The LGTM (Page 40)

The LGTM

Sign in Subscribe

GitHub Copilot App 0.2.28 Puts AI Credit Spend Where Developers Can Actually See It

GitHub Copilot App 0.2.28 Puts AI Credit Spend Where Developers Can Actually See It

GitHub Copilot app 0.2.28 is the sort of release that product teams like to call “quality of life.” That undersells it. The release puts token usage, context window, and AI credit spend into quick chats, which is exactly where agent cost visibility belongs: next to the developer making

Codex 0.139 Alpha 2 Turns Sandbox Policy Into Something You Can Debug

Codex 0.139 Alpha 2 Turns Sandbox Policy Into Something You Can Debug

Codex 0.139.0-alpha.2 looks, at first glance, like another fast-moving prerelease in a repository that already ships faster than most teams can read the changelog. That is the wrong read. The interesting part of this alpha is not the version number; it is the shape of the work:

Claude Code Action 1.0.141 Is a Tiny Bump With a Big CI Runtime Surface

Claude Code Action 1.0.141 Is a Tiny Bump With a Big CI Runtime Surface

Claude Code Action v1.0.141 is a six-file dependency bump. That is the kind of release people ignore right up until their CI agent is running yesterday’s runtime against today’s threat model. The release landed June 8, one minute after Claude Code v2.1.169. The compare

Claude Code 2.1.169 Adds Safe Mode Because Agent Customization Finally Needs a Circuit Breaker

Claude Code 2.1.169 Adds Safe Mode Because Agent Customization Finally Needs a Circuit Breaker

Claude Code v2.1.169 is not a feature release pretending to be a platform shift. It is something more useful: a runtime admitting it has become complex enough to need a circuit breaker. The headline addition is --safe-mode, also available through CLAUDE_CODE_SAFE_MODE. When enabled, Claude Code

NVIDIA’s NVFP4 MaxText Recipe Makes 4-Bit Training Look Operational, Not Experimental

NVIDIA’s NVFP4 MaxText Recipe Makes 4-Bit Training Look Operational, Not Experimental

Everyone wants to talk about agents because agents demo well. NVIDIA’s more important June 9 story is less photogenic: making 4-bit training boring enough that infrastructure teams can put it into a budget spreadsheet. The company published a JAX and MaxText recipe for training large language models with NVFP4

Anthropic’s Biology-Agent Benchmark Says the Model Is Not the Whole System

Anthropic’s Biology-Agent Benchmark Says the Model Is Not the Whole System

The most useful thing in Anthropic’s new biology-agent paper is not that GPT-5.5 beat Claude Sonnet 4 on a benchmark. That is scoreboard trivia. The useful thing is that both numbers got much less important once the researchers stopped asking models to reverse-engineer a messy scientific website and

Qwen Code’s June 8 Nightly Reverts Yesterday’s Agent Memory Win — and That Is the Point

Qwen Code’s June 8 Nightly Reverts Yesterday’s Agent Memory Win — and That Is the Point

Qwen Code’s June 8 nightly looks like a one-line rollback. That is exactly why it is worth reading. The new release, v0.17.1-nightly.20260608.aea34fa2c, reverts yesterday’s move to expose /remember, /forget, and /dream through ACP mode. In ordinary release-note accounting, that is negative progress: feature lands,

Doosan Shows NVIDIA’s AI Factory Problem Is Also Power, Boards, and Robots

Doosan Shows NVIDIA’s AI Factory Problem Is Also Power, Boards, and Robots

The Doosan announcement is the NVIDIA Korea story that looks the least like software news and the most like actual infrastructure news. That is exactly why it deserves attention. AI factories are usually described as if the hard part is choosing accelerators and drawing a heroic rack diagram. Doosan is

SK hynix Is the Memory Roadmap Behind NVIDIA’s AI Factory Pitch

SK hynix Is the Memory Roadmap Behind NVIDIA’s AI Factory Pitch

The NVIDIA-SK hynix partnership is the least flashy kind of AI news and therefore one of the most important. It is not a new chatbot, not a benchmark victory, not a demo of a robot folding a shirt under studio lighting. It is a reminder that the token economy runs

LG Is NVIDIA’s Physical-AI Productization Test, Not Just Another AI Factory Buyer

LG Is NVIDIA’s Physical-AI Productization Test, Not Just Another AI Factory Buyer

NVIDIA’s deal with LG is easy to misread as another “AI factory” press release, which is now the industry’s default way to say “we bought a lot of GPUs and would like the market to clap.” The more useful read is sharper: LG is one of the few

LiteLLM 1.89 RC Turns MCP and A2A From Connectors Into Governed Agent Infrastructure

LiteLLM 1.89 RC Turns MCP and A2A From Connectors Into Governed Agent Infrastructure

LiteLLM’s v1.89.0-rc.1 looks, at first pass, like another gateway release with the expected parade of provider additions and integration fixes. That is the wrong read. The important story is that LiteLLM is turning MCP and A2A from “connectors my agent can call” into governed infrastructure: signed