AI Coding Live News

Cognition Ships Devin Review 2.0: ~82% Cheaper (~5x) Since August, Median Latency ~94s; Auto-Review, Autofix, Ultra & Custom Reviewers

On November 5, Cognition launched Devin Review 2.0. Since August, per-PR review cost fell about 82%, with a typical review at about $0.25–$0.75 and median latency about 94 seconds (down from about 139). It adds automatic review rules, incremental re-reviews, configurable per-PR spend limits, and tighter Devin Autofix loops. New controls include Devin Review Ultra and Custom Reviewers (beta).

Cognition Ships Devin Review 2.0: ~82% Cheaper (~5x) Since August, Median Latency ~94s; Auto-Review, Autofix, Ultra & Custom Reviewers

Key Takeaways

  • Cost: ~82% cheaper per PR since August (~5x); typical ~$0.25–$0.75; ~$2.25 average per fixed bug across customers (vendor)
  • Quality & speed: bugs found per PR rose 1.22→1.32 on average; median latency ~94s (~1.5x faster vs ~139s)
  • Incremental reviews: default re-reviews only changed parts; ~80% of PRs cost under $1 including all pushes; configurable per-PR spend cap
  • Loop: with Devin, findings can be fixed, dismissed, or escalated; Autofix available in Devin Cloud and Desktop
  • Controls: Devin Review Ultra for higher-effort reviews; Custom Reviewers (beta) run specialized checks from your instructions
Read full story

Claude Launches Personal Finance Beta in the US: Read-Only Bank Linking via Plaid, Up to 16 Banks and 24 Months of Transactions

On November 5 Anthropic announced a US beta of Personal Finance in Claude via @claudeai. Users link bank, card, loan and investment accounts through Plaid, see balances, cash flow, subscriptions and bills on one page, and ask questions in plain language. The official help article says access is read-only, so Claude cannot move, manage or invest money. It is limited to US Pro, Max and Ultra personal plans (not Free, Team or Enterprise) and is rolling out gradually.

Claude Launches Personal Finance Beta in the US: Read-Only Bank Linking via Plaid, Up to 16 Banks and 24 Months of Transactions

Key Takeaways

  • Read-only: balances, credit limits and up to 24 months of transactions; no money movement (vendor statement)
  • Up to 16 linked banks, US banks only; sign-in via Plaid so Claude never sees bank passwords
  • Pro, Max and Ultra personal plans only, on web, Desktop, iOS and Android, rolling out gradually
  • Chats inside the Personal Finance hub are not used for training; chats using account data are kept out of memory
  • Linked accounts cannot yet be used in Cowork, scheduled tasks or Claude Code
Read full story

Gemini 3.8 TTS Adds Voice Remixing: Edit Prebuilt or Designed Voices With Natural-Language Instructions Into New Reusable Voice IDs

The official Gemini API changelog released Voice remixing on November 4. Starting from a prebuilt voice, an Extended Voice Library voice or a Voice Design persona, developers describe changes such as accent, pitch, pacing or age in natural language, and POST /v1beta/voices returns a new standalone voice_ ID usable with Gemini 3.8 Flash TTS and Flash-Lite TTS. It is also available interactively in Google AI Studio.

Key Takeaways

  • New Voice remixing feature: apply relative natural-language edits to an existing voice to create a new standalone voice
  • Uses POST /v1beta/voices (type=prompted, store=true, plus a new prompted.base_voice field) and returns a voice_ ID with a 24kHz WAV preview
  • Base voices can be any of 30 prebuilt voices, an Extended Voice Library voice, or a stored custom voice_ voice in the project
  • The resulting voice_ ID works with gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts and can itself be remixed again
  • The original voice is never modified, and deleting it does not affect voices remixed from it
Read full story
Linked Models & Agents:
⚡ Gemini 3.8 Flash TTS⚡ Gemini 3.8 Flash-Lite TTS🌐 Google🌐 Google DeepMind

GitHub Copilot Comes to Xcode's Built-In Coding Assistant in Public Preview With Xcode 27.3 Beta, Supported on All Copilot Plans

GitHub's official changelog says Copilot now works directly in Xcode's built-in coding assistant, in public preview starting with Xcode 27.3 beta. It needs macOS Tahoe 26.6 or later, is set up under Xcode > Settings > Intelligence, and supports all Copilot plans; the existing Copilot for Xcode extension stays available.

