tim_sw
VLLM: Anatomy of a High-Throughput LLM Inference System
DeepSeek: Inference-Time Scaling for Generalist Reward Modeling
AI forecasting retrospective: you're (probably) over-confident
Will Scaling Reasoning Models Like O3 and R1 Unlock Superhuman Reasoning?
The Online Sports Gambling Experiment Has Failed
ByteDance's Recommendation System
Dario Amodei: Anthropic CEO on Claude, AGI and the Future of AI and Humanity
Waymo Incorporates Gemini for End to End Autonomous Driving Model
Waymo's Research on an End-to-End Multimodal Model for Autonomous Driving
Automated reasoning often makes systems more efficient and easier to maintain
Destructive Tightening
How the US Lost the Solar Power Race to China
Instruction Following Without Instruction Tuning
A Cynic's Guide to Fintech
The Dawn of a New Startup Era
Re:Former Google CEO Eric Schmidt's Leaked Stanford Talk
on Friday August 16, 2024 @02:43AM (#41263755)
False. Eric Schmidt is one of the sharper operators in tech and his effect can be seen when Google started declining after 2011 when he stepped down.
Durable Objects (DO) – Unlimited single-threaded servers spread across the world
Re:LangChain vs. LlamaIndex
on Tuesday August 06, 2024 @11:38PM (#41178036)
My 2 cents - don’t rely on these frameworks and just do it yourself (or pick libraries like Instructor over these frameworks)
I think both have the wrong abstractions for people to build more complex workflows and use cases beyond demos.