🎙️ How I AI: 8 real Jev use cases + How OpenAI uses ChatGPT Sites (live at DevDay!) + Claire’s DevDay recap
- ID
- 31963
- Status
- summarized
- Published
- 05 Oct 2026, 11:03 PM
- Fetched
- 06 Oct 2026, 1:46 AM
- Provider
- Lenny's Newsletter
- Category
- product-startup
- Original URL
- https://www.lennysnewsletter.com/p/how-i-ai-8-real-jev-use-cases-how
- Source URL
- https://www.lennysnewsletter.com/feed
Summary
- Score
- 6.5
- Created
- 06 Oct 2026, 1:47 AM
- Tags
- Audience
- developersai_ml_learnersai_agent_usersvibe_coders
What happened
In this How I AI episode, John Lindquist (creator of egghead.io, now running mega.dev) demos eight uses of "Jev" — a real-time voice assistant, data deduplication, app routing, chess analysis, multi-agent coordination, a live presentation coach and more — arguing it should be treated as a fast, cheap decision engine rather than a chatbot, since it returns scores, classifications, probabilities and function calls instead of prose. Concrete cost figures: 73 cents across 23 development runs, and a separate run where Claire processed 5 GB of JSON for 40 cents. In a chess benchmark, Jev analysed a full game in under a second — 10x faster and 4x cheaper than a low-reasoning LLM with no accuracy loss. The excerpt also teases an OpenAI ChatGPT Sites segment and a DevDay recap, but gives no details on either.
Why it matters
If your agents spend tokens on classification, routing or branch-selection calls, this is a concrete cost argument for re-pricing those paths: 73 cents over 23 dev runs and 5 GB of JSON for 40 cents is a different order of magnitude from per-token LLM calls, and the chess benchmark (10x faster, 4x cheaper, same accuracy) is the one directly comparable number. The recommended mental model — put Jev wherever a traditional program would have an if/else, switch or branch, and layer multiple cheap classifications instead of chasing one perfect prompt — is something you can apply this week. Caveat worth stating on air: the excerpt never says who makes Jev, what it costs in production, or how to access it, so treat this as a pattern to test, not a product to adopt. There is no Malaysia or Southeast Asia angle in the text.
Discussion angle
Take one branch in something you've shipped — a router, a tagger, a tool selector — and ask whether a cheap decision engine could replace the LLM call. Then argue the counter-case: where does layered classification beat one good prompt, and where does it just add latency and debugging pain?