Jevlike open-sources reverse-engineered Jev model

// 2h agoOPENSOURCE RELEASE

Jevlike open-sources reverse-engineered Jev model

Jevlike provides an independent, open-source implementation of a "system one" model designed to quickly select from a changing list of text choices by scoring all available choices in a single pass. The repository includes training scripts, synthetic data generators, and examples demonstrating the model's ability to operate game controllers while also supporting frozen Hugging Face encoders.

// ANALYSIS

A brilliant move toward democratizing low-latency decision-making models by ditching autoregressive bottlenecks. It radically improves inference speed by scoring multiple options simultaneously in one forward pass and proves its versatility through multimodal-like applications such as scoring controller buttons from image patches in Doom and chess.

// TAGS

aillmopen-sourcefast-inferenceclassificationnlp

DISCOVERED

2h ago

2026-09-17

PUBLISHED

8h ago

2026-09-16

RELEVANCE

8/ 10

AUTHOR

rochansinha

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

MODEL38m ago

Manycore Tech open-sources UniPhysGen for robotic simulation

Manycore Tech, in partnership with Zhejiang University and UESTC, has open-sourced UniPhysGen, a physical AI model that converts raw 3D assets into interactive, simulation-ready digital twins by predicting articulation kinematics and physical properties. Alongside model weights and code, the team released the UniPhys-40K dataset and UniPhys-Bench evaluation benchmark to advance embodied AI research.

RESEARCH48m ago

Schmidhuber traces four decades of recursive self-improvement

AI researcher Jürgen Schmidhuber has published a comprehensive technical note and historical overview titled "Recursive Self-Improvement (RSI) Since 1987," surveying four decades of work in meta-learning and self-modifying computational systems. The retrospective connects foundational paradigms—including self-modifying policies, fast weight programmers, and Gödel Machines—to modern LLM agents, concluding that achieving full artificial superintelligence ultimately requires coupling self-improving software with self-replicating physical hardware in the real world.

INFRA59m ago

ASCII positions boat as cheap Daytona alternative

In an X thread recounting an encounter at Y Combinator, the founder of boat (developed by ASCII) criticized competing cloud sandbox and dev environment providers like Daytona for unreliability and high post-credit pricing, framing boat as a cost-effective, persistent VM alternative for autonomous agents. Engineered for programmatic agent execution with tools like Claude Code, boat provides dedicated Ubuntu VMs with nested Docker support, snapshot forking, and per-second billing granting roughly 555 hours of 4 vCPU compute for $20.

Jevlike open-sources reverse-engineered Jev model