Beyond grep: the thesis of the rich-context AI coding harness
Ars Technica states what code agent practitioners were observing: context strategy has become the real lever - not the underlying model.
20 h ago 8 10
Weekly quota resets: the coding-agent budget cliff that nobody signed up for
For a few weeks now, code agent users have seen their weekly quotas reset "randomly". This is not a bug - it's the first sign that token rationing has become a real product lever.
Jul 19, 2026 at 00:39 10 10
"Claude Code: Anatomy of a Misfeature" - when public review becomes the real QA
Olaf Alders publishes on July 17 a well-argued critique of a Claude Code feature - the "public post-mortem of a misfeature" format is becoming a standard of hype fatigue.
Jul 17, 2026 at 22:05 34 11
Capital One releases VulnHunter: an AI code security agent, open source
Capital One is launching VulnHunter, an agentic security tool, on July 17 - the bank is contributing to the sec + agents ecosystem.
Jul 17, 2026 at 22:03 12 8
GitLab 19.2 delivers AI to fix vulnerable dependencies: security moves left, once more, but into the model
GitLab 19.2 includes AI tools to patch vulnerable dependencies. Shift-left security is back - this time in the model, not in the linter.
Jul 17, 2026 at 09:21 26 9
Gemini 3.5 Pro delayed: Google admits that the frontier release is now stuck on the code
Google differs Gemini 3.5 Pro to improve coding. The metric that blocks a frontier release is no longer knowledge, it's tool-use.
Jul 17, 2026 at 09:19 25 11
Kimi K3 goes live: Moonshot ships the model after the preview flood
After the wave of teasers and benchmark videos, Moonshot AI has put Kimi K3 into production on kimi.com and via its code API. The question is no longer "when," but "at what price, at what latency, and for what real use."
Jul 16, 2026 at 21:46 29 8
The archaeologist and his copilot: Malykhin disciplines the LLM on Java 1.5
Nik Malykhin had to run a Java 1.5 base on modern hardware. The first answers from his LLM were plausible, but did not hold up to scrutiny. The breakthrough: stop believing it at face value, force it to rely on evidence.
Jul 16, 2026 at 17:45 31 8
Fowler: DSLs are not dead, they are what makes LLM usable
A Martin Fowler article brings DSLs back into focus: not to impress the experts, but to give the LLM a narrow target where it can make recoverable mistakes.
Jul 15, 2026 at 19:29 30 6
Benchmark Stripe: agents connect APIs, they do not validate them
A public benchmark by Stripe shows that AI agents write integrations that compile, run, and silently fail on the edge cases that matter.
Jul 15, 2026 at 19:28 32 6
Ronacher: the tower doesn't fall, and that's exactly the problem
Babel stopped when men stopped understanding each other. With the agents, construction continues after the collapse of shared understanding. No one notices anything.
Jul 14, 2026 at 22:30 14 6
The burn rate of an engineer could soon equal their salary
Adam Mosseri announces token quotas per engineer within one to two years. Behind the joke, a real professional question: the marginal cost of code has just stopped being zero.
Jul 14, 2026 at 22:30 16 7