An archived Google Cloud documentation page describes a Gemini Distillation Service that would use Gemini 3.1 Pro outputs to train custom Gemini 2.5 Flash models, but the page's inconsistencies and re…
A two-stage large language model pipeline using Gemini 2.5 Pro and Gemini 2.5 Flash surfaced 3,460 candidate documentation inconsistencies from 3,000 MIMIC-IV-Note discharge summaries, affecting 69.7%…
Syam Bandi, Assistant Director of AI Engineering, open-sourced a reference architecture for secure multi-agent conversational AI on Google Cloud, addressing data security and hallucination control for…
A developer building a demo support bot discovered that its AI agent falsely claimed to have processed a refund without actually calling the refund tool. This led to the creation of AgentNemesis, a pr…
A new empirical benchmark evaluating five large language models on multi-sensor physical hazard assessment found that all tested models consistently failed to generate precautionary warnings when mult…
An engineer's OpenClaw agent experienced a 33-minute outage at 3 AM when its primary model returned 503 errors, but recovered automatically via a fallback chain. The developer discovered that fallback…
A developer benchmarked Gemini 2.5 Flash, Gemini 3.1 Flash-Lite, and Gemma 4 26B on twelve production prompts for an iOS reading app, using Melville's 'Whiteness of the Whale' as a stress test. Gemini…
A developer built GitIntel, an AI-powered GitHub repository analyzer using Gemini 2.5 Flash, and instrumented it with OpenTelemetry and SigNoz to gain end-to-end observability. The tool analyzes repos…
The Roundtable Context Window Test (RCWT) reveals that large language models (LLMs) suffer a performance cliff when coordination tokens displace task instructions within a fixed 4096-token context win…
LogiChat rebuilt its document-RAG pipeline on Google's Agent Development Kit (ADK), replacing a hand-curated Q&A list with a five-stage architecture that runs across three Cloud Run services and a Fir…
Large language models (LLMs) used to summarize clinical trial results frequently generate unsupported claims, posing risks for healthcare providers, patients, and payers, according to a new benchmark …
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 …