Just saw this in an agent's output as it was coding stuff. That '../../../' thing would have bothered me enough to spend an afternoon fixing back in the day. Now I don't care at all. What a beautiful world we live in now.

I don't use AI for everything, just stuff that matters.

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: arxiv.org/abs/2603.03212 Learn to build effective AI agents in our academy: academy.dair.ai/

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.

MIT just published a paper that quietly explains why LLM reasoning hits a wall and how to push past it. The usual story is that models fail on hard problems because they lack scale, data, or intelligence. This paper argues something much more structural: models stop improving because the learning signal disappears. Once a task becomes too difficult, success rates collapse toward zero, reinforcement learning has nothing to optimize, and reasoning stagnates. The failure isn’t cognitive, it’s pedagogical. The authors propose a simple but radical reframing. Instead of asking how to make models solve harder problems, they ask how models can generate problems that teach them. Their system, SOAR, splits a single pretrained model into two roles: a student that attempts extremely hard target tasks, and a teacher that generates new training problems. The catch is that the teacher is not rewarded for producing clever or realistic questions. It is rewarded only if the student’s performance improves on a fixed set of real evaluation problems. No improvement means zero reward. That incentive reshapes everything. The teacher learns to generate intermediate, stepping-stone problems that sit just inside the student’s current capability boundary. These problems are not simplified versions of the target task, and strikingly, they do not even require correct solutions. What matters is that their structure forces the student to practice the right kind of reasoning, allowing gradient signal to emerge even when direct supervision fails. The experimental results make the point painfully clear. On benchmarks where models start with zero success and standard reinforcement learning completely flatlines, SOAR breaks the deadlock and steadily improves performance. The model escapes the edge of learnability not by thinking harder, but by constructing a better learning environment for itself. The deeper implication is uncomfortable. Many supposed “reasoning limits” may not be limits of intelligence at all. They are artifacts of training setups that assume the world provides learnable problems for free. This paper suggests that if models can shape their own curriculum, reasoning plateaus become engineering problems, not fundamental barriers. No new architectures, no extra human data, no larger models. Just a shift in what we reward: learning progress instead of answers.

Managers have been vibe coding forever by @thekitze :D

Dishwasher updates pt. 3 w/@PlumberJohnn #dishwasher #kitchentech

New dishwasher updates w/ plumerjohn #dishwasher

So this morning I rolled out of bed and saw this post from Guillermo. My first thought? "Damn, that looks sick!" And the best part? It's actually super easy to recreate with @shadcn. Greetings to the guy who claims every shadcn/ui project looks the same - catch this! 👋 Watch in fullscreen ⬇️