4 posts tagged with "agents"

Most of the "agentic AI" I've shipped so far has one uncomfortable dependency baked in: a network call to somebody else's cloud. Every tool call, every reasoning step, every retry — all of it round-trips to an API. So when Meta dropped Muse Glimmer this week, a 30-billion-parameter agentic model that runs locally on a single GPU under an Apache 2.0 license, it caught my attention for reasons that have nothing to do with benchmark charts.

Let me walk through what it is, how they pulled it off, and where I think it actually fits.

If you use AI coding agents on a real repo, you've probably noticed they keep making the same avoidable mistakes — running the wrong test command, touching files they shouldn't, inventing a table name that doesn't exist. AGENTS.md is the fix, and it's quietly becoming a cross-tool standard. But there's a catch most people miss: a lazily written AGENTS.md can actually make your agent worse. So it's worth doing properly.

Here's a frustration anyone who works with AI agents knows well: every conversation starts from zero. The model doesn't remember how your team does code review, what your design system rules are, or the workflow you painstakingly explained yesterday. And the usual fix — stuffing all of that into one giant system prompt — makes things worse as it grows, because a bloated prompt dilutes the model's attention. SKILL.md is a genuinely clever answer to this, and I think it's one of the more important ideas in agent tooling right now.

Most AI coding tools still assume you're sitting in the driver's seat, hands on the keyboard, with the AI whispering suggestions. Google Antigravity starts from a different premise: what if the AI is the one doing the work, and your job is to direct and verify it? It's an agentic development platform, and the framing — the editor as mission control rather than a text buffer — is the interesting part.