Mercury 3 generates text by parallel refinement instead of token by token, and Inception says it matches or beats GPT-6 Luna and Claude Haiku 5.5 while running 4–8x faster. It's OpenAI API compatible and live on Inception's API, OpenRouter, Baseten, and Vercel AI Gateway at a 50%-off launch price of $0.10/$0.35 per million input/output tokens.
Agents can subscribe to six events at launch (new users, failed function executions, finished function and site deployments, new rows, and uploaded files) and get them over an open stream locally or as signed webhooks, so a "tell me when the deploy finishes" request no longer needs polling. It implements the proposed MCP Events extension (SEP 3415), each subscription is just an Appwrite webhook created with your OAuth token, and payloads carry IDs and metadata only (changelog)…
Projects like dumbtv and cleanyourtv let you aim a coding agent at an Android TV, Google TV, or Fire TV over Wi Fi to remove sponsored ads, disable ACR viewing tracking, and swap in a clean launcher, with no root needed and factory reset still possible. They're works in progress being tested across Sony, TCL, Xiaomi, Hisense, and others, so expect rough edges before you try it on the family TV…
Amnon Shashua's doubleAI calls Maxwell a "code execution model": instead of writing source like Claude Code, it watches a live program on CPU or GPU, emits faster binaries for the hardware and data it sees, formally proves each one equivalent, and falls back to the original code if its assumptions stop holding. The company claims 38x faster data pipelines, 4.5x faster inference kernels, and a 67% compute cost cut for one customer, none independently verified yet; it's in early access (The Next Web)…
Subject to stockholder approval, a wholly owned LLC gets 5% of Anthropic's shares now, plus another 2% at the board's discretion for every 50% rise in value above a baseline, and Anthropic says none of it will fund lobbying or political giving. Combined with founder and employee equity pledges, that's roughly 20% of the company earmarked for public good, with labor market impacts named as one target; governance details and the valuation milestones come later…
Full BYOC (private preview) puts compute, storage, and the Agent harness in your cloud, BYOC for Published Apps (early access) keeps the publish button but hosts apps in your tenant with private endpoints, and Image Exports hand you Docker, Terraform, and SBOM artifacts to self host. It's enterprise only with no pricing or GA date, and the control plane and model inference stay Replit managed, so it isn't air gapped (changelog)…
Spotted something we missed? Start a thread.