'After 16 Years of Research': AI Models Hit 'Celeryman-Complete' in New Meme Benchmark
gabriel1 · x · 2026-10-07
Developer turtlesoupy joked that "after 16 years of research, AI models have become celeryman-complete," launching celeryman.fun — a gag site riffing on the "X-complete" benchmark trope by rating models against a character called Celeryman. Gabriel Guberovic chimed in with a one-word "science" endorsement, classic AI-community self-aware humor.
Related event: Dev Jokes That AI Has Finally Achieved 'Celeryman-Complete' Status(3 posts)→
More from Fun
- OpenAI co-founder digs up still-working API key from the GPT-4 launch hackathon era — gabriel1 · 2026-10-07
- "I read all of the OpenAI math preprints and they all check out" — AI circle quip — airkatakana · 2026-10-07
- CS PhD submitted his no-LLM thesis the exact day Claude 3 Opus launched — willcb · 2026-10-07
- "OpenAI solves math while I answer Stripe billing pages — basically the same" — generativist · 2026-10-07
- "Convert all 722 preprints into 3blue1brown videos. Don't make mistakes" goes viral as a prompt meme — willcb · 2026-10-07
- AI turns OpenAI's 199-page zeta proof into a 2-minute 3D animation claiming first zero-free strip past 7/8 — imjustnewatai · 2026-10-07