Rumor: DeepSeek to Launch 800B Model; KOL Jokes 'If True, Lmao'
teortaxesTex · x · 2026-07-23
In response to rumors about DeepSeek (Wenfeng) potentially launching an 800B active parameter model named Mythos, an AI community KOL joked about it. He quipped that it might be a terrible experiment like GPT-4.5, and if the rumor is true, it would be hilarious.
More from Models
- Flux 3 is pitched as one multimodal AI for images, video, and reasoning — mark_k · 2026-07-24
- Microsoft says MAI models are now routing traffic in Copilot, Excel, and Outlook — satyanadella · 2026-07-24
- A user says OpenAI is in a different league on usefulness than Opus 4.8 — FlorianGallwitz · 2026-07-24
- OpenAI and Anthropic logos frame a “the labs never sleep” snapshot of frontier rivalry — MeetPatelTech · 2026-07-24
- GPT-5.6 Benchmarked on Slay the Spire, Shows Surprising Gaming Prowess — Jsevillamol · 2026-07-24
- Laguna S-2.1 GGUF fixes its chat template and thinking traces — fragment_me · 2026-07-24