The  LGTM
  • Home
  • Agentic Coding
  • Claude Code
  • Codex
Sign in Subscribe
Agent Optimizer Turns Prompt Tuning Into a Versioned Engineering Loop — With All the Usual Footguns
azure-ai

Agent Optimizer Turns Prompt Tuning Into a Versioned Engineering Loop — With All the Usual Footguns

Agent Optimizer is Microsoft’s attempt to professionalize the least professional part of agent development: the ritual of staring at failures, tweaking a system prompt, running three examples, and calling it a release. Every team says it is “iterating on behavior.” Too often, what it actually means is artisanal superstition
04 Jun 2026 4 min read
Foundry Agents Are Moving From Apps You Build to Coworkers IT Has to Govern
azure-ai

Foundry Agents Are Moving From Apps You Build to Coworkers IT Has to Govern

Microsoft’s newest Foundry agents story is easy to misread as another “now you can publish your bot to Teams” announcement. That is the small version. The more important version is that Microsoft is turning agents from app endpoints into governed workplace actors: things with identities, scopes, admin review, social
04 Jun 2026 4 min read
Grok’s Deepfake Lawsuit Is a Product-Safety Case Wearing a Media-Policy Jacket
xai

Grok’s Deepfake Lawsuit Is a Product-Safety Case Wearing a Media-Policy Jacket

Grok’s latest legal problem is easy to misread as a “bad users made bad images” story. That is the comfortable version for AI companies: the model is neutral, the platform is neutral, and responsibility begins only when someone types the wrong prompt. Jess Asato’s lawsuit against xAI is
04 Jun 2026 5 min read
Qwen Code 0.17.1 Shows Local Coding Agents Win on Memory, Auth, and Provider Plumbing
ai-frameworks

Qwen Code 0.17.1 Shows Local Coding Agents Win on Memory, Auth, and Provider Plumbing

Qwen Code 0.17.1 is not a glamorous release. Good. Glamour is usually where coding-agent reliability goes to hide. The June 3 release, followed by a June 4 nightly, is a clean snapshot of what local and bring-your-own-key coding agents are actually wrestling with in 2026: memory pressure, resumed-session
04 Jun 2026 5 min read
Microsoft Agent Framework 1.9 Turns Skills and MCP Discovery Into Runtime Governance
ai-frameworks

Microsoft Agent Framework 1.9 Turns Skills and MCP Discovery Into Runtime Governance

Microsoft Agent Framework 1.9.0 is the kind of release that looks boring until you ask the only question that matters in production: who decides what an agent is allowed to know, load, and call? The answer used to be “the prompt,” which is convenient and mostly fictional. The
04 Jun 2026 5 min read
Antigravity Migration Is Really a .gemini to .agents Governance Migration
agentic-coding

Antigravity Migration Is Really a .gemini to .agents Governance Migration

The Gemini CLI to Antigravity CLI migration is easy to describe badly: Google is moving developers from one command-line agent to another before a June 18 deadline. That framing is too shallow to be useful. The real migration is not from gemini to agy. It is from one governance model
04 Jun 2026 4 min read
Codex 0.137.0 Turns Agent Control Into Admin Surface Area
agentic-coding

Codex 0.137.0 Turns Agent Control Into Admin Surface Area

Codex 0.137.0 looks, at first glance, like another dense CLI release: a few app-server tweaks, some plugin polish, more web tooling, better multi-agent metadata. That reading misses the point. OpenAI is turning Codex from “the thing that edits my repo” into an administered agent runtime — one that has
04 Jun 2026 5 min read
Audio Interaction Model Makes Voice Agents Listen Before They Talk
ai-models

Audio Interaction Model Makes Voice Agents Listen Before They Talk

Most voice agents still behave like walkie-talkies with nicer latency. They wait for a turn boundary, transcribe the utterance, send text into a model, generate a response, and speak. That can feel real-time in a demo, but it is not the same thing as listening. Audio Interaction Model, a new
04 Jun 2026 5 min read
ThoughtFold Attacks the Real Reasoning-Model Tax: Tokens Wasted Thinking in Circles
ai-models

ThoughtFold Attacks the Real Reasoning-Model Tax: Tokens Wasted Thinking in Circles

The cheapest reasoning token is the one the model never emits. ThoughtFold, a new paper titled Folding Reasoning Chains via Introspective Preference Learning, is interesting because it attacks reasoning-model cost at the source: not with a pricing hack, not with a smaller context window, and not with the usual “just
04 Jun 2026 5 min read
GitHub Copilot App Canvases Admit the Real Problem: Agent Work Needs Inspectable State, Not Longer Chat Threads
codex

GitHub Copilot App Canvases Admit the Real Problem: Agent Work Needs Inspectable State, Not Longer Chat Threads

Chat was a fine demo surface for coding agents. It is a lousy supervision surface. That is the quiet admission inside GitHub’s expanded technical preview for the Copilot app, now available to existing Copilot Pro, Pro+, Business, and Enterprise customers, with Copilot Free and non-Copilot users pointed to a
04 Jun 2026 5 min read
OpenClaw’s Control-Plane Registry PR Is Early, But the Direction Is Right
openclaw

OpenClaw’s Control-Plane Registry PR Is Early, But the Direction Is Right

OpenClaw PR #90087 is not the kind of change that makes a good launch tweet. It adds contracts, schemas, registries, queues, reports, artifacts, dashboards, ledgers, and a read-only CI validator. In other words, it adds paperwork. For agent platforms, that paperwork is the product surface everyone pretends they will add
03 Jun 2026 4 min read
OpenClaw’s Session-Lock Fix Shows Why Provider Hangs Become Platform Outages
openclaw

OpenClaw’s Session-Lock Fix Shows Why Provider Hangs Become Platform Outages

The easiest agent reliability bug to underestimate is the one that looks like a normal timeout. A model provider hangs, the user sees an error, everybody shrugs, and the next turn should be fine. In OpenClaw PR #90065, the next turn was not fine. The provider hang left the session
03 Jun 2026 4 min read
← Newer Posts Page 3 of 108 Older Posts →
The LGTM © 2026
  • Sign up
Powered by Ghost