Pydantic AI V2: Capabilities, the Harness, and What Changed
Pydantic AI V2 is stable. Here is what the capabilities model, the Harness package, and V2 breaking changes mean for Python developers building ...
Meta Model API Is Live: Plug Muse Spark Into Your SDK Now
Meta's paid AI API launched July 9. Muse Spark 1.1 accepts OpenAI and Anthropic SDK ...
Ollama Raises $65M Series B: What Changes for Developers
Ollama closed a $65M Series B led by Theory Ventures. Here is what the cloud ...
Nano Banana 2 Lite and Gemini Omni Flash Are Live Now
Google launched Nano Banana 2 Lite and Gemini Omni Flash via API. Chain them to ...
OpenAI GPT-Realtime-2.1: Reasoning Comes to the Mini Voice Model
OpenAI released gpt-realtime-2.1 and gpt-realtime-2.1-mini on July 6. The mini now includes reasoning and tool ...
Google TabFM: Zero-Shot Tabular Predictions Without Training
Google's TabFM predicts tabular data without training loops — beating tuned XGBoost on benchmark. Here's what it does, what it can't do, and ...
Claude Opus 4.8: Mid-Session System Messages and API Changes
Anthropic shipped Claude Opus 4.8 on May 28 without making much noise about the parts ...
Firebase Genkit Agents API: Stateful Chat Agents
Google's Genkit Agents API ships a single chat() call that handles session history, tool loops, ...
OpenAI Jalapeño Chip: What Cheaper Inference Means for Developers
OpenAI and Broadcom unveiled Jalapeño — a custom inference chip targeting 50% cheaper LLM tokens. ...
ZML LLMD: Run LLMs on Any Chip — No NVIDIA Required
ZML released LLMD, a free chip-agnostic LLM inference server running LLaMA, Gemma, and Qwen on ...