📄 文章列表
356 篇文章
TDS
Context Rot: Why Claude Code Sessions Decay, and How to Govern Them
AlphaSignal
Perplexity Swaps Claude for Grok 4.5 at Half the Cost | AlphaSignal
AlphaSignal
OpenAI's LifeSciBench Exposes Where GPT-Rosalind Still Fails Real Drug Discovery | AlphaSignal
AlphaSignal
Meta and Google DeepMind Prove LLMs Memorize Exactly 3.6 Bits per Parameter | AlphaSignal
TDS
RAG vs Fine-Tuning Explained: What They Actually Do and When to Use Each
AlphaSignal
GPT-5.6 Sol Tops the Only Physics Benchmark AI Can't Cheat | AlphaSignal
TDS
Time-Series LLMs, Explained with t0-alpha
TDS
Tokenminning: How to Get More from Your Chatbot for Less
TDS
Stop Returning Text from RAG: The Typed Answer Contract That Prevents Hallucination
TDS
Validating the RAG Answer Before the User Sees It: Spans, Quotes, and the Feedback Loop
TDS
Proxy-Pointer RAG: Temporal Reasoning Without Semantic Precompilation
TDS
How to Choose Between Small and Frontier Models
TDS
How Far Can Classical NLP Go? From Bag-of-Words to Stacking on Spooky Author Identification
TDS
Surviving the Data Science Behavioral Interview
TDS
The Untaught Lessons of RAG Question Parsing: Structure Before You Search
AlphaSignal
Behold Mythos!: Anthropic released Claude Mythos 5 and Claude Fable 5, a public version with safeguards
AlphaSignal
Agentic Tests Beyond the Bug Hunt: DeepSWE, ProgramBench, and ITBench-AA push agents harder than SWE-bench
AlphaSignal
Nvidia’s Nemotron Goes Big: Nvidia Nemotron 3 Ultra bets on speed and openness to win customers
AlphaSignal
Cursor Composer undercuts competition: All the top news from Google’s I/O event
AlphaSignal