The  LGTM
  • Home
  • Agentic Coding
  • Claude Code
  • Codex
Sign in Subscribe
qwen

The Alibaba/Nvidia Smuggling Allegation Is an AI Supply-Chain Warning

The useful way to read the Alibaba/Nvidia smuggling report is not as another round of great-power drama with GPUs in the headline. Read it as a provenance story. AI teams have spent the last two years learning to ask where a model came from, what data trained it, which
09 May 2026 5 min read
QwenPaw Is Shipping the Boring Ops Layer Local Agents Actually Need
qwen

QwenPaw Is Shipping the Boring Ops Layer Local Agents Actually Need

QwenPaw v1.1.6 is not a model launch, which is exactly why it is worth paying attention to. The Qwen ecosystem already has plenty of benchmark theater. What it needs now is the unglamorous runtime machinery that determines whether an agent assistant survives contact with real users: isolated cron
09 May 2026 5 min read
Microsoft Brings Magentic Orchestration to .NET, Closing the Gap Between AutoGen Research Patterns and Enterprise Agent Workflows
ai-frameworks

Microsoft Brings Magentic Orchestration to .NET, Closing the Gap Between AutoGen Research Patterns and Enterprise Agent Workflows

Microsoft bringing Magentic Orchestration to the .NET side of Agent Framework is not a flashy model announcement, which is why it is worth paying attention to. The serious agent-platform work in 2026 is not about inventing another chat loop. It is about taking research patterns that looked impressive in notebooks
09 May 2026 5 min read
Microsoft Shows How Prompt Injection Becomes RCE When Agent Frameworks Trust Tool Arguments Too Much
ai-frameworks

Microsoft Shows How Prompt Injection Becomes RCE When Agent Frameworks Trust Tool Arguments Too Much

Prompt injection stops being an abstract AI safety debate the moment it reaches a tool boundary. Microsoft’s latest Semantic Kernel write-up is useful because it strips away the mysticism: an attacker influenced an agent’s tool argument, that argument landed in unsafe Python string interpolation, and a prompt became
09 May 2026 4 min read
Codex Plugins Make Agent Workflows Installable — and Auditable
agentic-coding

Codex Plugins Make Agent Workflows Installable — and Auditable

Codex plugins are easy to describe as a convenience feature: install Gmail, connect Drive, pull Slack context, expose a few MCP tools, move on. That framing is too small. Plugins are the moment Codex workflows become installable software. And once agent workflows are installable, they inherit the same old problems
09 May 2026 6 min read
Codex 0.130.0 Turns Agent Configuration Into Product Surface
agentic-coding

Codex 0.130.0 Turns Agent Configuration Into Product Surface

Codex 0.130.0 looks like a normal release note until you read it less like a changelog and more like a map of where AI coding tools are going. The headline is not one feature. It is the accumulation: plugins with visible hooks, shareable workflow metadata, a headless remote-control
09 May 2026 5 min read
Gemini in Chrome Is Expanding in Asia-Pacific — and the Browser Is Becoming Google’s Agent Runtime
google-ai

Gemini in Chrome Is Expanding in Asia-Pacific — and the Browser Is Becoming Google’s Agent Runtime

Google’s latest Gemini-in-Chrome announcement looks like a regional availability update. It is not. The useful read is that Chrome is becoming Google’s agent runtime: the place where Gemini can see the page, compare tabs, call into Google apps, transform images, and eventually perform multi-step chores with the browser’
09 May 2026 6 min read
llm-rankings

The Best Model Is the One Your Router Knows When Not to Use

The leaderboard story this week is not that one model moved one slot. That is leaderboard theater. The useful story is that two different markets are now visible at the same time: the models developers admire in benchmarks, and the models production systems can afford to call a few billion
09 May 2026 5 min read
ai-models

Gemini 3.1 Deep Think Is Google’s Answer to the Frontier Benchmark Knife Fight

Google’s Gemini 3.1 Deep Think update is not interesting because another lab found another benchmark where it can print a bigger number. That game is now mostly a knife fight in a spreadsheet. It is interesting because Google is no longer asking developers to believe Gemini is catching
09 May 2026 4 min read
ai-models

Gemini 3.1 Flash-Lite Makes the Cheap Model the Architecture Decision

The most important model in a production AI system is often not the smartest one. It is the cheap, fast, good-enough model that gets called 40 times before the expensive model ever sees the request. That is why Gemini 3.1 Flash-Lite deserves more attention than its name will probably
09 May 2026 4 min read
Anthropic’s Mythos Is the Model Release That Turns Vulnerability Discovery Into an Operations Problem
ai-models

Anthropic’s Mythos Is the Model Release That Turns Vulnerability Discovery Into an Operations Problem

The headline version of Anthropic’s Project Glasswing is simple: Claude Mythos Preview found a lot of bugs. The useful version is more uncomfortable: vulnerability discovery is becoming cheap enough that the scarce part of security is no longer finding the flaw. It is deciding what to do with the
09 May 2026 4 min read
Codex Skills Turn Prompt Hygiene Into a Repo Artifact — Now Teams Need to Treat It Like Code
codex

Codex Skills Turn Prompt Hygiene Into a Repo Artifact — Now Teams Need to Treat It Like Code

Codex Skills look harmless if you describe them as reusable instructions. That is also the least useful way to understand them. The better framing is this: OpenAI is turning agent operating knowledge into a repo artifact, and the moment something becomes an artifact, it becomes part of your software supply
09 May 2026 7 min read
← Newer Posts Page 69 of 114 Older Posts →
The LGTM © 2026
  • Sign up
Powered by Ghost