The LGTM (Page 57)

The LGTM

Sign in Subscribe

Foundry’s Model Story Is Really About Cost Discipline, Not a Bigger Dropdown

Foundry’s Model Story Is Really About Cost Discipline, Not a Bigger Dropdown

The least useful way to cover Microsoft Foundry’s model update is to recite the catalog. DeepSeek, Gemma, Llama, Mistral, Kimi, Qwen, GLM — fine, the dropdown is bigger. Builders do not need another model-name parade. The real story is that Foundry is pushing model choice toward operations discipline: contracts, evals,

Microsoft’s Open Trust Stack Is an Attempt to Make Agent Guardrails Portable Instead of Prompt-Shaped

Microsoft’s Open Trust Stack Is an Attempt to Make Agent Guardrails Portable Instead of Prompt-Shaped

The least convincing agent safety plan is still the most common one: tell the model not to do the bad thing and hope the stochastic parrot respects the policy under pressure. Microsoft’s Build 2026 “open trust stack” is worth paying attention to because it points in a better direction.

Hosted Agents Are Becoming Azure’s Agent Runtime, and the Boring Parts Are the Product

Hosted Agents Are Becoming Azure’s Agent Runtime, and the Boring Parts Are the Product

Agent platforms usually fail in the gap between the demo and the incident review. Microsoft’s latest Hosted Agents update is interesting because it spends most of its calories in that gap: isolation, identity, filesystem state, traces, versioning, evals, guardrails, voice transport, rollback, and deployment plumbing. In other words, the

Copilot CLI’s Rubber Duck and Scheduled Prompts Make Terminal Agents More Reviewable

Copilot CLI’s Rubber Duck and Scheduled Prompts Make Terminal Agents More Reviewable

GitHub’s latest Copilot CLI release looks like a grab bag: a better terminal UI, a rubber-duck critic, scheduled prompts, and local voice input. It is more coherent than that. This is GitHub turning the terminal agent from a chat box with shell access into a workbench with critique, cadence,

Google’s AI Search Opt-Out Is Real Progress. The Missing Click Data Is the Tell

Google’s AI Search Opt-Out Is Real Progress. The Missing Click Data Is the Tell

Google’s new AI Search controls are not a generosity story. They are a power story with a dashboard attached. On Wednesday, Google began testing a new Search Console toggle that lets website owners decide whether their content can appear in and help ground generative AI Search features, including AI

NVIDIA’s DGX Spark Update Makes Local Agents Look Less Like a Hobby and More Like Infrastructure

NVIDIA’s DGX Spark Update Makes Local Agents Look Less Like a Hobby and More Like Infrastructure

Local AI agents have spent the last two years trapped between two unsatisfying defaults: tiny models that fit on developer hardware but collapse under real repo context, and frontier APIs that work well until the bill, data policy, or network dependency becomes the product constraint. NVIDIA’s latest DGX Spark

Copilot SDK GA Makes Agent Runtime Embedding a Build-vs-Buy Decision

Copilot SDK GA Makes Agent Runtime Embedding a Build-vs-Buy Decision

GitHub just made the Copilot SDK generally available, which sounds like a package-management footnote until you notice what is actually being sold: not another chatbot wrapper, but an agent runtime that product teams can embed without rebuilding the entire scary middle of agent software. That middle is where most “we’

Recall Makes Agent Memory Boring: Search the Chats You Already Have, Don’t Invent a Second Brain

Recall Makes Agent Memory Boring: Search the Chats You Already Have, Don’t Invent a Second Brain

Most agent-memory products start from the assumption that developers need another brain. Recall starts from a better assumption: developers already have the memory, it is just scattered across chat histories they cannot search well. Cursor sessions, Claude Code JSONL files, Codex CLI rollouts, pi conversations — the answers are often already

AgentCAD Turns Claude Code Into a Parametric CAD Operator — With JSON Where the Vibes Usually Go

AgentCAD Turns Claude Code Into a Parametric CAD Operator — With JSON Where the Vibes Usually Go

AI CAD keeps getting marketed as if the hard part is turning a sentence into a shape. AgentCAD is interesting because it refuses that premise. The hard part is not convincing a model to emit a cube with a fillet; any decent coding agent can write plausible Python for that.