Notes from the trenches on AI engineering, LLM apps, and the full-stack work that holds it all together.
Shanghai AI Lab's Self-Harness lets a fixed model improve its own agent scaffolding through weakness mining, targeted edits, and regression gates. Here is what the Terminal-Bench numbers mean and how to run a lightweight version today.
Inkling ships 975B total / 41B active MoE with native text, image, and audio in one architecture, 1M context, Apache 2.0 weights, and controllable thinking effort. It is not the leaderboard king. It is the customization base Mira Murati's team wanted.
Twelve million servers leak .env files to the open web. When you give an agent Gmail, CRM, and Slack access, local plaintext tokens turn a config mistake into a company-wide breach.
Dharmesh Shah argues agent skills are the next career moat. After shipping agents for clients, I agree on the skill gap, but the bar is workflow design, not another chat subscription.
The July 2026 commitment funds Amii, Mila, Vector, CHEO, CAMH, Université Laval, U of T, and U of Saskatchewan with no-strings Claude API credits plus startup program access for affiliated founders.
Anthropic's August 2026 CHIVE pipeline found activation oracles, NL autoencoders, and sparse autoencoders gave zero uplift over transcript-only predictors on wild LLM behaviors. Here is what that means for production debugging.
Anthropic GA'd computer_toolset_20260801 with multi-action turns, browser use, Skills API, and Files API. Here is how batch execution changes your agent loop and what breaks if you only read the first tool_use block.
Anthropic opened Mythos 5-powered GitHub scans to all Claude Enterprise customers in August 2026. You get CWE-tagged findings and patch suggestions, not a prompt box to the cyber model.