How come these buttons show up at the same location on codex and claude app, but do completely different things. @jxnlco @trq212 can y'all sort this out?

Opus 5.5 is incredible at animations tried the circulating prompt on @LiteLLM: "make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are, like it's your showreel for a résumé. go all out."

Opus 5.5 is def very good with animations!

Gemini 3.8 Flash TTS + Opus 5.5 = Animated explainers! Grandpa explains how rotary phones worked back in the day. Prompted Opus 5.5 to explain rotary phones as a conversation, using Gemini 3.8 Flash TTS via @LiteLLM gateway.

Thanks for sharing Jake! Have been using hyperframes a lot and these are helpful

Congrats! Made a skill to mimic the launch video style here:

Claude Opus 5.5 is INSANE at recreating animations and video edits! I asked Claude Opus 5.5 to mimic its launch video and it one-shotted this video. Turned it into a skill here: github.com/misbahsy/claude-h… Used it for the announcement of Day 0 support on @LiteLLM

Agreed! That’s what devs should know about Jev, and how they could combine LLMs + Jev for different use cases.

Nice! Worked on something similar with voice and gestures

This was definitely needed, have been using hyperframes quite a bit for videos and a separate bench def makes sense

Yes, and the good thing is answers come back with probabilities and a confidence score, so you can inspect even in prod

A simple illustrative guide for Devs to build with Jev @typesafeai (agent-friendly)

Here's how the full breakdown on my local machine

Jev is a super fast video editor! Edited this entire video in less than a minute, and here's how: First, I transcribed raw vid locally with word timestamps, cut it into 16 beats, then asked Jev these seven questions about every beat: does this line need a visual at all? which card template? (18 to pick from, premade) which text effect? which transition into it? how hard do we punch in on the face? which sound effect? which word gets emphasised? Plus five about the video as a whole. Style, colour, caption treatment, energy, progress bar. 117 questions answered by jev < 1 s ~ $0.0017 Using @typesafeai via @LiteLLM

Voice + Generative UI = real vibe coding

Jev is definitely insane! What if you could just point and build a website? Uses json-render @ctatedev @LiteLLM gateway to call Jev

Yep, pdf-inspector pulls each page's text layer locally , then Jev gets that text, and answers one question: does it need OCR?

Measured on 19 documents / 155 pages, mistral-ocr-latest through a @LiteLLM gateway: OCR-only vs Jev-router 155 pages billed down to → 87 19 API requests down to → 13 35.6s → 20.7s (1.72x speed) $0.3100 → $0.1783 (1.74x savings) Repo: github.com/misbahsy/doc-rout…

Doc-OCR router using Jev @typesafeai A Jev-powered router that looks at a PDF page by page, decides which pages actually need OCR, extracts the rest locally. Result: save cost on # OCR pages + speed

TIL - Noul If you are gonna be using Jev, you might hear this too.