←Search results

Search “Reasoning”

By relevance · Total 695 results Clear search

Saturday

  1. A6 a6-047 · Baseten Engineering Blog

    Baseten Engineering Blog Research Articles List: GLM-5 Inference Optimization and Legal Agent Training

    The Baseten Engineering Blog research section features several articles, including "How we built the fastest GLM-5 on Artificial Analysis," post-training frontier legal agents in collaboration with Harvey, dark-free distillation, BYO SWE-grep automatic training of search sub-agents (Part 1), Lumina customer-in-the-loop self-improving evaluation, attention-based attribution, and robust sample-efficient SFT with prompt mutation. Popular models listed on the page include DeepSeek V4.1 Flash, GLM-5.3 Fast, GLM-5.3, GLM-5.3-Flash, Kimi K3, and Whisper Large V3.

    The Baseten Engineering Blog research section features several articles, including "How we built the fastest GLM-5 on Artificial Analysis," post-training frontier legal agents in collaboration with Harvey, dark-free distillation, BYO SWE-grep automatic training of search sub-agents (Part 1), Lumina customer-in-the-loop self-improving evaluation, attention-based attribution, and robust sample-efficient SFT with prompt mutation. Popular models listed on the page include DeepSeek V4.1 Flash, GLM-5.

    Matched fieldsTitle

    #a6-editorial#English text is being prepared.

Friday

Thursday

  10. A6 a6-051 · Cerebras：BlogSelected

    Cerebras explains model and reasoning-effort selection for GPT-5.6 Sol, Terra, and Luna

    Cerebras published a post introducing the three GPT-5.6 models Sol, Terra, and Luna in the Codex subscription; the three are trained and deployed independently and come with reasoning-effort levels, used to trade off among speed, cost, and intelligence. On price, Terra is half of Sol, and Luna is one-fifth of Sol, for both short and long contexts. The article suggests starting most tasks with Luna and upgrading to Terra or Sol when progress stalls; Sol can reach 750 tokens/s on Cerebras, and it also explains how to use the five reasoning levels in Codex, from Light to Ultra.

    Cerebras published a post introducing the three GPT-5.6 models Sol, Terra, and Luna in the Codex subscription; the three are trained and deployed independently and come with reasoning-effort levels, used to trade off among speed, cost, and intelligence. On price, Terra is half of Sol, and Luna is one-fifth of Sol, for both short and long contexts. The article suggests starting most tasks with Luna and upgrading to Terra or Sol when progress stalls; Sol can reach 750 tokens/s on Cerebras, and it

    Matched fieldsTitle

    #a6-editorial#Tutorials / practice#Reasoning#English text is being prepared.