Feldar AI is building a writing benchmark probing model naming and sentence quirks
almmaasoglu · x · 2026-09-06
The Feldar AI team is building a writing benchmark that drills into the names models keep choosing, their opening words, and sentence rhythms.
- Early findings reveal curious, recurring patterns in how different models phrase and structure text
- The team says more results are coming soon; this is a preliminary peek
More from Models
- OpenAI Hits 'Automated Research Intern' Milestone, Targets Fully Automated AI Researcher by 2028 — soumitrashukla9 · 2026-09-07
- Hands-on video takes GPT 6 Astra for a test run — PurzBeats · 2026-09-07
- kimmonismus: Path to Recursive Self-Improvement Is Clear, Alignment Is the Only Problem — kimmonismus · 2026-09-07
- Qwen3.8-Max-0902 with 1M-token context ranks high on Code Arena WebDev — alifcoder · 2026-09-07
- Astra architecture debate: recurrent depth vs temporal recurrence, and a strange OpenAI leak — burny_tech · 2026-09-07
- OpenAI and Anthropic models share a favorite name, writing benchmark finds — almmaasoglu · 2026-09-07