Jev case: Built an alternative version of @typesafeai but

Rebuilt a TypeSafe-style decision pipeline on Cerebras with Qwen 3.8 27b, finding TypeSafe cheaper and faster.

The original post

Built an alternative version of @typesafeai but on @cerebras with Qwen 3.8 27b.

Similar quality, similar performance, but vastly different cost. TypeSafe was way cheaper, and did beat Qwen on performance.

Closest we can get using LLMs I think.

Source:

Quoted post

C

@CompleteSkeptic34.6M views

source

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

What the author linked

• github.com/iammrduncan/ty…
• GitHub - iammrduncan/typesafe-ai-benchmark: This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev. — This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev. - iammrduncan/typesafe-ai-benchmark

Engagement when collected

Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.