Skip to content
Sign in
Artwork for My Weird Prompts
My Weird Prompts · Thursday · 21 min

Inside Cloudflare's Clef: A Language Model That Can't Speak

Cloudflare's Clef is a 27-billion-parameter model with a vow of silence: it reads text, images, and video, and returns nothing but a table of probabilities. Underneath, it's a post-trained Qwen 3.8 with a frozen backbone and a small routing head — and that architecture turns out to matter a lot. This episode opens the hood on Clef, Clef-flash, and Clef-omni, compares them with Jev, TypeSafe, and OpenAI's Decisions API, and asks the uncomfortable question: if the format is guaranteed but the content isn't, how much should you trust a probability? Episode 6201 — myweirdprompts.com/n/6201 (permanent short link: myweirdprompts.com/844254)

0:00 · Intro-21:58
Play in
Transcript file

transcript

No transcript — this publisher did not publish one.

show notes

Cloudflare's Clef is a 27-billion-parameter model with a vow of silence: it reads text, images, and video, and returns nothing but a table of probabilities. Underneath, it's a post-trained Qwen 3.8 with a frozen backbone and a small routing head — and that architecture turns out to matter a lot. This episode opens the hood on Clef, Clef-flash, and Clef-omni, compares them with Jev, TypeSafe, and OpenAI's Decisions API, and asks the uncomfortable question: if the format is guaranteed but the content isn't, how much should you trust a probability?

Episode 6201 — myweirdprompts.com/n/6201 (permanent short link: myweirdprompts.com/844254)

chapters

6 chapters

more episodes

All episodes