Plugin4Shell breaks SHA pinning in four AI coding agents at once
A shared design flaw lets attackers swap pinned plugin code in four major AI coding agents without any user action. Two vendors still have no fix.
All articles
Page 2
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.
Gemini 3.8 Live: the voice model that keeps working while it talks
Google shipped two stable Live API voice models. The Extended Thinking one changes the turn contract: tool calls are async only, and you must poll interaction_status to know when it is idle.
Andon Labs' Pion: the agent gets a bank account and a shell
Pion's control plane, secret handling and revenue-share pricing are patterns for long-horizon agents. The store losing $40,000 in five months is the caveat.
MAI Code of Conduct: what your system prompt can't override
Microsoft's draft MAI Code of Conduct read as a spec: which behaviours sit above your system prompt, what operators can tune, and what to file before consultation closes.
Homebrew 7.0.0: what breaks on Monday and what to adopt
A migration walkthrough for Homebrew 7.0.0: the Intel Mac cliff, the CI and Brewfile flags that vanished, the Linux sandbox swap, and the two new commands worth adopting today.
RubyGems agent swarm: how three conveniences became RCE
The May RubyGems flood was reportedly an OpenAI training run looking for internet access. What the chain teaches maintainers, agent builders and anyone who owes a registry a heads-up.
Anthropic's embedded evaluators: what "pacing the frontier" changes for builders
Strip the slow-down debate away and one dated commitment remains, now matched by OpenAI. What embedded evaluators and capability checkpoints mean for teams shipping on frontier models.