Daily AI news from Hacker News · The Verge · arXiv.
Hacker News · AI 热议
- Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw · ⭐365 💬375
- Show HN: Travel Hacking Toolkit – Points search and trip planning with AI · ⭐24 💬5
- We replaced RAG with a virtual filesystem for our AI documentation assistant · ⭐241 💬102
- Run Linux containers on Android, no root required · ⭐44 💬11
- Post Mortem: axios NPM supply chain compromise · ⭐206 💬83
- Getting Claude to QA its own work · ⭐8 💬0
The Verge · AI News
- Anthropic essentially bans OpenClaw from Claude by making subscribers pay extra
- OpenAI’s AGI boss is taking a leave of absence
- Apple’s best product ever
- Chatbots are now prescribing psychiatric drugs
- PSA: Anyone with a link can view your Granola notes by default
arXiv · Latest Papers
- How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study
arXiv:2604.00005v1 Announce Type: new Abstract: Emotion plays an important role in human cognition and performance. Motivated by this, we investigate…
- One Panel Does Not Fit All: Case-Adaptive Multi-Agent Deliberation for Clinical Prediction
arXiv:2604.00085v1 Announce Type: new Abstract: Large language models applied to clinical prediction exhibit case-level heterogeneity: simple cases y…
- Open, Reliable, and Collective: A Community-Driven Framework for Tool-Using AI Agents
arXiv:2604.00137v1 Announce Type: new Abstract: Tool-integrated LLMs can retrieve, compute, and take real-world actions via external tools, but relia…
- A Safety-Aware Role-Orchestrated Multi-Agent LLM Framework for Behavioral Health Communication Simulation
arXiv:2604.00249v1 Announce Type: new Abstract: Single-agent large language model (LLM) systems struggle to simultaneously support diverse conversati…
Auto-generated by GitHub Actions · 2026-04-04