Search Practical AI

Search everything this publication has kept. The same list is available as JSON.

• 15 Sep 2026Cloudflare Lets Sites Block AI Training Without Losing Search VisibilityCloudflare has introduced new controls that let site owners stay discoverable in search while disallowing AI training. The company says an Accountable
• 15 Sep 2026OdoBot web agent reports 44-80% fewer tokens than two rival agentsA preprint describes OdoBot, a web agent that builds a model of an application from successful task demonstrations. On 45 Canvas LMS tasks it used 44%
• 15 Sep 2026Judge-guided revision narrows the gap between cheap and costly patent draftsA preprint scores AI-drafted patents with a separate model acting as judge, then feeds that feedback back to the drafting agent. Judge-guided revision
• 14 Sep 2026GitHub Copilot auto model selection adds efficiency, balance, and intelligence tiersGitHub Copilot auto model selection now offers three tiers: efficiency, balance, and intelligence. The tier you choose reflects how you want auto to w
• 12 Sep 2026Autonomous AI Agents: What They Can Do and How to Manage the RisksA guide from the workflow-automation vendor n8n sets out how autonomous agents differ from ordinary automation, where most production deployments sit
• 12 Sep 2026OpenRouter's GPT Sol Latest alias always points to the newest modelOpenRouter lists a model entry called OpenAI: GPT Sol Latest that it says always redirects to the newest model in the GPT Sol family. The listing does
• 12 Sep 2026Nemotron specialists reach IMO gold threshold with open natural-language pipelineTwo Nemotron 3 Ultra specialist checkpoints scored 30 of 42 points at IMO 2026, the gold-medal threshold, working entirely in natural language with no
• 12 Sep 2026Handing arithmetic to a solver helps a 32B model, not a 7B oneA preprint tests whether a model can write case-specific Python for a restricted executor instead of doing clinical arithmetic itself. The handoff hel