Distilled DeepSeek 14B still fails the Voight-Kampff test locally
Apoorva__Lal · x · 2026-08-22
User shares a chain-of-thought snippet from a locally running Distilled DeepSeek 14B model. The reasoning process exhibits distinct 'machine logic', humorously compared to failing the Voight-Kampff test from Blade Runner.
More from Fun
- NoSpoon Agent generates MV in 11 minutes, AI music video workflow test — Kyrannio · 2026-08-22
- Coworker sent unformatted Markdown table that AI couldn't read directly — verrsane · 2026-08-22
- Someone made a 'Now That's What I Call Slop!' album of AI-generated bangers — gabrielchua · 2026-08-22
- AI handles entire loop from exam creation to grading, sparking replacement fears — kuanhoong · 2026-08-22
- ChatGPT's new memory feature roasts user for having 14 active side-quest threads — RileyRalmuto · 2026-08-22
- Fun drawing tool lets you see others drawing in real-time — talkaboutdesign · 2026-08-22