Researchers propose Graph-Regularized Agentic Context Evolution (GRACE), a method that maintains persistent LLM agent instructions as a typed semantic graph to enable local verification of updates, im…
Google launched Stitch, a free AI UI generator that produces production-quality HTML/CSS or Tailwind from text prompts in under 60 seconds, with a March 2026 update adding MCP server support for direc…
Google Gemini users are urging the company not to discontinue the Gemini 2.5 Flash model, citing superior performance and low latency for voice agents in Australia compared to newer models.…
Researchers evaluated Gemini models as audio judges for full-duplex voice agents, finding that Gemini 2.5 Flash achieves near-human reliability on most scoring dimensions. The study shows that LALM (L…
Google accidentally deprecated its Gemini 2.5 Flash and Pro models early, causing widespread production outages for developers who rely on the models. The issue was resolved after about 30 minutes, wi…
RouterBase provides an OpenAI-compatible API that enables developers to test model fallback logic with a simple two-model chain. By using environment variables to configure primary and fallback models…
RouterBase offers an OpenAI-compatible endpoint that lets developers switch routing layers by changing only the base URL, API key, and model ID in their existing client code. A developer demonstrates …
RouterBase provides an OpenAI-compatible API gateway at https://routerbase.com/v1, enabling developers to switch between multiple AI models with minimal code changes. By simply altering the base URL a…
Between January and June 2026, OpenAI, Anthropic, and Google made 14 combined pricing changes across their LLM model lineups, with some prices dropping, others rising, and models being deprecated and …
A developer built Kajota Pulse, a Bloomberg-terminal-style dashboard for African micro-commerce co-sellers that uses Gemini 2.5 Flash to recommend what stock to buy. The app runs on the 'zero stack'—V…
A developer built Lagotto Meter, a tool that checks how well a website's structured data (llms.txt, JSON-LD) supports its claims for AI agents. It fetches declared data, passes it to Llama 3.3 70B or …
Researchers introduced DMV-Bench, the first interactive benchmark for multimodal-agent visual memory, testing agents' ability to recall visual cues from product images in a simulated e-commerce enviro…
A developer built a RAG system from scratch using pgvector and Gemini embeddings, explaining design decisions such as choosing pgvector over dedicated vector databases, using 768-dimensional embedding…
A developer created SOLS-Runner, an educational narrative puzzle game for the June Solstice Game Jam that teaches astronomy concepts through a story about a young runner's journey of growth. The game …
Fetch.ai published a developer tutorial for building an autonomous agent that generates images using Google's Gemini 2.5 Flash model and shares them across the Agentverse ecosystem. The guide walks th…
GLM 5.2, a new open-weights model, achieved 15% fewer achievements than Gemini 3 Flash in text adventure games, a statistically significant difference. The benchmark, costing $5.1, controlled for game…
A developer discovered that using Cursor Agent Mode for a simple font-pairing task consumed 1% of their token budget, leading to an investigation of usage-based pricing. The engineer found that input …
Niixo launched moneasy, a budgeting app that avoids bank login by using Apple Vision Framework and Gemini 2.5 Flash for receipt OCR and Siri for voice entry. Transactions are stored via CloudKit sync …
Researchers introduced DPBench, a benchmark evaluating coordination in multi-agent LLM systems, finding that protocol structure—not model capability—determines deadlock rates. GPT-5.2 achieved 25% dea…
Researchers from PSL compared commercial and open-source large language models on Arabic Islamic inheritance reasoning, finding commercial models significantly more reliable. Gemini 2.5 Flash achieved…