Knowledgator Engineering released GLiFormer, a schema-conditioned encoder framework for information extraction, with two Apache 2.0 checkpoints on Hugging Face: GLiFormer Base v1 at 264.2M parameters …
A developer debugging a 504 Gateway Timeout on Vercel discovered that the default 10-second function execution limit was killing AI requests before the model could respond. Enabling Fluid Compute in t…
A developer building AI features for the PSS NGO website spent about $5 on OpenRouter during development. The project integrates a knowledge base with MongoDB and embeddings to control AI-generated co…
A new arXiv preprint (2608.29028v1) finds that multi-agent LLM handoffs cause 'summary collapse,' where boundary metadata governing data use is lost while operational facts survive, leading to privacy…
Researchers propose Urban-Agent, a tool-augmented agent framework that combines a large language model with code execution, API calls, and Model Context Protocol to handle cross-system urban tasks. In…
A study presented at the Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security (NLPAICS 2026) found that GPT-5-mini outperformed Qwen2.5-Coder-7…
Google researchers propose embedding the Universal Declaration of Human Rights into AI training pipelines as a forward-alignment technique for agentic AI, testing their Human Rights Taxonomy against 1…
A blogger reports that Anthropic's Claude Opus 4.8 is nearly 10 times faster than OpenAI's GPT-5 in rewriting blog comments, with both models producing equally good results. The blogger also notes a 3…
An independent developer reports that Anthropic's Claude Opus 4.8 is nearly 10 times faster than OpenAI's GPT-5 at non-streaming completions, based on side-by-side testing of blog comment rewrites. Th…
A new study on arXiv (2607.09743v1) finds that structured reasoning interventions have opposite effects on GPT-4.1-mini and GPT-5-mini in Hotelling spatial market tasks, with commitment scaffolding im…
ContraFix, a new automated vulnerability repair system using GPT-5-mini, achieves a 92% resolution rate on SEC-Bench and 73.8% on PatchEval across Go, Python, and JavaScript. Its contrastive runtime a…
Researchers demonstrate that moving memory retrieval inside the agent loop reduces latency from hundreds of milliseconds to ~100 microseconds, eliminating redundant actions and improving recall. In te…
A developer cut their AI agent's token cost by 62% in one weekend, reducing per-task cost from $5.40 to $2.05 without quality regression. Key optimizations included pre-filtering web page content befo…