Key Takeaways

  • Copilot joins Xcode's native coding assistant in public preview, starting with Xcode 27.3 beta
  • Requires macOS Tahoe 26.6 or later
  • Set it up under Xcode > Settings > Intelligence; all Copilot plans are supported
  • The existing GitHub Copilot for Xcode extension remains a separate option
  • Apple's Xcode 27.3 beta 1 release notes list it under Coding Intelligence
Read full story
ADSponsored

Apple Opens Siri AI to All Developers: iOS 27.3 Betas Add a Developer Preview for App Intents and Multi-Step Skills

On November 3, Apple announced on its Developer site that a new Developer Preview in the iOS 27.3, iPadOS 27.3, macOS 27.3 and visionOS 27.3 betas lets any app bring its content and actions into Siri AI through App Intents, tapping personal context, onscreen awareness and natural language. Apple also introduced skills, which teach Siri AI to combine several actions into one experience, and Siri AI can now surface any entity in the Spotlight semantic index. It is a preview only: customer rollout is a few months away and App Store submissions open in spring. Siri AI remains unavailable in the EU on iOS, iPadOS and watchOS.

Apple Opens Siri AI to All Developers: iOS 27.3 Betas Add a Developer Preview for App Intents and Multi-Step Skills

Key Takeaways

  • Covers four platform betas: iOS 27.3, iPadOS 27.3, macOS 27.3 and visionOS 27.3 (Apple Developer news)
  • Any app can join Siri AI via App Intents; new skills combine several actions into one request, and Siri AI can surface any Spotlight semantic-index entity, not just ones that fit an existing schema
  • Apple has already rolled the capabilities into 15 of its own apps, including Calendar, Files, Finder, Mail, Maps, Messages, Notes, Photos, Safari, Shortcuts and Weather
  • Timeline: customers get it "in a few months," App Store submissions open in spring, and Apple Intelligence Group Labs run November 4-5
  • Limits: Siri AI is unavailable in the EU on iOS, iPadOS and watchOS and for users under 13; server-model features have daily usage limits, with paid expanded access promised later
Read full story
Linked Models & Agents:

Vercel Security Review Enters Public Beta: Vulnerability Review on Every GitHub Push, One-Click Fixes with Vercel Agent

On November 3 (US Pacific time), Vercel launched Security Review in public beta. It is a new Vercel Agent capability alongside Code Review and Investigation: once enabled, every push to connected GitHub repositories triggers a diff-only vulnerability review that finishes in seconds. Findings land in the Security dashboard, PR comments and the CLI, and can be fixed with one click by Vercel Agent or pulled into your own coding agent via vercel security vulnerabilities. It is available to Pro and Enterprise teams, and reviews are free until November 10.

Vercel Security Review Enters Public Beta: Vulnerability Review on Every GitHub Push, One-Click Fixes with Vercel Agent

Key Takeaways

  • Trigger: every GitHub push (including direct pushes to production) is reviewed automatically; only the diff is scanned, which Vercel says finishes in seconds, so it can run on every preview and production deployment
  • Beyond pattern matching: the agent traces how changed code is reached, checks existing protections and rechecks each finding, which Vercel says catches logic flaws such as missing authorization checks
  • Teams can write security policies in plain language, scoped to projects or the whole team, and manage them with vercel security policy
  • Pricing: Vercel Agent rate, model tokens at provider cost with no markup, plus $0.25 per million tokens; reviews are free until November 10, 2026, while Agent fixes are billed
  • Availability: public beta for Pro and Enterprise teams; Vercel has not published detection-rate or false-positive benchmarks
Read full story

Anthropic Launches Message Threads in Public Beta on the Messages API: Server-Side Conversations Cut Claude Code TTFT About 35% on 500K-1M Token Requests

On November 2 (US time) Anthropic put message threads into public beta on the Messages API (beta header message-threads-2026-08-12). The API keeps the conversation on the server: the first request sends the full conversation and creates a thread, and each later request sends only new messages plus the previous response id. Anthropic says threads are on by default for most Claude Code users, cutting median time to first token by about 35% on 500K-1M token requests, while the median long-conversation request shrank from about 800 KB to 1.8 KB. Threads expire after 5 idle minutes; pricing and rate limits are unchanged.

