✕ Clear all filters
9 articles
▶ Videos →

📰 Dev.to · pueding

9 articles · Updated every 3 hours · View all reads

All Articles 189,109Blog Posts 170,867Tech Tutorials 50,677Research Papers 36,770News 23,152 ⚡ AI Lessons
Cluster-Route-Escalate Cascade Serves LLMs at 97-99% Accuracy for Less Cost: Cost-Aware LLM Cascade
Dev.to · pueding 🧠 Large Language Models ⚡ AI Lesson 2mo ago
Cluster-Route-Escalate Cascade Serves LLMs at 97-99% Accuracy for Less Cost: Cost-Aware LLM Cascade
What: A new paper, Cluster, Route, Escalate (arXiv 2606.27457), is a cost-aware cascade for...
View lesson → + Playlist
S-Agent: Spatial Tool-Use Makes an 8B Agent Rival GPT-5.4 on Spatial Reasoning: Spatio-Temporal Evidence Accumulation
Dev.to · pueding 🧠 Large Language Models 2mo ago
S-Agent: Spatial Tool-Use Makes an 8B Agent Rival GPT-5.4 on Spatial Reasoning: Spatio-Temporal Evidence Accumulation
What: S-Agent is an agent framework for spatial reasoning over multi-view images and video,...
Read article → + Playlist
Baidu Unlimited OCR Holds the KV Cache Constant for 40+ Pages: Reference Sliding Window Attention
Dev.to · pueding 🧠 Large Language Models 3mo ago
Baidu Unlimited OCR Holds the KV Cache Constant for 40+ Pages: Reference Sliding Window Attention
What: The Unlimited OCR release (Baidu, arXiv 2606.23050) is a 3-billion-parameter open OCR...
Read article → + Playlist
AMD ATOM + ATOMesh: Prefill/decode Disaggregation on ROCm
Dev.to · pueding 🧠 Large Language Models ⚡ AI Lesson 3mo ago
AMD ATOM + ATOMesh: Prefill/decode Disaggregation on ROCm
What: AMD shipped ATOM + ATOMesh, a ROCm-native LLM serving stack whose headline trick is...
View lesson → + Playlist
NVIDIA Blackwell Sweeps MLPerf Training 6.0: Strong Scaling
Dev.to · pueding 🧠 Large Language Models ⚡ AI Lesson 3mo ago
NVIDIA Blackwell Sweeps MLPerf Training 6.0: Strong Scaling
What: On June 16, 2026, NVIDIA's Blackwell platform posted the fastest time on all seven...
View lesson → + Playlist
MiniMax M3 Ships Open-Weight 1M Context: MiniMax Sparse Attention (MSA)
Dev.to · pueding 🧠 Large Language Models ⚡ AI Lesson 3mo ago
MiniMax M3 Ships Open-Weight 1M Context: MiniMax Sparse Attention (MSA)
What: The MiniMax M3 release — an open-weight model with a 1M-token context and 59% on...
View lesson → + Playlist
Google Releases DiffusionGemma: Parallel Block Decoding
Dev.to · pueding 🧠 Large Language Models ⚡ AI Lesson 3mo ago
Google Releases DiffusionGemma: Parallel Block Decoding
What: Google released DiffusionGemma, an open-weight model whose headline trick is parallel...
View lesson → + Playlist
Cursor Composer 2.5: Targeted Textual Feedback RL
Dev.to · pueding 🧠 Large Language Models ⚡ AI Lesson 4mo ago
Cursor Composer 2.5: Targeted Textual Feedback RL
What: The Cursor Composer 2.5 release blog introduces targeted textual feedback RL — a constructed...
View lesson → + Playlist
Camouflage Injection Paper: Camouflage Detection Gap
Dev.to · pueding 🧠 Large Language Models ⚡ AI Lesson 4mo ago
Camouflage Injection Paper: Camouflage Detection Gap
What: The Domain-Camouflaged Injection paper shows that prompt-injection detectors collapse on...
View lesson → + Playlist