In ViBench 2.0 the agent starts from an empty project, builds a first version of a product from a short spec, then adds up to eighteen more features on top of its own code. The benchmark has seventeen products, 241 feature requests and…
In the News: October 31, 2026 (Midday)
Replit's ViBench 2.0 has the best agents passing every test plan in 49 to 65 percent of builds, and most failures sit where features meet.
Midday edition
Machine-readable
Download Markdown
Story
Replit's ViBench 2.0: the best agents pass every test plan in 49 to 65 percent of builds
Read story →
Story
Claude Code 2.1.316 deprecates Opus 4.8 fast mode, with removal on November 30
The release notes state that fast mode for Opus 4.8 is deprecated as of October 30, 2026 and will be removed on November 30, 2026. After removal, fast mode requests on Opus 4.8 return an error and do not fall back to standard Opus 4.8.
Story
Martin Alderson on making agents fast: check thinking budgets first
Alderson applies web-performance habits to agent workflows. He argues that inference speed is only part of it: with provisioning, tools and suspend and resume unchanged, he says halving inference time takes about 20% off a task, a figure he…