The LGTM (Page 86)

The LGTM

Home
Agentic Coding
Claude Code
Codex

Sign in Subscribe

PulseAgent Tackles the Hardest Problem in Long-Running Coding Agents: What Happens When the User Changes Their Mind Mid-Task

PulseAgent Tackles the Hardest Problem in Long-Running Coding Agents: What Happens When the User Changes Their Mind Mid-Task

Every developer who has used a coding agent for more than a few weeks has experienced the same failure mode. You start a task. The agent goes off and works. Twenty minutes later you come back and find the agent has been faithfully implementing something you would have redirected hours

28 Apr 2026 4 min read

Brain Exists Because the Market Finally Admits That Coding Agents Need Better Memory Than 'Read the File Again'

Brain Exists Because the Market Finally Admits That Coding Agents Need Better Memory Than 'Read the File Again'

The agentic-coding ecosystem has spent the past year arguing about which model is smarter, which benchmark matters, and which interface wins. Meanwhile, a quieter problem has been accumulating: coding agents have no memory worth the name. A session starts, context gets loaded, work gets done, and then — nothing. The agent

28 Apr 2026 4 min read

OpenAI and AWS Close the Loop: Codex Is Now an AWS Service

OpenAI and AWS Close the Loop: Codex Is Now an AWS Service

OpenAI and AWS closed a loop that has been conspicuously open for two years. As of April 28, Codex, GPT-5.5, and OpenAI Managed Agents are available in limited preview on Amazon Bedrock. AWS CEO Matt Garman put the logic plainly: "Their production applications run in AWS. Their data

28 Apr 2026 4 min read

GitHub Copilot's Meter Is Now Running: Usage-Based Billing Arrives June 1

GitHub Copilot's Meter Is Now Running: Usage-Based Billing Arrives June 1

GitHub just told you what Copilot actually costs to run. That matters more than the price change. Starting June 1, Copilot stops being a subscription and starts being a meter. GitHub is replacing its premium request unit model with GitHub AI Credits on June 1, which means every chat prompt,

28 Apr 2026 4 min read

Four Incidents in One Day: What Claude's April 28 Outage Pattern Actually Tells Us

April 28 was not a good day to be running Claude in production. Looking at the status page history, the service experienced four separate incidents within a single UTC day — a pattern that stands out even in a week where Claude's reliability has been inconsistent. Let me lay

28 Apr 2026 3 min read

Anthropic's Creative Tool Connector Blitz Is Really a Platform Play in Open Protocol Clothing

Anthropic's Creative Tool Connector Blitz Is Really a Platform Play in Open Protocol Clothing

Anthropic has been building Claude into an enterprise story for over a year. Today's announcement is the next logical move in that arc: a coordinated release of nine connectors targeting creative professionals — Blender, Adobe, Autodesk Fusion, Ableton, Affinity, Resolume, SketchUp, and Splice — all through MCP. The framing is

28 Apr 2026 4 min read

OpenClaw v2026.4.26 Drops 12 Hours After Beta Train — and It's Mostly About Not Crashing

There is a version of OpenClaw's release cadence that is just checking boxes: ship features, cut a changelog, move on. Then there is the version that showed up twelve hours after the beta train closed on April 27 and spent the entire release budget on not breaking things.

28 Apr 2026 4 min read

GitHub Copilot's New Metered Billing Is Microsoft's First Honest Admission That Unlimited AI Coding Was Always Borrowed Time

GitHub Copilot's New Metered Billing Is Microsoft's First Honest Admission That Unlimited AI Coding Was Always Borrowed Time

GitHub Copilot has a pricing problem it finally decided to stop pretending does not exist. Starting June 1, GitHub is moving every Copilot plan from request-based billing to usage-based billing, replacing flat monthly quotas with a token-metered system called GitHub AI Credits. Under the old model, a two-minute autocomplete snippet

28 Apr 2026 3 min read

Microsoft Let OpenAI Off the Exclusive Leash, and Azure's AI Business Model Will Never Look the Same

Microsoft Let OpenAI Off the Exclusive Leash, and Azure's AI Business Model Will Never Look the Same

For years, if you wanted to run OpenAI's models through a cloud provider with enterprise-grade procurement, compliance, and SLA support, there was exactly one place to go: Azure. That was not an accident. It was a contract, and it was worth billions to both sides. On Monday, Microsoft

28 Apr 2026 4 min read

OpenAI Symphony Turns Your Issue Tracker Into an Always-On Coding Agent Orchestrator

OpenAI Symphony Turns Your Issue Tracker Into an Always-On Coding Agent Orchestrator

OpenAI shipped something interesting on April 28, and it did not bother with the usual framing. Symphony is not a framework, not an SDK, not a product. It is a specification document — a written description of how to connect an issue tracker to an autonomous coding agent — plus an Elixir

28 Apr 2026 5 min read

The 60%-to-20% Delegation Gap: What Anthropic's Report Actually Says About Where Agentic Coding Is Breaking

The 60%-to-20% Delegation Gap: What Anthropic's Report Actually Says About Where Agentic Coding Is Breaking

Anthropic published its 2026 Agentic Coding Trends Report this month, and the headline number you will see quoted most often is probably the productivity claim: projects scoped at four to eight months finishing in under two weeks. That figure comes from Augment Code, and it is real. But the number

28 Apr 2026 3 min read

OpenAI's Rate Limit Reset Today Is a Signal, Not Just a Housekeeping Event

OpenAI's Rate Limit Reset Today Is a Signal, Not Just a Housekeeping Event

OpenAI reset Codex rate limits for all paid plans today — and the fact that a community member had to post about it publicly because the communication was unclear tells you most of what you need to know about how the agent infrastructure layer is being managed. The rate reset itself

28 Apr 2026 2 min read

← Newer Posts Page 86 of 114 Older Posts →

The LGTM © 2026

Sign up

Powered by Ghost