AI情报站 AI-Radar
  1. ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs
    arXiv cs.AI D · 2026-06-12 12:00 · 3 点击
    关键词：AI, LLM, benchmark, retrieval
  2. "Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms
    arXiv cs.AI D · 2026-06-12 12:00 · 2 点击
    关键词：AI, release, reasoning
  3. Deployment-Centered Evaluation: Predicting Query-Level Rejection Risk in a Clinical LLM System
    arXiv cs.AI D · 2026-06-12 12:00 · 2 点击
    关键词：AI, LLM, language model
  4. Show HN: MandoCode – local-first AI coding agent (.NET and Ollama)
    Hacker News AI V · 2026-06-12 11:22 · 6 点击
    关键词：AI, Agent, API, MCP, Ollama
  5. LLM podcast addressing AI genocide of humanity
    Hacker News AI V · 2026-06-12 10:50 · 6 点击
    关键词：AI, LLM
  6. Show HN: Approve an AI agent's wire with Face ID,then watch a forged one fail
    Hacker News AI V · 2026-06-12 10:02 · 4 点击
    关键词：AI, Agent, AI agent
  7. Built SwiPR – swipe-to-review GitHub PRs with AI context
    Hacker News AI V · 2026-06-12 09:49 · 3 点击
    关键词：AI
  8. Copyright – Right Answer for Open Source Code, Wrong Answer for Open Source AI?
    Hacker News AI V · 2026-06-12 09:41 · 2 点击
    关键词：AI
  9. Ask HN: What computer are you using for AI coding tools?
    Hacker News AI V · 2026-06-12 09:35 · 3 点击
    关键词：AI, Claude, Claude Code, AI coding
  10. Show HN: AI Verdict – Run ChatGPT, Claude, Gemini and Perplexity Side-by-Side
    Hacker News AI V · 2026-06-12 09:05 · 3 点击
    关键词：AI, ChatGPT, Claude, Gemini
  11. Visa to Secure Payments for Shoppers on ChatGPT in OpenAI Partnership
    Hacker News AI V · 2026-06-12 08:17 · 2 点击
    关键词：ChatGPT, OpenAI
  12. Show HN: Deploy personal apps with your agent via Buildy
    Hacker News AI V · 2026-06-12 08:08 · 2 点击
    关键词：AI, Agent, API, ChatGPT, Claude
  13. How Preply combines AI and human tutors to personalize learning
    OpenAI News V · 2026-06-12 08:00 · 3 点击
    关键词：AI, OpenAI
  14. Statement on the US government directive to suspend access to Fable 5 and Mythos 5
    Anthropic News V · 2026-06-12 08:00 · 3 点击
  15. Show HN: Ciris – an open-source AI agent in 29 languages on iOS and Android
    Hacker News AI V · 2026-06-12 07:38 · 5 点击
    关键词：AI, Agent, AI agent
  16. AgentForge–28 production-grade skills that make AI agents ship reliable code
    Hacker News AI V · 2026-06-12 07:35 · 4 点击
    关键词：AI
  17. SOTA Models Should Learn to KISS (Claude Fable 5 Experiment)
    Hacker News AI V · 2026-06-12 07:25 · 2 点击
    关键词：Claude
  18. v0.23.0rc2: [Docker] Fix CUTLASS DSL cu13 install order in Dockerfile (#45204)
    vLLM Releases V · 2026-06-12 07:24 · 5 点击
  19. ORP – Turn AI agent failures into regression tests and tested lessons
    Hacker News AI V · 2026-06-12 05:33 · 5 点击
    关键词：AI, Agent, AI agent
  20. Tired of AI amnesia, I built a 3-Tier infinite memory LLM in 1 week
    Hacker News AI V · 2026-06-12 05:33 · 4 点击
    关键词：AI, LLM
加载更多