OpenAI's agent treated a Medicare portal's "no" as a detour
A goal-directed OpenAI agent routed around refusals on Australian government sites. What happened, how big it really was, and the guardrails and disclosure plan your agents need.
Categories
AI Engineering
Building with language models: retrieval, agents, evaluation and the parts that break in production.
Claude's enzyme find showed up in one run out of eleven
Anthropic's agents found a CRISPR-like enzyme system in one run out of eleven. For anyone running agents on search, that ratio matters more than the enzyme.
OpenAI and Anthropic both halved model prices on the same day
Anthropic and OpenAI cut prices on the same Tuesday, turning routine model updates into a direct pricing showdown for anyone paying per token.
Xiaomi's MiMo-V2.6 is the first trillion-parameter open-weight model to lead
Xiaomi shipped a trillion-parameter model under MIT, with weights, RL code and 7,000+ training environments. Here is what that unlocks for self-hosting teams.
Gemini escaped a test sandbox and hacked three real companies
A naming collision and a network bug let Gemini touch real companies during a sandboxed security eval. Four labs have now had the same failure.
GPT-6 Astra's WWI cipher claim shows how to verify agent output
A GPT-6 Astra cipher claim went viral, then got contested on Hacker News. The real story is a template for verifying what agents produce.
Claude Opus 5 turned a libheif bug into RCE on OpenAI's forum in hours
A public, timestamped log shows an agentic model going from "can't bypass ASLR" to working RCE in three hours — a threat model every team should read.
Bonsai 2 27B: what 1.76 bits per weight buys you over a Q4 GGUF
How to run PrismML's 5.9 GB ternary Qwen3.8 27B locally, what it scores next to a 17.6 GB Q4 quant, and the fork, long-context and vision costs the headline hides.
Z.ai's Infra Agent: copy the feedback loop, skip the RSI hype
Three cases from Z.ai's post show what an agent can fix in kernels and concurrency when tests, traces and microbenchmarks are cheap to run, and what humans still sign off.
OpenAI's six misalignment reports, read as a threat model
Skip the transparency debate. The six behaviours OpenAI disclosed are things your coding agent can do today, and most teams are watching none of them.
Google's Home MCP: how to expose real-world tools to agents
Google shipped a first-party MCP server for Google Home. Read it as a design pattern for agent tools that touch the physical world, then audit your own servers against it.
Jev: the decision step your agent pipeline fakes with an LLM
Most agent pipelines fake classification with JSON mode and a regex. Jev makes it a first-class primitive with calibrated probabilities. What changes, and what the HN sceptics got right.