AI TrackerGet the app

Coding news,
for builders.

The latest coding news from every AI provider: launches, price changes and retirements, summarized with what they mean for you.

Cursor· Coding

Cursor lets cloud agents build and host live web apps

Cursor says you can now build a web app in Cursor and share it with a link. You start a cloud agent and tell it you want to build an app; Cursor then scaffolds the app, spins up a Postgres database if needed, sets up authentication behind Cursor SSO and provisions hosting. When you publish, you pick a unique domain and get a live link. If the app needs to reach your systems, such as a data warehouse, Cursor asks for the secrets it needs.Models

Design Arena ranks Ling-3.2-flash #10 on Image to Frontend Arena

Design Arena says Ant Ling's Ling-3.2-flash placed #10 on its Image to Frontend Arena with an Elo of 1238, among models from Meta, Anthropic and DeepSeek. It says the model sets a new Pareto frontier of preference against price, at $0.30 input and $0.90 output per 1M tokens, the cheapest for any model at that level of performance.Coding

Cognition releases Devin Review 2.0, which it says is up to 5× cheaper and 1.5× faster

Cognition says Devin Review 2.0, its pull-request review feature for Devin, is up to 5× cheaper and 1.5× faster than before, with new features and integrations. It adds an Autofix option, which Cognition pitches as a way to save time on review, and says the release is available in Devin Cloud and Devin Desktop. The cost and speed figures are Cognition's own.Mistral AI· Coding

Mistral adds managed agents and apps to Mistral Studio, its enterprise AI platform

Mistral expanded Mistral Studio, its platform for building and running enterprise AI, with managed agents and apps, plus new capabilities for workflows, enterprise context, agent observability and evaluations. It pitches Studio as the layer that puts Mistral Large 4 ("Le Chonk") to work in a business.RumorOpenAI· Models· 10 discussions

GPT-6.2 Astra appears in some users' Codex usage; OpenAI has not announced it

OpenAI has not announced a GPT-6.2 Astra. Several users report that their Codex usage breakdowns list a model called gpt-6.2-astra, while the model picker still shows GPT-6 Astra.OpenAI· Coding

Cat Wu, formerly a product lead on Claude Code, joins OpenAI to lead product management for Core Products

Cat Wu announced on X that they are joining OpenAI to lead product management for Core Products. They said they will work with Tibo (@thsottiaux), the PM team and others across OpenAI, and that the aim is to "build agents that have your back and your team's, and keep you in control." They did not say which products Core Products covers.OpenCode Go· Models

Tencent's Hy4 is now available in OpenCode Go

OpenCode announced on X that Tencent's Hy4 is now available in OpenCode Go, its subscription plan for open coding models. The post gives no usage limits or pricing for the model. Tencent released Hy4 on November 3.OpenAI· Models· 3 discussions

OpenAI says an upcoming cyber model's pipeline produced 948 Linux kernel privilege-escalation exploits

OpenAI describes an autonomous pipeline that finds, reproduces, exploits and patches vulnerabilities in the Linux kernel, run with an upcoming cyber model that has not been released. In a mid-October run against a stock desktop Linux distribution, OpenAI says the pipeline analyzed 2,308 candidate findings, dynamically reproduced 1,724 vulnerabilities, and produced 291 information-leak proofs of concept and 948 working local privilege-escalation (LPE) exploits, which let an unprivileged local user gain root. Human researchers reviewed the results before reporting them to maintainers, together with candidate patches.Google· Coding

Antigravity CLI: /btw side questions can use tools, `--settings` overrides, and `agy acp` built in

Shengzhe Yao, who posted on X about changes the team shipped for its own daily agy runs, lists three updates to the Antigravity CLI:Meta· Coding

Conductor, the app for running coding agents in parallel, is joining Meta

Charlie Holtz, a founder of Conductor, announced on X that Conductor is joining Meta. The team will work with Nat Friedman and Alexandr Wang at Meta Superintelligence Labs (MSL) to build what Holtz calls "the next interface", and he says users who liked Conductor will like what is coming. Terms of the deal were not given in the post.Google· Coding

Gemini CLI 0.67.0 adds a `models` command and a `--list-models` flag

Gemini CLI 0.67.0 adds a models command and a --list-models flag for discovering which models are available. It also bridges the IDE companion into container sandboxes over exec stdio.GitHub Copilot· Coding

GitHub Copilot is now available in Xcode's coding assistant

GitHub says you can now use Copilot inside Xcode's built-in coding assistant. The integration is in public preview, starting with the Xcode 27.3 beta, and all Copilot plans are supported.Models· 4 discussions

Ricursive AI releases Ripple-65B Preview, a 65B dense open-weight model for agentic coding

Ricursive AI released Ripple-65B Preview on November 4, a 65-billion-parameter dense language model it says it pretrained from scratch. The company claims it sets a new state of the art for U.S. open-weight models on agentic coding tasks, ahead of much larger models it names: Muse Spark Open-816B, Beam-501B, Inkling-975B and Nemotron 3 Ultra-550B. These are the company's own claims.Models

Cognition releases SWE-2 Flash, a faster, cheaper coding model built on Thinking Machines' Inkling-Small

Cognition introduced SWE-2 Flash, a coding model based on Thinking Machines' Inkling-Small (276B total and 12B active parameters). Cognition says it costs 5x less and runs 3x faster than SWE-2, and that on leading evals it outperforms all American open-weight models, including ones three times larger. These are Cognition's own claims.Anthropic· Coding

Claude Code's background-subagent status updates now cost about 99% less

Anthropic's ClaudeDevs account said on X on November 4 that background subagents in Claude Code now use less of the usage limit. A running subagent updates its status line every 30 seconds, and each update used to re-read the subagent's whole conversation. Now Haiku 5.5 writes the status line from short notes instead, which Anthropic says makes each update cost about 99% less. The subagent itself keeps its own model.Models

Axiom releases a 16M-line formalization of the entire Stacks Project

Axiom, the AI math company, released a formalization of the entire Stacks Project, a large reference work for algebraic geometry that Axiom calls critical infrastructure underlying modern math. Axiom says the result is 16 million lines, with optimized code quality and the project's highly interconnected structure preserved, and calls it "a mathematical city".Models

Arena: on long-horizon Agent Arena tasks, Claude Opus 5.5 works longest and Kimi K3.1 Pro shortest

Arena, the leaderboard publisher, says long-horizon tasks in its Agent Arena, which run hundreds of turns (porting a codebase to Rust, auditing an investment strategy document, writing a math textbook), widen the differences between frontier models.Coding

Cloudflare open-sources a security-audit skill for coding agents

Cloudflare's developer account released cloudflare/security-audit-skill, an open-source skill that turns a coding agent into a team of security auditors. Cloudflare says the skill seeded its own vulnerability-discovery harness.OpenAI· Coding· 3 discussions

OpenAI will acquire Pierre Computer, the code-storage startup behind Codex's file and diff views

Axios reports, citing OpenAI, that OpenAI will acquire Pierre Computer, a developer tools startup, as it moves into territory long dominated by Microsoft's GitHub. According to the report, OpenAI plans to fold Pierre's code storage technology into Codex, extending the coding tool into the infrastructure where developers store and manage code.Mistral AI· Models

Mistral shows Mistral Large 4 finding, reproducing and patching a Django CVE

Mistral posted a video on X of Mistral Large 4 ("Le Chonk") working on a recent Django CVE. In its description, 133 agents map the code, hunt for flaws, test attack scenarios and confirm the bug, and the model then writes a patch: triage, reproduction, fix. The video is sped up 90x.
Older news