The LGTM (Page 5)

The LGTM

Sign in Subscribe

Codex Starts Treating Plugins Like a Supply Chain

Codex Starts Treating Plugins Like a Supply Chain

Plugins are where coding agents stop being assistants and start becoming platforms. A plugin can bring skills, app integrations, MCP server configuration, lifecycle hooks, and marketplace metadata into the same runtime that reads your repository, proposes edits, runs commands, and sometimes asks for fewer approvals than a junior engineer would.

Claude Code’s Remote Auto-Compaction Bug Turns Context Management Into Hidden Runtime State

Claude Code’s Remote Auto-Compaction Bug Turns Context Management Into Hidden Runtime State

Context compaction is the garbage collector for coding-agent state. Nobody wants to think about it until it silently stops running. That is why Claude Code issue #70477 is more interesting than a routine token-cost complaint. The report says remote or bridge-attached Claude Code sessions can skip threshold auto-compaction and ignore

Claude Code Dynamic Workflows Need Token Admission Control, Not a Concurrency Dial

Claude Code Dynamic Workflows Need Token Admission Control, Not a Concurrency Dial

Claude Code’s Dynamic Workflows problem is not that users can start too many agents. It is that “too many” is being measured in the wrong unit. A concurrency cap sounds like a control. It is not a budget. Fifteen workers that each grep one small file are cheap. Fifteen

Claude Code’s Prompt-Injection False Memory Bug Is How Safety Heuristics Become Superstitions

Claude Code’s Prompt-Injection False Memory Bug Is How Safety Heuristics Become Superstitions

Claude Code’s latest prompt-injection report is not alarming because the model saw hostile text. It is alarming because, according to the reporter, the model invented the hostile text, diagnosed it as a prompt injection, and then wrote that diagnosis into memory where future sessions could inherit it. That is

DFlash Turns Speculative Decoding Into a Blackwell Utilization Story

DFlash Turns Speculative Decoding Into a Blackwell Utilization Story

Speculative decoding is one of those ideas that sounds like a serving hack until you remember the original problem is stranger: we run massively parallel accelerators and then ask large language models to emit text one token at a time. DFlash, the block-diffusion speculative decoding method NVIDIA is now highlighting

Tokens per Watt Is Becoming the AI Factory’s Real P&L Metric

Tokens per Watt Is Becoming the AI Factory’s Real P&L Metric

“Tokens per watt” sounds like a facilities metric until you have to run a real AI product under real capacity limits. Then it becomes the P&L. NVIDIA’s latest AI factory energy-efficiency post is easy to misread as green-computing content. It is really a margin story: every watt

NVIDIA OpenShell Is the Interesting Part of the Agent Toolkit Story

NVIDIA OpenShell Is the Interesting Part of the Agent Toolkit Story

The agent market has spent too much time pretending the hard problem is choosing the smartest model. It is not. The hard problem is giving an agent enough authority to be useful without giving it enough authority to become a root-cause analysis document. NVIDIA’s Agent Toolkit announcement is interesting

NVIDIA and AWS Are Making GPU Retrieval Boring — Which Is Exactly the Point

NVIDIA and AWS Are Making GPU Retrieval Boring — Which Is Exactly the Point

GPU announcements usually arrive dressed as hardware news. This one is more useful if you read it as a retrieval infrastructure story. NVIDIA and AWS are not merely adding another accelerated EC2 shape; they are pushing GPU acceleration into the boring middle of production AI, where vector indexes get rebuilt,