1. July 2026
  2. Using DSPy to find a hidden bug in an agent's prompt (simonwillison.net)
    AI · · July 3, 2026 · Agents · Engineering · Evaluation
  3. Agents still fail most enterprise Java migrations (huggingface.co)
    AI · · July 3, 2026 · Agents · Benchmarks · Coding
  4. One transformer layer can match full RL fine-tuning (arxiv.org)
    AI · · July 3, 2026 · Research · Reinforcement Learning · Fine-tuning
  5. Claude Sonnet 5's new tokenizer quietly raises the real price (simonwillison.net)
    AI · · July 2, 2026 · Anthropic · Claude · Economics
  6. Cloudflare will block AI crawlers that hide their purpose (techcrunch.com)
    AI · · July 2, 2026 · Cloudflare · Policy · Web
  7. Mollick: work is shifting from chatting to assigning (oneusefulthing.org)
    AI · · July 2, 2026 · Agents · Productivity · Economics
  8. Claude Science pulls a researcher's tools into one workbench (anthropic.com)
    AI · · July 1, 2026 · Anthropic · Science · Agents
  9. Claude Sonnet 5 arrives built for agents (anthropic.com)
    AI · · July 1, 2026 · Anthropic · Claude · Models · Agents
  10. GLM-5.2 is the open model that works as a general agent (interconnects.ai)
    AI · · July 1, 2026 · Open Models · Agents · China
  11. Ornith-1.0 is an open coding model that scaffolds itself (simonwillison.net)
    AI · · July 1, 2026 · Open Models · Agents · Coding