LIVE · refreshes every 20 min

updated Sep 4, 22:02 UTC

← 110010.art all stories

Hacker News (AI) ·Jul 21, 2026

Ask HN: Claude Blind Test Results reveal bug or feature?

Read the original at news.ycombinator.com→

Original headline: "Ask HN: Claude Blind Test Results: Bug or Feature?"

Coverage timeline

Jul 21, 15:34 UTC Hacker News (AI) lead source Ask HN: Claude Blind Test Results: Bug or Feature?

Related stories

ChatGPT, Grok, and Claude experience simultaneous outages; OpenAI, xAI, and Anthropic report elevated errors across products.

The Verge AI · 1d ago · source ↗

Moonshot AI unveils Kimi K3, a 2.8-trillion-parameter model described as their most capable to date, with open weights promised by July 27, 2026.

Simon Willison · Jul 16, 2026 · source ↗

How Claude's text watermarking works

Anthropic (via Google News) · 21d ago · source ↗

Gemini vs. Claude: which AI model created a better perfume?

Hacker News (AI) · just now · source ↗

Anthropic releases Claude Fable 5.1 and Claude Mythos 5.1, with Fable 5.1 reportedly cheaper for agentic work.

Anthropic (via Google News) · 3d ago · source ↗