The LGTM (Page 94)

The LGTM

Home
Agentic Coding
Claude Code
Codex

Sign in Subscribe

Claude Code’s Next Trick Is Delegating to a Pool of Codex Workers Instead of Doing the Whole Job Itself

Claude Code’s Next Trick Is Delegating to a Pool of Codex Workers Instead of Doing the Whole Job Itself

Multi-agent coding has spent the last year sounding like a research demo genre. One agent plans, another implements, a third reviews, and somewhere in the middle a human tries to remember which branch is the real one. Most of that work has been high on spectacle and low on operational

24 Apr 2026 4 min read

Doby Is a Small, Sharp Rebuttal to the Idea That AI Coding Needs More Context Instead of Better Navigation

Doby Is a Small, Sharp Rebuttal to the Idea That AI Coding Needs More Context Instead of Better Navigation

There is a lazy answer to most AI-coding quality problems right now: give the model more context. Bigger windows, more retrieval, more MCP tools, more documents, more screenshots, more everything. Sometimes that works. Sometimes it just creates a larger room for the model to get lost in before it edits

24 Apr 2026 4 min read

Copilot’s Pull Request Chat Update Is Really About Giving the Agent More Review Surface Area

Copilot’s Pull Request Chat Update Is Really About Giving the Agent More Review Surface Area

GitHub’s latest Copilot pull-request chat update looks small enough to ignore. That would be a mistake. On the surface, the April 23 changelog entry is about better pull-request context, improved summaries, and more review-oriented chat behavior when Copilot is given a PR as context. But the deeper story is

24 Apr 2026 4 min read

Codex 0.124.0 Is OpenAI Spending Its Upgrade Budget on the Runtime, Which Is the Correct Bet

Codex 0.124.0 Is OpenAI Spending Its Upgrade Budget on the Runtime, Which Is the Correct Bet

Codex CLI 0.124.0 is exactly the kind of release that most AI tooling coverage underserves. There is no cinematic demo here, no sweeping benchmark claim, no fresh declaration that autonomous coding has entered a new era. Instead, OpenAI spent this version on the runtime: multiple managed environments in

24 Apr 2026 4 min read

GPT-5.5 Is the First OpenAI Launch That Reads Like a Coding Workflow Upgrade, Not Just a Model Upgrade

OpenAI’s GPT-5.5 launch looks, at first glance, like the usual frontier-model ceremony: bigger benchmark table, bigger claims, bigger quotes from early users who now speak about software the way people usually speak about religion. But the interesting part of this release is not that GPT-5.5 is smarter

24 Apr 2026 4 min read

OpenClaw’s Bedrock Auth Regression Shows How Easy It Is for a Credential Store to Break the Cloud-Native Path It Was Supposed to Simplify

The most revealing bugs in agent infrastructure are the ones that break the boring, correct path. That is why OpenClaw’s Bedrock authentication regression deserves more attention than a typical provider-integration ticket. According to issue #69708, since OpenClaw 2026.4.1 the gateway has been rejecting "type": "

23 Apr 2026 5 min read

OpenClaw’s Windows Gateway Hang Was Not a Networking Mystery. It Was a Loopback Contract Bug Hiding in Plain Sight

For a certain class of infrastructure bug, the most dangerous symptom is not a crash. It is a service that looks alive enough to waste your afternoon. That is what made OpenClaw’s Windows gateway hang worth paying attention to this week. The bug did not present as a dramatic

23 Apr 2026 4 min read

NVIDIA Found the Real GTM Win in GPT-5.5: Be the Inference Layer Nobody Can Avoid

NVIDIA Found the Real GTM Win in GPT-5.5: Be the Inference Layer Nobody Can Avoid

The most interesting thing about OpenAI’s GPT-5.5 launch is not that the benchmark chart moved again. It is that NVIDIA managed to turn another model announcement into a reminder that the real money is moving down the stack. When NVIDIA says Codex is now powered by GPT-5.5

23 Apr 2026 4 min read

NVIDIA’s Latest Developer Pitch Is Simple: GPUs Turn Kaggle Tricks Into Production Habits

NVIDIA’s Latest Developer Pitch Is Simple: GPUs Turn Kaggle Tricks Into Production Habits

NVIDIA’s latest Kaggle post looks, at first glance, like the sort of thing developers are trained to ignore. A leaderboard story. A playground competition. Another vendor using somebody else’s result to imply a sweeping industry trend. Read past the packaging and the story is better than that. What

23 Apr 2026 5 min read

Microsoft’s Prior-Authorization Template Is a Good Demo, but the Real Story Is That Foundry Is Becoming Compliance Workflow Infrastructure

Microsoft’s Prior-Authorization Template Is a Good Demo, but the Real Story Is That Foundry Is Becoming Compliance Workflow Infrastructure

The most interesting thing about Microsoft’s new prior-authorization template is not that it uses four agents. Everyone has four agents now. The interesting thing is the kind of workflow Microsoft picked to prove its point. Prior authorization is ugly work. It is politically toxic, operationally expensive, full of documentation

23 Apr 2026 5 min read

Azure MCP’s New .mcpb Packaging Matters Because Microsoft Is Selling Setup Friction as a Product Bug

Azure MCP’s New .mcpb Packaging Matters Because Microsoft Is Selling Setup Friction as a Product Bug

Microsoft did not ship a new Azure capability this week so much as remove the first hour of frustration required to use one. That sounds small. It is not. The Azure MCP Server can now be installed as an MCP Bundle, or .mcpb, which means someone can drop a file

23 Apr 2026 5 min read

PydanticAI 1.86.0 Tightens the UI Prompt Boundary, Which Is Exactly Where Agent Frameworks Need to Be Less Naive

PydanticAI 1.86.0 Tightens the UI Prompt Boundary, Which Is Exactly Where Agent Frameworks Need to Be Less Naive

Prompt security gets talked about like a model problem far more often than it gets treated like a systems problem. That is a mistake. In real agent applications, some of the most dangerous prompt behavior starts at the UI boundary, where convenience features quietly blur trust assumptions. PydanticAI 1.86.

23 Apr 2026 4 min read

← Newer Posts Page 94 of 116 Older Posts →

The LGTM © 2026

Sign up

Powered by Ghost