Dev jokes about running 10 parallel Sol 6.1 sessions to beat seconds-per-token speeds
mgostIH · x · 2026-10-01
Developer mgostIH jokes that Sol 6.1 inference runs at "seconds per token" rather than "tokens per second," forcing him to run 10 parallel sessions just to get work done — a relatable meme about painfully slow model serving.
More from Fun
- Anthropic Co-founder Daniela Amodei Used Stuffed Animals as a Personal Advisory Council, Report Says — Polymarket · 2026-10-01
- User Asked Claude Opus to Mercilessly Mock the Loser — and It Was Him — justin_hart · 2026-10-01
- Developers panic over a missing Codex 'remote' button, echoing community love for Codex — Dimillian · 2026-10-01
- Gemini 4 Pro Turned a Fly Into a Luxury Watch in One Prompt, Under 7 Minutes — cgarciae88 · 2026-10-01
- Parody video 'AI CEOs Panel' hilariously wraps up recent AI podcast moments — abursuc · 2026-10-01
- Robot parade in town: Dexmate 3D-printed a hat for a researcher's daughter — chris_j_paxton · 2026-10-01