The LGTM (Page 108)

The LGTM

Sign in Subscribe

Valid Bash Is Not Safe Bash: NVIDIA’s Small-Model Benchmark Is Really an Agent Security Warning

Valid Bash Is Not Safe Bash: NVIDIA’s Small-Model Benchmark Is Really an Agent Security Warning

The most important sentence in NVIDIA’s new Bash-generation research is not the benchmark result. It is the premise: Bash is “one of the most flexible and powerful interfaces exposed to AI agents.” That is the polite version. The less polite version is that a coding agent producing shell commands

Google I/O 2026 Is a Gemini Runtime Watchlist, Not a Keynote Drinking Game

Google I/O 2026 Is a Gemini Runtime Watchlist, Not a Keynote Drinking Game

The least useful question before Google I/O is whether Google says “Gemini 4.0” on stage. Model names are launch theater. The better question is where Gemini will be allowed to act — because a model wired into Chrome, Android, XR glasses, Workspace, AI Studio, and developer APIs changes product

Gemini Live’s Hidden Model Picker Is the Interesting I/O Leak: Voice Agents Are About to Get Tiers

Gemini Live’s Hidden Model Picker Is the Interesting I/O Leak: Voice Agents Are About to Get Tiers

Gemini Live’s most interesting leak is not that Google may have a new model waiting for I/O. Of course it does. The interesting part is that Google appears to be testing a model picker for voice — which means voice assistants are about to inherit the same tradeoff menu

Claude Code Finally Gets the Prometheus Dashboard Its Enterprise Pilots Were Going to Build Anyway

Claude Code Finally Gets the Prometheus Dashboard Its Enterprise Pilots Were Going to Build Anyway

Claude Code now has the kind of dashboard that only appears after a tool stops being a toy. Rock Martel-Langlois published a Prometheus/Grafana dashboard for Claude Code metrics this morning, and on the surface it is infrastructure glue: a port of an existing Azure Application Insights dashboard into PromQL.

Megatron Bridge on GB10 Shows the Painful Gap Between ‘Supported’ and ‘Usable’

Megatron Bridge on GB10 Shows the Painful Gap Between ‘Supported’ and ‘Usable’

The useful NVIDIA forum posts are not always the polished ones. Sometimes the useful one is a frustrated builder saying Megatron Bridge is eating “endless VRAM” on a two-node GB10 setup and falling over at batch sizes where the simpler Hugging Face path survives. That is not a definitive indictment