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.
4 h ago 4 5
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.
17 h ago 9 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.
17 h ago 8 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."
yesterday 9 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.
yesterday 9 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 9 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 10 6
« Loop engineering »: new discipline or cron job rebranding?
The term is on the rise, the Pragmatic Engineer investigation concludes to a mix of triggers, cron jobs, and LLM slop. A real underlying question remains: who possesses the robustness of an observe-decide-act loop powered by LLM?
Jul 15, 2026 at 12:34 9 7
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 9 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 9 7
Three loops in a trench coat: the real anatomy of an agent
An agent isn't magic. It's an inference loop, a tool loop, and a human in the way. The profession is shifting: you no longer write the prompt, you write the loop.
Jul 14, 2026 at 22:30 9 8
antirez: "Control the ideas, not the code" - the pivot of the dev profession in the AI era
Salvatore Sanfilippo (Redis) publishes a short and clear post on what remains for the developer when AI writes the code. His answer: the idea, the architecture, the judgment. The rest is delegable.
Jul 13, 2026 at 17:27 9 8