The LGTM (Page 33)

The LGTM

Sign in Subscribe

Gemini CLI’s Antigravity Migration Is Really an Auth Migration

The Gemini CLI to Antigravity CLI migration was never going to fail because developers could not find the new command. It was going to fail because the old tool had quietly accumulated state: OAuth clients, Workspace scopes, local token files, Cloud project IDs, MCP servers, environment variables, and just enough

DeepMind Is Funding the Safety Work Agent Builders Keep Hand-Waving Away

The agent industry has spent the last year demoing little teams of bots as if parallelism were the same thing as management. One agent writes code, one reviews it, one searches docs, one opens a pull request, and the slide says “autonomous workforce.” Cute. Also incomplete. The hard part is

DIRECT Says Bigger VLM Planners Are Often Just Slower. Route the Robot's Brain Instead

Robots make the agent-cost problem impossible to ignore. A browser agent can waste twenty seconds “thinking” and merely irritate you. A robot arm doing the same thing is just standing there, burning latency in the physical world while a banana waits for a frontier model to discover object permanence. That

Qwen Code 0.18 Preview 2 Turns Agentic Coding Into an Orchestration Problem

Qwen Code 0.18 Preview 2 Turns Agentic Coding Into an Orchestration Problem

Qwen Code 0.18.0-preview.2 is not a “new model got better at coding” story. That would be too easy, and frankly less interesting. Alibaba’s coding agent is moving into the harder layer: orchestration, permissions, desktop integration, long-running work, and the weird runtime seams that determine whether an

Halos OS Is NVIDIA’s Argument That Robotaxi Safety Needs a Stack, Not a Slogan

Halos OS Is NVIDIA’s Argument That Robotaxi Safety Needs a Stack, Not a Slogan

NVIDIA’s Halos OS announcement is not really about robotaxis. It is about what happens when autonomous-driving demos have to become boring enough for regulators, insurers, cities, fleet operators, and passengers to trust them. That distinction matters. The robotaxi industry has spent years selling capability: better perception, smoother planning, more

Azure Skills 1.1.68 Is a Small Release With a Big Signal: Cloud Agents Need Approval Gates, Not Prompt Packs

Azure Skills 1.1.68 is a small release with a product lesson hiding in plain sight: cloud agents do not need more charming prompt packs. They need governed workflows that know when to stop. Microsoft’s Azure Skills Plugin repository merged PR #137 on June 9, an automated sync

Microsoft's AI Investigation Playbook Turns Copilot Telemetry Into Incident Response Plumbing

Microsoft's AI Investigation Playbook Turns Copilot Telemetry Into Incident Response Plumbing

AI incident response has reached the boring phase, which is exactly when it starts to matter. Microsoft’s new investigator playbook for reconstructing AI activity across Microsoft 365 Copilot and Azure AI services is not the kind of announcement that wins a launch-day popularity contest. There is no new model,