Jev
TypeSafe's general-purpose classifier model optimized for speed and cost over traditional LLMs. Every AI Coding Weekly story on Jev, newest first. 5 stories since September 2026.
- Theo's Jev router benchmark shows no win on cost or speed
A $1,000 overnight run on DeepSWE put OpenRouter's new router level with GPT-6 Astra on low, slightly pricier and almost 5x slower.
- Two teams benchmark Jev, and it wins on speed and accuracy
Independent evals from Malte Ubl and the fx team both put Jev ahead of the small models they were already running.
- Theo lists six problems with Jev compaction, Armin Ronacher pushes back
A demo that scores every tool call and deletes the rest turned into the week's argument about what a fast classifier can actually decide.
Have the good opinion, not the loud one
One email a day. Under three minutes. What working engineers found out about coding with AI.
- Theo says ranking reasoning outputs is Jev's worst use
Malte Ubl counters with the Lean proof argument, that checking work is easier than doing it.
- Mario Zechner calls TypeSafe's Jev a general purpose classifier
Same-day impressions, one price tag, and no evals yet.
Get the next one by email
Coding with AI, read daily so you do not have to. The experiments, the receipts and the arguments from engineers shipping real software. Not a changelog.