📄 文章列表
858 篇文章
AlphaSignal
Anthropic's Claude Opus 4.8 Runs Hundreds of Parallel Agents 4x More Honestly | AlphaSignal
AlphaSignal
Anthropic's Claude Opus 4.8 Hits 69.2% on SWE-Bench and Lands in Devin | AlphaSignal
AlphaSignal
Anthropic's Claude Opus 4.8 Breaks Records on the Hardest AI Benchmark | AlphaSignal
AlphaSignal
Anthropic's Claude Opus 4.8 Beats Its Predecessor but Trails GPT-5.5 by 12 Points | AlphaSignal
AlphaSignal
Anthropic's Claude Fable 5 Launched and Got Pulled by the US Government | AlphaSignal
AlphaSignal
Anthropic's Claude Fable 5 Dethrones GPT-5.5 Pro on Math | AlphaSignal
AlphaSignal
Anthropic's Claude Fable 5 Beats the Hardest Coding Benchmark in Under 2 Hours | AlphaSignal
AlphaSignal
Anthropic's Claude Fable 5 Beats Every Rival on Coding and Research | AlphaSignal
AlphaSignal
Anthropic's Claude Fable 5 Beats Every Rival but Blocks Itself on Dangerous Requests | AlphaSignal
AlphaSignal
Anthropic's Claude Beats ChemDraw at Reading Molecular Spectra Without Chemistry Training | AlphaSignal
AlphaSignal
Alibaba's Qwen3.7-Max Slashes Input Costs 90% With Automatic Prompt Caching | AlphaSignal
AlphaSignal
Alibaba's Qwen3.7-Max Runs 35 Hours Straight to Hit a 10x Coding Speedup | AlphaSignal
AlphaSignal
Ai2's ModSleuth Automatically Maps the Hidden Supply Chain Behind Open-Source LLMs | AlphaSignal
TDS
A Three-Phase Factual Recall Circuit in Gemma-2B and Gemma-12B-IT
TDS
An LLM as arbiter in RAG retrieval: picking the right candidate with reasons
TDS
3 Agents. 3 LLMs. 1 Aging GPU: Engineering Parallel Inference on Bare Metal
TDS
The Hot Path Belongs to GBDTs, Agents Own the Cold Path: A Payment-Fraud Benchmark
TDS
Amplify the Expert: A Philosophy for Building Enterprise RAG
TDS
From Local LLM to Tool-Using Agent
TDS