Anthropic Launches Message Threads in Public Beta on the Messages API: Server-Side Conversations Cut Claude Code TTFT About 35% on 500K-1M Token Requests

Key Takeaways

  • Per Anthropic, median time to first token on 500K-1M token Claude Code requests is about 35% lower.
  • The median long-conversation request fell from about 800 KB to about 1.8 KB, since each turn uploads only new messages plus previous_message_id.
  • A thread expires 5 minutes after its last request and is deleted within 1 hour; an expired thread returns 404 thread_not_found and must be replayed in full.
  • Pricing and rate limits are unchanged; Message Batches, token counting and on-demand compaction are unsupported, and threads are not ZDR or HIPAA eligible.
  • Available on the Claude API, Claude Platform on AWS, Google Cloud (Anthropic managed) and Microsoft Foundry, with a thread helper in the SDKs.
Read full story
Linked Models & Agents:

Google DeepMind expands Gemini-built PlanAssist to 15 English councils after pilots cut planning assessment time by up to 58%

On October 31, Google DeepMind said PlanAssist, a Gemini-built planning tool developed with the UK government, Google Cloud and Faculty, will be made available to 12 more local planning authorities in England, bringing the total to 15 for a 12-month Beta on live applications. In early pilots at Barnet, Camden and Dorset, DeepMind says the average officer time on householder assessment tasks fell by 58%, and more than 70% of the drafted reports were approved with no edits. Planning officers keep the final decision.

Google DeepMind expands Gemini-built PlanAssist to 15 English councils after pilots cut planning assessment time by up to 58%

Key Takeaways

  • Scale: from 3 pilot councils to 15; the 12 new ones join in three cohorts for a 12-month Beta (DeepMind blog)
  • Efficiency: average officer time on householder assessment tasks fell 58% in pilots (vendor-reported; DeepMind's X post says "up to 58%")
  • Quality: more than 70% of AI-drafted reports were approved by officers with no edits (vendor-reported)
  • The UK government says, together with new rules, routine householder processing can halve from eight weeks to four, and it aims to offer the tool to every council in England in 2027 (GOV.UK)
Read full story

Nous Research opens the official Hermes Agent mobile beta: iOS via TestFlight, Android via Firebase, connecting your phone to your own gateway to approve tools and manage bots and routines

During NousCon 2026 in New York on Oct 30, Nous Research released an official mobile beta of Hermes Agent and put up a sign-up page at hermes-agent.nousresearch.com/mobile: iOS users join the "Hermes Agent - Mobile" beta through TestFlight, and Android users join through Firebase App Distribution. The TestFlight page says the app connects to your own Hermes gateway so you can chat with streaming, approve tool calls, and manage bots and routines from anywhere. Teknium, co-founder and lead engineer of Hermes Agent, confirmed on X that the iPhone and Android betas launched together. Nous has not announced a general release date or any benchmarks.

Key Takeaways

  • Entry point: the official page hermes-agent.nousresearch.com/mobile covers 2 platforms, iOS through TestFlight and Android through Firebase App Distribution
  • Positioning: the TestFlight description says the app connects to your own gateway for streaming chat, tool-call approval, and managing bots and routines; it is a client, not a separate agent running on the phone
  • Confirmation: Teknium, co-founder and lead engineer of Hermes Agent, confirmed in a reply on X that the iPhone and Android betas both launched on NousCon day
  • Watch for clones: several third-party Hermes phone clients already exist, so only use the links on the official page; Nous has not published a general release date or benchmarks
Read full story

Apple Intelligence is coming to China: iOS 27.3 developer beta starts Nov 4, public release in December, with Alibaba Qwen inside Siri, Writing Tools and Visual Intelligence

In a press release on its China newsroom, Apple said the first Apple Intelligence features will open for testing in the latest iOS developer beta starting November 4 and reach users in China with the iOS 27.3 release in December. The features run on Apple-built generative models and include Live Translation, Writing Tools, Visual Intelligence, Clean Up, Genmoji, notification and Mail summaries, and Type to Siri; Apple also partnered with Alibaba to bring Qwen into Siri, Writing Tools and Visual Intelligence. The first wave covers iPhone 15 Pro and newer only; Siri AI and the other next-generation features announced at WWDC 2026, plus Image Playground, are not included, and Mac, iPad and other platforms wait on further approvals.

