The  LGTM
  • Home
  • Agentic Coding
  • Claude Code
  • Codex
Sign in Subscribe
ai-frameworks

CrewAI 1.14.5a4 Is a Dependency Hygiene Release With a Security Lesson Attached

CrewAI 1.14.5a4 is the kind of release that gets skipped in sprint planning because it does not contain a feature anyone can demo. That is exactly why it is worth paying attention to. The public changelog says the prerelease updates LLM listings, moves textual into crewai-cli, adds certifi,
10 May 2026 4 min read
Agent Skills Are Becoming the Portable Layer Between Claude Code, Codex, and Cursor
agentic-coding

Agent Skills Are Becoming the Portable Layer Between Claude Code, Codex, and Cursor

The most important file in your coding-agent stack may not be your model config. It may be a markdown file with YAML frontmatter and a deceptively boring name: SKILL.md. VoltAgent’s awesome-agent-skills repository is useful because it makes that shift visible. The repo describes itself as a curated collection
10 May 2026 4 min read
Claude Code’s URL Plugins Turn Agent Extensions Into a Supply-Chain Problem
agentic-coding

Claude Code’s URL Plugins Turn Agent Extensions Into a Supply-Chain Problem

Claude Code’s Week 19 update looks like a convenience release until you read the two new ideas together: plugins can now be loaded straight from zip archives or URLs, and auto mode can now enforce hard_deny rules that override broader allow policies. That pairing is the story. Anthropic
10 May 2026 4 min read
Google I/O 2026 Is a Gemini Runtime Watchlist, Not a Keynote Drinking Game
google-ai

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
10 May 2026 5 min read
Gemini Live’s Hidden Model Picker Is the Interesting I/O Leak: Voice Agents Are About to Get Tiers
google-ai

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
10 May 2026 5 min read
GitHub’s Grok Code Fast 1 Deprecation Is a Small Changelog With a Big Model-Routing Lesson
codex

GitHub’s Grok Code Fast 1 Deprecation Is a Small Changelog With a Big Model-Routing Lesson

The least interesting way to read GitHub’s Grok Code Fast 1 notice is as a housekeeping update: one model goes away, two alternatives are suggested, administrators flip a policy toggle, everyone moves on. That reading is also how teams get surprised by AI tooling drift. GitHub said it will
10 May 2026 5 min read
Claude Code Finally Gets the Prometheus Dashboard Its Enterprise Pilots Were Going to Build Anyway
claude-code

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.
10 May 2026 6 min read
Megatron Bridge on GB10 Shows the Painful Gap Between ‘Supported’ and ‘Usable’
nvidia

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
09 May 2026 5 min read
Qwen3.6-397B Is the Right Question Even If the Answer Is ‘Not by Copy-Paste’
nvidia

Qwen3.6-397B Is the Right Question Even If the Answer Is ‘Not by Copy-Paste’

The most useful Qwen thread this weekend is not an announcement of a new model. It is a builder asking whether a hypothetical Qwen3.6-397B can be created from the ingredients already on the table: Qwen3.5-397B-A17B, Qwen3.6-35B-A3B, Hugging Face configs, vLLM recipes, and enough NVIDIA hardware ambition to
09 May 2026 4 min read
NIM’s 40 RPM Free Tier Is Starting to Break Agent Workflows Before the Model Does
nvidia

NIM’s 40 RPM Free Tier Is Starting to Break Agent Workflows Before the Model Does

NVIDIA NIM’s most revealing product feedback this week did not arrive as a keynote slide. It arrived as a queue of forum posts asking for the same thing: please raise the default API limit from 40 requests per minute, because agent workflows are tripping over it before the model
09 May 2026 4 min read
LangChain 1.2.18 Is the Maintenance Release That Treats Legacy Agent Surfaces Like Real Risk
ai-frameworks

LangChain 1.2.18 Is the Maintenance Release That Treats Legacy Agent Surfaces Like Real Risk

LangChain 1.2.18 is the kind of release that looks minor until you remember where agent systems actually fail. Not in the keynote demo. Not in the “hello, weather tool” tutorial. They fail in old compatibility paths, serialized state, prompt-hub leftovers, streaming event consumers, and metadata changes that accidentally
09 May 2026 5 min read
Vibe Coding’s Security Problem Is Invisible Production
agentic-coding

Vibe Coding’s Security Problem Is Invisible Production

The security problem with vibe coding is not that generated code sometimes has bugs. That is true, but it is the smaller story. The bigger story is that prompt-to-app tools are creating a new production surface outside the engineering perimeter: apps with URLs, databases, forms, customer data, and business logic
09 May 2026 5 min read
← Newer Posts Page 68 of 114 Older Posts →
The LGTM © 2026
  • Sign up
Powered by Ghost