Klorn, an email classification service, suffered a cost cap bug that over-billed by up to 100x due to substring matching in its pricing table. The developer had previously fixed the table to over-esti…
In a benchmark of tool-calling AI models, Google's hosted gemini-3.6-flash and the open-weight gemma-4-12B-it tied at the top score, with the 12B model using about an eighth of the tokens. The test, A…
A self-described small research lab called Unslop.run found that 15 leading AI models, including GPT, Claude, Gemini, Llama, DeepSeek, Qwen, Kimi, GLM, and Mistral, consistently scored in the libertar…
Voicify, a Google Cloud customer, uses Gemini Flash via the Gemini Enterprise Agent Platform to power AI-enabled voice assistants for restaurants and healthcare, achieving 25% to 30% cost savings comp…
Amazon has redesigned Alexa to rely less on Anthropic's Claude models, part of a sweeping effort to lower AI costs, according to internal documents reviewed by Business Insider. The initiatives were e…
A user reports using DeepSeek for 80% of private AI work, citing high satisfaction, while criticizing enterprise Copilot for degraded quality, slow speed, and API errors, and noting that GPT-5.4 has d…
A developer who reverse-engineered Cognee, Graphiti, and Neo4j's agent-memory tools found they all rely on heavy knowledge-graph designs with ontologies, LLM extraction pipelines, and deduplication, w…
A new analysis by AI researcher and open-source harness developer finds that the common practice of using a frontier model to plan and a cheaper model to execute—dubbed the '/plan' pattern—actually in…
A developer built resolvo, an agentic pipeline that converts a GitHub issue into a tested pull request without requiring a local clone. Built with LangGraph and Google's Gemini models, the system rout…
A practical guide explains how to use AI screen monitoring by capturing screenshots every five seconds and analyzing them with computer vision to identify workflow inefficiencies, potentially recoveri…
A new phenomenon called 'tokenflation' shows AI coding agents using excessive tool calls and reasoning for trivial inputs like 'Hi', costing developers time and money. Benchmarking 14 models revealed …
Researchers at barkup-bench ran seven pre-registered studies with over 13,000 model runs to determine the most reliable way for LLM agents to edit structured data. They found that giving every node a …
A developer benchmarked 14 AI agent models and found that the true cost of a simple greeting like "Hi" is not the token price (as low as $0.005) but the waiting time, which can cost up to $5.10 per gr…
Google's Agent Development Kit (ADK) and Gemini Flash enable a new architecture for enterprise multi-agent systems that replaces static prompting with a centralized metadata registry, dynamically inje…
A developer reflects on the trade-offs of using AI code assistants, noting a 15-20% speed increase in daily workflow but expressing concerns about dependency and code quality. The developer observed t…
Researchers developed a method to combine AI control protocols by routing between them based on predicted usefulness and suspicion, achieving better safety-usefulness tradeoffs. They also addressed at…
A developer reports that AI coding costs can be slashed by 70% through task-level model routing instead of using a single frontier model for all tasks. After profiling usage, the developer found that …
A developer created a Toy Story-themed analogy for the open-source ecosystem, personifying tools like Python's cpython and Facebook's React as characters. The story explores conflicts between legacy a…
A Hacker News user asked the community which AI models power their products' daily features, revealing that many teams choose models based on cost and latency rather than rigorous evaluation. The user…
Google debuted Infinite Scaler at Google I/O 2026, a game where attendees generated 3D levels in real time using text prompts and reference images via the Gemini API. The game showcased Gemini's speed…