Apple Intelligence is coming to China: iOS 27.3 developer beta starts Nov 4, public release in December, with Alibaba Qwen inside Siri, Writing Tools and Visual Intelligence

Key Takeaways

  • Timeline (Apple): testing in the latest iOS developer beta from November 4, public rollout with iOS 27.3 in December, no exact date given
  • First-wave features include Live Translation (Messages, FaceTime, Phone and AirPods), Writing Tools, Visual Intelligence, Clean Up, Genmoji, natural-language photo search, Priority Mail, notification summaries and Type to Siri
  • Alibaba Qwen is built into Siri, Writing Tools and Visual Intelligence: users can ask about photos, PDFs and presentations and use Qwen to compose original text, signing in with a Qwen account or Sign in with Apple
  • Supported devices: iPhone 16 and later, iPhone Duo, iPhone 15 Pro/Pro Max and iPhone Air, with Siri and device language set to English and Simplified Chinese
  • Siri AI and other next-generation WWDC 2026 features are excluded, MacRumors says Image Playground is also missing, and other platforms follow after the necessary approvals
Read full story
Linked Models & Agents:
⚡ Qwen⚡ Apple Foundation Models🤖 Siri🌐 Apple🌐 Alibaba
ADSponsored

Claude API launches the Usage and Cost Analytics API in beta and raises the request size limit to 128 MB

Per the official Claude API release notes, on Oct 29 Anthropic launched the Usage and Cost Analytics API in beta, with two endpoints, /v1/organizations/analytics/usage and /analytics/cost, that filter and group token usage and cost by model, workspace, API key, and the user or service account behind each request, with 1-minute, 1-hour, or 1-day buckets. The older Usage and Cost API is now legacy but still supported. On Oct 28 the maximum request size for the Messages and Token Counting APIs on the first-party Claude API rose from 32 MB to 128 MB.

Key Takeaways

  • The new API needs the analytics-usage-cost-2026-08-24 beta header; one endpoint returns token and request counts, the other cost in USD (per the official docs)
  • group_by takes up to 5 dimensions, time buckets can be 1m, 1h, or 1d, and each filter accepts up to 100 values
  • Claude Console and Claude Enterprise organizations share the same endpoints and fields; it also works on Claude Platform on AWS and Claude Models on Google Cloud (Anthropic managed)
  • The old Usage and Cost API and four Enterprise Analytics usage and cost report endpoints are now legacy but still supported, with migration guides
  • Since Oct 28 the Messages and Token Counting APIs accept requests up to 128 MB instead of 32 MB (4x), on the first-party Claude API only
Read full story

Amp launches macOS Satellites beta: agents boot a cloud Mac with Xcode in ~30 seconds to build, test and run iOS and Mac apps, from $2/hour

On Oct 29 Amp shipped macOS Satellites: threads keep running on a Linux orb, and when work needs macOS Amp boots a fresh cloud Mac with Xcode and simulators, uses it only to build, run and test, and returns screenshots, logs and screen recordings to the thread. mac.medium costs $2/hour and mac.large $4/hour; the beta is waitlisted. CEO Quinn Slack says agents need a Mac only about 35% of the time even for macOS-heavy work.

Amp launches macOS Satellites beta: agents boot a cloud Mac with Xcode in ~30 seconds to build, test and run iOS and Mac apps, from $2/hour

Key Takeaways

  • Amp says the cloud Mac is ready in about 30 seconds with Xcode, iOS simulators and Homebrew preinstalled
  • Two sizes: mac.medium (6 CPUs, 14 GB) at $2/hour and mac.large (12 CPUs, 28 GB) at $4/hour, drawn first from plan orb usage, then Amp credits
  • A Mac stays up 20 minutes after use so follow-ups reuse its build cache, then it is deleted and nothing is saved
  • CEO Quinn Slack posted on X that even macOS-heavy agent work needs a Mac only ~35% of the time (company figure)
  • Beta only: join the waitlist under Settings > Experimental Features
Read full story
Linked Models & Agents:

Vercel CI enters beta: runs only the Turborepo tasks a change affects, 2-6x faster CI built for coding agents

On Oct 28 Vercel launched Vercel CI in beta on all plans. It reads turbo.json, runs only the tasks affected by a code change, serves unchanged tasks from Remote Cache, and gives each task its own machine on Hive, Vercel's compute layer. Vercel says time from git push to "CI passed" in its own repos is 2-6x faster and that nearly 8 million tasks have run across its repos and the private beta; agents can watch and debug CI through the Vercel CLI and MCP.

