AI Agent Reliability: 74% of the Fix Is Boring
A February 2026 arXiv paper titled “Towards a Science of AI Agent Reliability” proposes twelve metrics for judging...
Jev: The Language-Free System One Model at $0.042
Jev, TypeSafe’s language-free System One model, runs at a stated $0.042 per million input tokens and cannot write...
Adaptive Evidence Routing Turns Context Selection Into a Decision
Not a stuffing problem. A routing problem. RECAST landed on arXiv October 7, 2026, filed under cs.AI as...
Open-Source Multimodal Embeddings: Google’s 740M Model Rewrites the Math
Google DeepMind announced EmbeddingGemma 2 on October 6, 2026. And it pushes open-source multimodal embedding models into genuinely...
arXiv Submission Limit: Two Papers a Month, No Exceptions
arXiv now caps every submitter at two papers per calendar month. The new submission limit took effect October...
Query-Aware Multimodal Memory: Six Buckets Beat One Pile
MIRIX splits an agent’s memory into six types, Core, Episodic, Semantic, Procedural, Resource Memory. And Knowledge Vault, before...
Open-Source Web Search for AI Agents Now Costs $0
Open-source web search for AI agents has a $0 base layer now. Proof’s sitting on GitHub’s web-search topic...
AI Coding Agents Stopped Autocompleting. Devin Started It.
AI coding agents did not slowly stop being autocomplete. They stopped on March 12, 2024, the day Cognition...
OpenAI DevDay 2026 Shipped a Platform, Not a Model
OpenAI announced more than 20 products and features at DevDay 2026, held September 29 at Fort Mason in...
Autonomous AI Agents Won $750 Competing Against Human Hackers
First among the AI teams. Top-20 worldwide. Humans on the same field. And an autonomous AI agent named...