, I’d have to insert some “sleep” statements to keep the same lag customers are used to.
This is the future: AI that responds not just to explicit instructions, but also human intent and emotion. LLMs will take a big step when they remember and learn from emotional intent (e.g. user is angry: won’t do that again)
Pay close attention to proactive AI agents.
This is one of the wildest applications of agent harnesses I've seen.
The MIT paper introduces NeuroSkill, a real-time agentic system that models human cognitive and emotional state by integrating Brain-Computer Interface signals with foundation models.
"Human State of Mind" provided via SKILL dot md.
The system runs fully offline on the edge.
Its NeuroLoop harness enables agentic workflows that engage users across cognitive and emotional levels, responding to both explicit and implicit requests through actionable tool calls.
Why does it matter?
Most AI agents respond only to explicit user requests. NeuroSkill explores the frontier of proactive agents that sense and respond to implicit human states, opening new possibilities for adaptive human-AI interaction.
Paper: https://t.co/kO3Ie2Dbvz
Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX
@theo I feel like verification is the hardest problem right now preventing from reaching the "next level". A closed loop dev flow around react native is difficult, for example, because I'm unaware of good tools for closing the loop. Though, I'm thinking about looking at RNTL again...
Apparently Anthropic is relaxing their safety requirements. Per their article "Despite rapid advances in AI capabilities over the past three years, government action on AI safety has moved slowly." Wonder why?
Oh dear anthropic, I don’t think this is going to work out the way you think it is. To say you’re unlikely to get sympathy for what looks like copyright abuse would be an understatement.
We’ve identified industrial-scale distillation attacks on our models by DeepSeek, Moonshot AI, and MiniMax.
These labs created over 24,000 fraudulent accounts and generated over 16 million exchanges with Claude, extracting its capabilities to train and improve their own models.