Generative AI
Anthropic Claude Opus 4.8 Ships Side by Side with Powerful Workflows and Cheap Fast Mode, with Workflows Set to 1,000 Subagents
May 28, 2026
Anthropic Claude Opus 4.8 Ships Side by Side with Powerful Workflows and Cheap Fast Mode, with Workflows Set to 1,000 Subagents
Anthropic recently released Claude Opus 4.8. Also, there are two Claude Code updates posted. A dynamic workflow uses multiple subagents…
Perplexity AI Open-Sources Unigram Tokenizer That Achieves 5x Lower p50 Latency Than Hugging Face tokenizers Crate
May 28, 2026
Perplexity AI Open-Sources Unigram Tokenizer That Achieves 5x Lower p50 Latency Than Hugging Face tokenizers Crate
Perplexity AI’s research team reimplemented their Unigram tokenizer from scratch in Rust and open-sourced the code in pplx-garden, their inference…
A Coding Guide for Using a pgvector-Powered Semantic, Hybrid, Sparse, and Quantized Vector Search System
May 28, 2026
A Coding Guide for Using a pgvector-Powered Semantic, Hybrid, Sparse, and Quantized Vector Search System
In this lesson, we create a complete pgvector playground inside Google Colab and explore how PostgreSQL can serve as a…
Sakana AI Proposes DiffusionBlocks: a Block-wise Training Framework That Converts Residual Networks into Independently Trainable Denoising Modules
May 28, 2026
Sakana AI Proposes DiffusionBlocks: a Block-wise Training Framework That Converts Residual Networks into Independently Trainable Denoising Modules
Researchers from Sakana AI and the University of Tokyo propose DiffusionBlocks. It trains transformer-based networks one block at a time.…
NVIDIA Releases Polar, a Token-Faithful Rollout Framework for GRPO Training Across Codex, Claude Code, and Qwen Code
May 27, 2026
NVIDIA Releases Polar, a Token-Faithful Rollout Framework for GRPO Training Across Codex, Claude Code, and Qwen Code
Reinforcement learning for language agents is growing more complex. Agents now manage multi-turn tool use, long-running contexts, and multi-agent orchestration.…
Meet EAGLE 3.1: A predictive coding algorithm that corrects Attention Drift in LLM Inference
May 27, 2026
Meet EAGLE 3.1: A predictive coding algorithm that corrects Attention Drift in LLM Inference
Predictive coding is a way to speed up language model prediction. A small, fast draft model raises several tokens. A…
MEMO: A Modular Framework for Training a Dedicated Memory Model on New Knowledge Without Modifying LLM Parameters
May 27, 2026
MEMO: A Modular Framework for Training a Dedicated Memory Model on New Knowledge Without Modifying LLM Parameters
Large language models become static after pretraining. Their knowledge does not update as the world changes. Retraining a full LLM…
Design an Accurate Rerank and Rerank Pipeline with ZeroEntropy Zerank-2 Reranker
May 26, 2026
Design an Accurate Rerank and Rerank Pipeline with ZeroEntropy Zerank-2 Reranker
print("n" + "="*70 + "nPART 4: NDCG@10 evaluationn" + "="*70) eval_set = [ {"query": "Where is most ATP produced in…
Stability AI Releases Stable Audio 3: A Family of Fast Latent Diffusion Models for Audio Generation and Editing
May 26, 2026
Stability AI Releases Stable Audio 3: A Family of Fast Latent Diffusion Models for Audio Generation and Editing
Stability AI has released open weights for Stable Audio 3 along with a technical research paper. Stable Audio 3 is…
Meet OmniVoice Studio: The Local, Open Source Alternative at ElevenLabs
May 26, 2026
Meet OmniVoice Studio: The Local, Open Source Alternative at ElevenLabs
OmniVoice Studio – How to Use it 01 / 08 What is OmniVoice Studio? OmniVoice Studio is an app an…