The  LGTM
  • Home
  • Agentic Coding
  • Claude Code
  • Codex
Sign in Subscribe
Oh My Pi 15.10.0 Shows Why Provider Compatibility Is the Hidden Tax of Vibe Coding
agentic-coding

Oh My Pi 15.10.0 Shows Why Provider Compatibility Is the Hidden Tax of Vibe Coding

“Supports every provider” is the agentic-coding equivalent of “works on my machine,” only more expensive. The phrase sounds like freedom until a tool call loses its arguments, a reasoning block gets replayed in the wrong format, a usage report double-counts a shared quota, or one crashed turn poisons the next
07 Jun 2026 5 min read
llm-rankings

Claude Opus 4.8 Turns Coding Benchmarks Into an Anthropic Bracket

The most interesting leaderboard move this week is not that Claude Opus 4.8 appeared near the top. That was expected. The interesting part is how little room there is left at the top of the coding-agent board for anyone who is not Anthropic. Arena AI’s latest Text and
07 Jun 2026 5 min read
Gemini 3.5 Flash Is Google’s Bet That Agent Models Should Be Fast Enough to Waste Less Time
ai-models

Gemini 3.5 Flash Is Google’s Bet That Agent Models Should Be Fast Enough to Waste Less Time

Google is not positioning Gemini 3.5 Flash as the smartest model in the room. That would be the boring version of the story, and Google’s own benchmark table does not support it anyway. The more interesting claim is that Flash-class models are becoming the default workers for agent
07 Jun 2026 6 min read
Codex Sites Is Not No-Code. It Is Deployment Power With an Approval Problem.
codex

Codex Sites Is Not No-Code. It Is Deployment Power With an Approval Problem.

Codex Sites will be tempting to describe as “no-code.” Don’t. That undersells both the feature and the risk. OpenAI’s Sites documentation says Codex can create, save, deploy, and inspect websites, web apps, dashboards, internal tools, and games hosted by OpenAI. It can turn a prompt or compatible existing
07 Jun 2026 4 min read
GPT-5.5 Is Now the Codex Default Recommendation. The Real Question Is When Not to Use It.
codex

GPT-5.5 Is Now the Codex Default Recommendation. The Real Question Is When Not to Use It.

OpenAI’s Codex model guidance now has a simple recommendation: for most tasks, start with gpt-5.5. That is good advice for an individual staring at a hard problem. It is incomplete advice for a team paying for a fleet of agents. The refreshed Codex models page positions gpt-5.5
07 Jun 2026 4 min read
Codex Project Config Just Got a Trust Boundary. Treat It Like One.
codex

Codex Project Config Just Got a Trust Boundary. Treat It Like One.

Codex configuration just moved from “developer preference” to “security boundary,” which is exactly where coding-agent config was always going to end up. OpenAI’s refreshed Codex configuration reference now says a project-scoped .codex/config.toml is loaded only after the user trusts the project. More importantly, the repo-local file cannot
07 Jun 2026 4 min read
ClawHub's New Abuse Scoring Treats Agent Skills Like a Marketplace, Not a Folder of Markdown
openclaw

ClawHub's New Abuse Scoring Treats Agent Skills Like a Marketplace, Not a Folder of Markdown

Agent skill registries cannot stay cute forever. The moment a registry influences what agents install, trust, invoke, or recommend, it stops being a folder of Markdown and becomes supply-chain infrastructure. That means popularity metrics become attack surface, publisher accounts become assets, and “community discovery” becomes a moderation problem whether the
06 Jun 2026 3 min read
OpenClaw's Lobster Runner Is Getting the In-Process Bridge It Should Have Had From the Start
openclaw

OpenClaw's Lobster Runner Is Getting the In-Process Bridge It Should Have Had From the Start

The easiest way to make an embedded workflow call back into its host agent is also the wrong one: hand the workflow a gateway URL, drop a bearer token into its environment, and let nested CLI calls pretend they are first-class integration. It works right up until the workflow runs
06 Jun 2026 3 min read
OpenRouter OAuth in OpenClaw Is About Model Routing Without Another Secret-Handling Ritual
openclaw

OpenRouter OAuth in OpenClaw Is About Model Routing Without Another Secret-Handling Ritual

OpenRouter OAuth in OpenClaw sounds like a login convenience. It is more important than that, because provider authentication is becoming part of the agent control plane. The more an agent runtime depends on model routing, fallback chains, free-tier testing, media providers, and per-team billing profiles, the less acceptable it is
06 Jun 2026 3 min read
OpenClaw's Microsoft Foundry Bugs Are What Enterprise Agent Integration Actually Looks Like
openclaw

OpenClaw's Microsoft Foundry Bugs Are What Enterprise Agent Integration Actually Looks Like

Enterprise agent integration does not usually fail in the dramatic places. It fails in the seams: the auth mode that passes its connection test but cannot persist config, the alias provider that looks equivalent to the base provider until one request argument crosses the wire, the reasoning knob that is
06 Jun 2026 3 min read
Microsoft Is No Longer Content Renting the Frontier — MAI Is Its Bid for AI Self-Sufficiency Inside Azure
azure-ai

Microsoft Is No Longer Content Renting the Frontier — MAI Is Its Bid for AI Self-Sufficiency Inside Azure

Microsoft’s relationship with OpenAI is no longer the whole Azure AI story. That does not mean Microsoft is breaking up with the lab it helped bankroll with more than $13 billion. It means the company has decided that renting the frontier is not enough when the frontier is now
06 Jun 2026 5 min read
llama.cpp Adds Qwen-VL Video Plumbing and Fixes Reasoning Leakage Where Local Models Actually Break
ai-models

llama.cpp Adds Qwen-VL Video Plumbing and Fixes Reasoning Leakage Where Local Models Actually Break

The least glamorous local-AI work is usually the work that decides whether local AI is usable. A model card can promise a better Qwen, a smaller quant, a longer context window, or a more capable reasoning path. Then the serving stack has to make that promise survive contact with chat
06 Jun 2026 5 min read
← Newer Posts Page 47 of 141 Older Posts →
The LGTM © 2026
  • Sign up
Powered by Ghost