Skip to contentSkip to stories
Updated

#Reasoning

Oct 1

  1. Anthropic ResearchAI score60

    Matthew Schwartz on finding Claude-shaped science problems with BootLoops

    AIPhysicist Matthew Schwartz describes building BootLoops, an open-source harness for exact quantitative calculations, after choosing problems suited to Claude's strengths. He reports that Claude solved long-standing integrals and found connections across ecology, population genetics, economics, and linguistics, with domain experts steering results toward questions those fields care about. The post states that the approach required constant human oversight, since Claude often overstated results and misjudged time.

    Why it matters: The guest post explains why scientists often find current AI tools frustrating and offers a method for finding problems where AI and researchers match, backed by concrete projects.

Sep 27

  1. Xiaomi MiMoAI score62

    Xiaomi MiMo Explains Fixing Tool-Call Repetition in MiMo-V2.6 Models

    AIXiaomi MiMo reports that tool-call repetition in MiMo-V2.6 reached over 0.05% of responses across agent harnesses, causing stalled agents and wasted context. The team traced the cause to an RL flooding penalty set at 32 calls per turn, which missed smaller excess behavior, and replaced the approach with a specialized teacher distilled via MOPD. Repetition rates for both Pro and Flash dropped substantially, at roughly $90,000 versus an estimated $2.31 million for the alternative fix.

    Why it matters: The post traces an agent failure to a reward blind spot and compares the costs of two fixes, offering a transferable debugging method for RL-trained tool-calling models.

Sep 14

  1. vLLM BlogAI score62

    How vLLM Speculators trained a DSpark draft model for Kimi K3 on GB300 NVL72

    AIThe vLLM team trained a DSpark speculative decoding draft model for Kimi K3, a 2.8T-parameter model, using the Speculators library on GB300 NVL72 hardware. They added a MooncakeHiddenStatesConnector to stream hidden states from disaggregated vLLM inference nodes to training nodes across multiple machines. The released speculator raises single-stream interactivity from about 110 to about 435 tokens per second per user on math reasoning, with up to about 3.5x higher output throughput under concurrent load.

    Why it matters: The post shows how hidden-state extraction and Mooncake transfers let a 2.8T-parameter model's speculator be trained across multiple nodes, a reusable pattern for similar setups.

That’s everything