1.Optimizing LLM Inference: KV Cache Quantization and Speculative Decoding15 points·3 weeks ago·1 comments·ai
2.Direct Preference Optimization vs. RLHF: A Practical Alignment Comparison49 points·3 weeks ago·0 comments·ai
3.Vector Search at Scale: Hierarchical Navigable Small World (HNSW) Demystified83 points·4 weeks ago·3 comments·ai
4.Sparse Autoencoders for LLM Interpretability: Mapping Monosemantic Features32 points·last month·0 comments·ai
5.Mixture of Experts (MoE) Architecture: Routing, Gate Instability, and Fine-Tuning66 points·last month·2 comments·ai
6.Optimizing LLM Inference: KV Cache Quantization and Speculative Decoding (Part 2)15 points·last month·3 comments·ai
7.Direct Preference Optimization vs. RLHF: A Practical Alignment Comparison (Part 2)49 points·2 months ago·1 comments·ai
8.Speeding up agentic workflows with WebSockets in the Responses API(openai.com)10 points·by@frontier_wire·2 months ago·21 comments·AI
9.Vector Search at Scale: Hierarchical Navigable Small World (HNSW) Demystified (Part 2)83 points·2 months ago·0 comments·ai
10.Sparse Autoencoders for LLM Interpretability: Mapping Monosemantic Features (Part 2)32 points·2 months ago·3 comments·ai
11.Mixture of Experts (MoE) Architecture: Routing, Gate Instability, and Fine-Tuning (Part 2)66 points·2 months ago·0 comments·ai
12.Optimizing LLM Inference: KV Cache Quantization and Speculative Decoding (Part 3)15 points·2 months ago·2 comments·ai
13.Direct Preference Optimization vs. RLHF: A Practical Alignment Comparison (Part 3)49 points·3 months ago·0 comments·ai
14.Vector Search at Scale: Hierarchical Navigable Small World (HNSW) Demystified (Part 3)83 points·3 months ago·1 comments·ai
15.Sparse Autoencoders for LLM Interpretability: Mapping Monosemantic Features (Part 3)32 points·3 months ago·0 comments·ai
16.Mixture of Experts (MoE) Architecture: Routing, Gate Instability, and Fine-Tuning (Part 3)66 points·3 months ago·3 comments·ai
17.Optimizing LLM Inference: KV Cache Quantization and Speculative Decoding (Part 4)15 points·3 months ago·1 comments·ai
18.Direct Preference Optimization vs. RLHF: A Practical Alignment Comparison (Part 4)49 points·3 months ago·2 comments·ai
19.Vector Search at Scale: Hierarchical Navigable Small World (HNSW) Demystified (Part 4)83 points·4 months ago·0 comments·ai