Jev versus text-generating models
Jev does not generate free-form text. A side-by-side video compares parallel decision-making with token-by-token text generation.
Experimenting with TypeSafe AI's Jev in Playground: Testing Semantic Evaluation via HEX/RGB
Testing Jev in Playground: hiding Choice candidate names as option_a etc. and providing only HEX/RGB values to see if the model evaluates them semantically as colors. When one of a candidate's HEX or RGB values is changed to red to create a contradiction, its probability drops to nearly 0%; no clear HEX-first or RGB-first bias observed so far.
TypeSafe AIの #Jev を Playground で実験なう✨ Choice の候補名を option_a 等に隠してHEX/RGB だけ与えても、値を色として意味的に評価する様子。 例えば blue 候補の HEX か RGB の片方だけデータで赤に変えて矛盾させるとその候補確率はほぼ0%。 HEX優先／RGB優先の偏りは今のところなさそう🤔
· 5 likesOpen on X
More like this
Pricing, evaluations, and the name Jev
The launch thread explains code-and-AI workflow evaluations, the input price announced at launch, and free output tokens.
Jev Model: Decision-Making Probability Generation, 200× Faster and 400× Cheaper Than LLMs
This model is built for decision-making rather than text generation, outputting probabilities for each option in parallel instead of token-by-token responses. The author shares a simplified comparison of normal LLMs versus this Jev model.
