Claude-derived TF descriptions serve as rough draft before literature verification
jmschreiber91 · x · 2026-10-29
The author explains his transcription factor knowledge base: Claude-derived descriptions and citations at the bottom are not all verified—he uses them for a rough sense, then confirms interesting details via literature search. He also notes an intermittent bug where second searches fail to replace the initial search, calling it "vibe-coded slop".
Related event: Researcher Open-Sources Claude-Assisted Transcription Factor Knowledge Base(3 posts)→
More from Research
- Lie detector compiled into Qwen3.5 weights flags 91% of lies with zero false positives — teortaxesTex · 2026-10-29
- Practitioner: No serious lab actually trains on the test set today — nrehiew_ · 2026-10-29
- Researchers slam secrecy around OpenAI-linked Yang-Mills proof materials — anshulkundaje · 2026-10-29
- KITP forms Yang-Mills Working Group to vet AI-related proof, drawing skepticism — anshulkundaje · 2026-10-29
- Job-market paper: German engineering societies lifted regional patents 4.8% — Afinetheorem · 2026-10-29
- François Fleuret Skeptical of Self-Improvement Training: Only Boosts the Easy Early Part — francoisfleuret · 2026-10-29