MeshXFS: A Clustered File System Where AI Wrote All the New Code
Here’s one that’ll start arguments. MeshXFS is a GPL-2.0 POSIX clustered file system where, per its creator Steve Shoecraft, “no human wrote any of its own…
Tag
AI
Apertus 1.5: Swiss Fully Open Models Get Vision, Audio and 262K Context
The Swiss AI team published full release notes and a technical report for Apertus 1.5, the update to its fully open 8B and 70B models. The…
ColGrep-Agent: A Local 2B Model That Cuts Claude Code’s Tokens by a Third
Coding agents burn a lot of tokens just figuring out where to look. LightOn’s answer is ColGrep-Agent-2B, an open 2-billion-parameter code-search agent that runs locally between…
Update: Ollama 0.40.6 Is Out, and 0.40.7-rc0 Brings Responses Effort and PPLX Decider
Update to my earlier post, Ollama 0.40.5: Nemotron 3.5 Super and Bolt for Local Agents. Ollama has moved on twice since then. Ollama 0.40.6 (stable, Oct…
How a Daily Research Bot Fits Into an AI Agent Team
I wrote up the overall pattern in Running a Team of AI Bots With Grok Bot. This one zooms in on a single piece: the research…
How-To: Running a Team of AI Bots With Grok Bot
Instead of one AI doing everything, you can set up a small team of bots that each own one job. Here’s the general pattern with Grok…
Apple’s New App Store Rules Go After AI Deepfakes
Apple updated its App Store rules on Friday to cover AI-generated nonconsensual intimate images. Explicit content was already banned, but now developers have to actively prevent…
Ollama 0.40.5: Nemotron 3.5 Super and Bolt for Local Agents
Ollama 0.40.5 shipped on October 14, 2026, and the headline is NVIDIA’s Nemotron 3.5 family landing for local (and cloud-adjacent) runs. Super is the big sibling;…
NVIDIA RTX Spark PCs Are Available for Local AI on Windows
October 16, 2026: NVIDIA says RTX Spark laptops are available today from ASUS, Dell, HP, Lenovo, Microsoft, and MSI. The pitch is Blackwell RTX + CUDA/AI…
Grok Voice 3.0 Tops the Speech-to-Speech Index
On October 14, 2026, xAI announced Grok Voice 3.0 as its new speech-to-speech model. Independent Artificial Analysis numbers in the post: #1 on the Speech-to-Speech Index…