Markets

Weather

Loading weather

AI

AI models, agents and LLM tooling

dev.to (home feed)

Apple Vision OCR runs 300x faster than a local 27B VLM but destroys table structure

1 hour agoRead more

dev.to (home feed)
Runtime gateways and layered defenses: how teams govern AI agents in production
4 hours ago
dev.to (home feed)
OpenAI launches GPT-6 Astra with 1.05M-token context, new pricing and reasoning tiers
4 hours ago
dev.to (home feed)
SWE-Bench ProMax: best model solves 41.2% of large multilingual refactors
5 hours ago
dev.to (home feed)
Benchmark finds Q4_K_M nearly twice as fast as MXFP4 for local LLMs on M2 Mac
5 hours ago
dev.to (home feed)
Unsloth Desktop wraps llama.cpp and MLX into one-click local AI setup
6 hours ago
dev.to (home feed)
Unit 42 traces LLM-assisted intrusion attempts against Mexican and Brazilian targets
6 hours ago
Hacker News – Front Page (hnrss.org)
GPT-6 Astra catches up to 20% more cross-file bugs in early CodeRabbit review
6 hours ago
dev.to (home feed)
Claude agents produce first computer-checked Lean proof of Fermat's Last Theorem
7 hours ago
Hacker News – Front Page (hnrss.org)
Moadim: an open-source loop engine that runs AI agents on a schedule against your repos
9 hours ago

dev.to (home feed)

Apple Vision OCR runs 300x faster than a local 27B VLM but destroys table structure

1 hour ago

dev.to (home feed)
Runtime gateways and layered defenses: how teams govern AI agents in production
4 hours ago
dev.to (home feed)
OpenAI launches GPT-6 Astra with 1.05M-token context, new pricing and reasoning tiers
4 hours ago
dev.to (home feed)
SWE-Bench ProMax: best model solves 41.2% of large multilingual refactors
5 hours ago
dev.to (home feed)
Benchmark finds Q4_K_M nearly twice as fast as MXFP4 for local LLMs on M2 Mac
5 hours ago