Explainers and tests of unconventional AI model designs: looped and recurrent transformers, diffusion LLMs, world models and decision models.
NVIDIA Dory1.0-4B scores 50.3 to 61.8 on SWE-bench Verified from 1 to 4 loops. See how it compares with Qwen3.5-4B, Qwen3.5-9B and Gemma 4.
Mercury 3 is a diffusion LLM that hits 1,068 tokens/s. See how it differs from autoregressive models and how it compares with Haiku 5.5 and GPT-6 Luna.
Mercury Decide returns an answer and probability in about 0.16 seconds, now with images. How it works, its independent evals, and how to pair it with Mercury 3.
Dory1.0-4B is NVIDIA's looped 4B language model that reuses a shared layer block to scale compute per token. Architecture, loop counts, and benchmarks.
Compare AI decision models like Jev, OpenAI's Decisions API, and Laya with LLMs: how they work, cost, latency, benchmark results, and when to use each.
Decision models return typed choices and scores; execution models and sandboxed code act on them. Compare latency, cost, and real benchmarks.
Jev made fast, cheap decision models mainstream. CLM makes them self-hostable and fine-tunable. A numbers-first comparison of speed, cost, accuracy, and ownership.
RLCD trains models like Jev to output calibrated decisions, not text. Here's how it works, the real speed and cost numbers, and why 'can't hallucinate' isn't 'can't be wrong.'
Jev-class decision models trade text generation for typed choices, scores, and probabilities, running 40-400x cheaper and up to 200x faster than chat LLMs.
What is a System 1 AI model versus JEV? A grounded look at fast, calibrated classifiers versus reasoning LLMs for GUI and form-filling agents.
Infinite-parameter LLMs turn live data into model weights instead of prompts. Here's how they work, and what they change for data engineering teams.
Looped transformers reuse the same layers repeatedly to reason in hidden math, not words. Here's how they work, why OpenAI's Astra uses them, and the safety tradeoff.
Recurrent depth loops shared transformer layers instead of stacking new ones. Here's how it powers GPT-6 Astra and why it raises governance concerns.
AI world modeling means predicting the next state of an environment, not just the next word. Here's what it is, where it came from, and why it matters for coding agents.