AI news for builders and product teamsUpdated Nov 18, 2026, 11:00 UTC
AI news, straight from the source.
Releases, research, and ideas for developers and product teams. Updated every hour.
Across the feeds
Newest first
OpenClaw is a personal AI assistant that links messaging platforms to local AI coding agents through a centralized gateway running on the user's own devices. Ollama published installation and launch instructions, including an ollama launch openclaw command and a recommended context length of at least 64k tokens.

An experimental four-day University of Pennsylvania executive MBA class produced working startup prototypes that the instructor estimates were an order of magnitude further along than pre-AI student work over a full semester, using Claude Code and Google Antigravity to build and ChatGPT, Claude and Gemini for business tasks.

Mistral AI released Mistral Vibe 2.0, an upgrade to its terminal-native coding agent, powered by the Devstral 2 model family. It adds custom subagents, multi-choice clarifications, slash-command skills, unified agent modes, and automatic updates, and is available on Le Chat Pro and Team plans.

Ollama released a new command, ollama launch, that sets up and runs coding tools such as Claude Code, OpenCode and Codex with local or cloud models without environment variables or config files. It requires Ollama v0.15+ and recommends at least 64000 tokens of context length.

Mistral AI engineers describe investigating a memory leak in vLLM that appeared during pre-production testing of disaggregated serving with Mistral Medium 3.1 and graph compilation, causing system memory to grow 400 MB per minute and eventually reach an out-of-memory state.

Ollama has added experimental image generation support on macOS, with Windows and Linux planned. The feature runs models like Alibaba's Z-Image Turbo and Black Forest Labs' FLUX.2 Klein locally via the ollama run command.

Ollama v0.14.0 and later are now compatible with the Anthropic Messages API, allowing tools like Claude Code to run with open-source models locally or via ollama.com. The release supports tool calling, streaming, vision, and other features.

Open models can now be used with OpenAI's Codex CLI through Ollama, according to an Ollama post dated January 15, 2026. Codex can read, modify, and execute code in the working directory using models such as gpt-oss:20b, gpt-oss:120b, or other open-weight alternatives.

A first-person account describes using Claude Code, powered by Opus 4.5, to autonomously build and deploy a working website selling a 500-prompt set over about an hour and fourteen minutes. It attributes recent AI coding gains to more autonomous self-correction plus an agentic tool harness.

The essay revisits the "Jagged Frontier" concept of uneven AI ability, arguing bottlenecks can block automation while reverse salients like Google's Nano Banana Pro image model can suddenly remove them.

Mistral AI released Mistral OCR 3, a document extraction model it says achieves a 74% overall win rate over Mistral OCR 2 on forms, scanned documents, complex tables and handwriting. It is available via API and a new Document AI Playground in Mistral AI Studio, priced at $2 per 1,000 pages with a 50% Batch-API discount.

Mistral AI released Devstral 2, a 123B coding model scoring 72.2% on SWE-bench Verified, plus Devstral Small 2 (24B, 68.0%), both open-source. It also introduced Mistral Vibe CLI, an open-source terminal coding agent. Devstral 2 is free via API before moving to paid pricing.

Google has launched Gemini 3, its newest model, alongside Antigravity, an agentic coding tool in the vein of Claude Code and OpenAI Codex, and an early hands-on review finds it strong at planning, coding and research-style tasks.

Public benchmarks can't tell an organization which model fits its own work, so Ethan Mollick argues teams should evaluate models the way they hire people: build realistic tasks, run them repeatedly, and have experts grade results blind. He cites OpenAI's GDPval research as a model for that kind of assessment.

Ollama is partnering with OpenAI and ROOST to release the gpt-oss-safeguard reasoning models for safety classification, available in 20B and 120B sizes under the Apache 2.0 license.

MiniMax M2 is now available on Ollama's cloud, described as a model built for coding and agentic workflows. Ollama also published setup instructions for using it with tools including VS Code, Zed, and Droid, plus cloud API access.

Ollama published benchmark results for running various models on NVIDIA DGX Spark hardware using firmware 580.95.05 and Ollama v0.12.6, reporting prefill and decode tokens-per-second figures across models including gpt-oss, gemma3, llama3.1, deepseek-r1, and qwen3.

Ethan Mollick's late-2025 guide argues that roughly 10% of humanity now uses AI weekly, that free models suffice for most everyday tasks, and that anyone paying for serious work should choose between Claude, Gemini and ChatGPT at the $20 or $200 tiers.

Ollama announced on October 16, 2025 that GLM-4.6 and Qwen3-coder-480B are available on its cloud service with integrations for coding tools, and that Qwen3-Coder-30B has been updated for faster, more reliable tool calling in its new engine.

Ollama announced on October 14, 2025 that Alibaba's Qwen3-VL, described as the most powerful vision language model in the Qwen series, is now available on Ollama's cloud, with local availability to follow soon.