TypeSafe AI launched Jev, a structured decision model that returns probabilities instead of free-form text, claiming 70–500ms response times and significantly lower costs than large language models. The company raised $40 million in seed funding led by DCVC, though independent performance verification remains limited.
Jev is a specialized AI model that produces only structured output rather than free-form text, enabling it to generate responses in parallel rather than autoregressively. This architecture delivers dramatically faster latency (70-500ms versus seconds for standard LLMs) and enables new use cases like real-time video game playing, suggesting structured output could become a fundamental computational primitive for AI systems.
A new DuckDB extension enables users to classify rows in CSV, Parquet files, or DuckDB tables using Jev. It processes approximately 1,000 rows in 10 seconds, offering faster performance than LLMs and better ergonomics than traditional classifiers for data analysis workflows.
TypeSafe AI introduced Jev, a specialized 'System One' model designed for fast, bounded decisions in production systems. Unlike general-purpose LLMs, Jev outputs typed probabilistic decisions directly rather than generating text, achieving significantly lower latency and cost for operational tasks like incident routing and severity assessment.
A reverse-engineered model mimics Jev, TypeSafe's commercial system for selecting from multiple text options in a single pass. The repository includes implementations for Doom and chess games, with training and evaluation tools using attention-based scoring across option-context pairs.
TypeSafe AI introduces Jev, a new class of System One Models designed for machine automation rather than chat. Unlike RLHF-trained language models, Jev produces typed decisions with calibrated confidence estimates, enabling reliable autonomous workflows at significantly lower cost and latency.
Jev is a specialized AI model that produces only structured output instead of human language, enabling it to generate responses in parallel within a single forward pass rather than autoregressively token-by-token. This architecture makes Jev significantly faster (70-500ms vs. seconds for traditional LLMs) and opens new possibilities for AI applications, such as real-time game playing, though the author notes that similar performance could theoretically be achieved with existing LLM optimization techniques.
A developer releases Qwen-2.5-1B-RLCD, an open-source model enabling 5x faster on-device JSON inference without new training. The same developer also announces Jev, a frontier AI model developed over 2 years using a new training method (RLCD) that claims 20-200x performance improvements.
Jev is a specialized AI model that produces only structured output instead of human language, enabling dramatically faster response times (70-500ms) and parallel processing in a single forward pass. This architectural difference unlocks new computational possibilities beyond traditional autoregressive LLMs, such as real-time game playing, though the author argues similar performance could be achieved through optimized structured output on existing models.
TypeSafe AI announced Jev, a new frontier model optimized for structured decision-making and automation rather than text generation. Jev achieves comparable intelligence to existing large language models while being 40-400x cheaper and 20-200x faster, with parallel sampling that eliminates hallucinations and type errors.