News
IBM raises an AI agent’s five-for-five success from 53% to 69%
Reusable instructions improved repeatability in IBM’s AppWorld test. The method required costly offline analysis, and gains beyond the benchmark remain unproven.
open-source
Articles
News
Datasette patches private-data leaks after AI-assisted audit
Public-web operators should update to 0.65.4 or 1.0a39 now. One flaw let visitors test secret values in tables they could not read.