Vercel CI enters beta: runs only the Turborepo tasks a change affects, 2-6x faster CI built for coding agents

Key Takeaways

  • Speed: push-to-"CI passed" time in Vercel's own repos is 2-6x faster (vendor figure)
  • Scale: nearly 8 million tasks completed across Vercel's repos and the private beta
  • Setup: add "tags": ["ci"] to a task in turbo.json, with no workflow YAML, and Remote Cache is on by default
  • Agent-ready: vc ci ls, inspect, logs and grep plus Vercel MCP let agents inspect runs, logs and flaky tests
  • Compatible: posts a check to GitHub pull requests so existing branch protection still works; beta on all plans
Read full story

ChatGPT dots add texting: US Pro users can message their dot over iMessage or RCS, and the dot texts back with proactive updates

On Oct 28 OpenAI announced through @ChatGPT that users can now text their dot, the always-on agent inside ChatGPT. You can hand it a task or something to watch using text, photos or voice notes, and it texts you proactively when there is a relevant update. Texting runs over iMessage or RCS, not plain SMS; only you can text your dot and it can only text you. It is rolling out in beta to a limited number of US Pro users and is not supported in Business or Enterprise workspaces. Texts pass through the third-party provider Linq, and OpenAI says the conversation is not end-to-end encrypted.

ChatGPT dots add texting: US Pro users can message their dot over iMessage or RCS, and the dot texts back with proactive updates

Key Takeaways

  • Scope: a limited beta for US Pro users; not supported in Business or Enterprise workspaces (OpenAI Help Center)
  • Channels: iMessage on iPhone and RCS on Android only; a plain SMS gets an automatic reply asking you to use iMessage, RCS or the app
  • Setup in 3 steps: open the dot's profile and choose Texting, enter your number to get a confirmation text, then enter the code
  • Privacy: texts route through third-party provider Linq, so they are not end-to-end encrypted; Linq keeps no message content after delivery, only metadata such as timestamps and delivery status
  • Context: texting shares the same memory and plugins as the dot in the app; reply STOP or turn it off under Texting to stop
Read full story

Apple Creator Studio adds AI assistants built on Apple models and OpenAI to Logic Pro, Keynote, Pages and Numbers, plus MCP support so external agents can edit iWork documents

On October 27 Apple announced a major Apple Creator Studio update: Logic Pro for Mac plus Keynote, Pages and Numbers gain beta intelligent assistants that Apple says are powered by a combination of Apple-built models and OpenAI and understand document context. Keynote, Pages and Numbers also add Model Context Protocol (MCP) support, letting external AI agents read content, make edits and run automated actions inside the apps. Pixelmator Pro adds natural-language Generate Fill, and Keynote introduces the open JSON-based .keyx format. The update ships free to existing subscribers on the App Store in November; pricing stays $12.99 per month or $129 per year.

Apple Creator Studio adds AI assistants built on Apple models and OpenAI to Logic Pro, Keynote, Pages and Numbers, plus MCP support so external agents can edit iWork documents

Key Takeaways

  • Logic Pro for Mac, Keynote, Pages and Numbers gain beta assistants that Apple says run on a combination of Apple-built models and OpenAI
  • Keynote, Pages and Numbers support MCP so external AI agents can read content, edit and automate actions (requires macOS 27 or later)
  • Keynote adds the open JSON-based Keynote Interchange Format (.keyx), designed to be readable by external tools and AI agents
  • Assistants are U.S. English only and need an Apple Intelligence-capable device on iOS, iPadOS or macOS 27; free update for subscribers in November
  • Pricing unchanged at $12.99 per month or $129 per year, $2.99 per month for education
Read full story