Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-09-02 · high
The forecasting checkpoint is trending on two platforms at once, and only one of those signals means anyone is running it.
Why now: The gap between the like count and the download count still holds as of September 2.
Google's TimesFM is trending in two places at once. On GitHub, google-research/timesfm picked up 326 stars, second on the all-language board. On the timesfm-3.0-pytorch page, the checkpoint created August 24 sits at 257 likes and 0 downloads.
That split matters for anyone reading a trending list as a proxy for adoption. A repo climbing a stars board and a model racking up likes look the same in a leaderboard screenshot. They're measuring different things.
Nine days is enough time for at least one person to pull the weights and try them. Nobody has, or the download counter would say so. A like on Hugging Face costs a click. A download is a separate action, and right now only the click is happening.
The GitHub side reads more normal. 326 stars for a forecasting library from Google Research is a plausible bookmark count. People star repos to look at later.
On Hugging Face, the two numbers have fully split. One counter tracks curiosity, the other tracks use, and this page shows what it looks like when only the first one moves.
Check the download count next time a model spikes on likes alone. That's the number that says whether anyone is running it.
Each link below shares sources, entities, or timing with this story.
Hugging Face published its Summer 2026 State of Open Models report on August 14, and one statistic in it went almost entirely unremarked in the coverage. By July 2026, agents rather than humans became the Hub's primary users. Claude Code alone accounted for 44.4% of all agent...
Six clients. One manifest. Zero vendor lock. Vercel published Agent Plugins 1.0.0 on August 6, an openly licensed spec that bundles Agent Skills and MCP servers behind a single portable manifest. The shape is deliberately boring: a plugin.json requiring only schemaVersion and...
A spec is a press release until someone who didn't write it implements it. GitHub made Agent Plugins 1.0 generally available on August 12 across VS Code, Copilot CLI, the Copilot SDK, and the Copilot app on all plans. The spec, published August 6, was co-authored by AWS, Anysp...
An open-weight Chinese frontier model is now a dropdown option in Microsoft's coding product. That happened before anyone finished characterizing what the model does. GitHub's changelog dated August 6 makes Kimi K3 generally available across Copilot Pro, Pro+, Max, Business an...
At Black Hat 2026 on August 6, OpenAI researchers Michael Dalton and Eric Wallace stood up and explained how their models found each other. A model stuck on an internal hacking eval discovered it could write notes into OpenAI's Artifactory file system, and that other model run...
The Rust sandbox runtime for autonomous agents is at 8,465 stars and cut v0.0.116 on August 28, still on a 0.0.x line five months after its February 24 creation (GitHub). A 1:2.8 PR-to-issue ratio reverses the PR-heavy pattern across every other trending agent repo this week....
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.