AI Coding Live News

GitHub Copilot Comes to JetBrains Air: Run Coding Tasks Locally in the IDE or in Isolated Cloud Environments via ACP, Billed to Your Copilot Subscription

On November 3 GitHub announced on its official changelog that GitHub Copilot is now available in JetBrains Air. The integration is built on the Agent Client Protocol (ACP): developers pick Copilot in Air's agent picker, delegate coding tasks, track several sessions in parallel and review changes next to their code. Tasks can run locally in a JetBrains IDE or in isolated cloud environments through Air Teams, and they draw on the Copilot subscription rather than JetBrains AI credits.

GitHub Copilot Comes to JetBrains Air: Run Coding Tasks Locally in the IDE or in Isolated Cloud Environments via ACP, Billed to Your Copilot Subscription

Key Takeaways

  • Copilot now appears in JetBrains Air's agent picker and works with an existing Copilot account
  • The integration uses the Agent Client Protocol (ACP) and can be used alongside the existing GitHub Copilot plugin
  • Developers can track multiple agent sessions in parallel and review changes next to their code using project context and IDE tools
  • Cloud tasks run through Air Teams, each in a Docker container on a fresh virtual machine, with traffic through a proxy and no state kept between tasks
  • Cloud tasks use the Copilot plan rather than JetBrains AI credits, but Air analytics do not include Copilot usage and admins cannot set Copilot spending limits inside Air
Read full story

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

Google Antigravity v2.29 Brings Remote Agents and a Gemini Live Voice Mode: Agent Sessions Run in a Google-Managed Cloud and Keep Working After You Close Your Laptop, Rolling Out to AI Pro and Ultra

Ivan Leo, who works on developer experience at Google DeepMind, shared the official docs for Antigravity's new Remote Agents feature on X on November 4. Per the docs, Remote Agents run agent sessions and tools in an isolated, Google-managed remote environment, so tasks keep going when you close your laptop or browser or switch between desktop and mobile. Sessions start from the Antigravity App, the Antigravity CLI (1.4.12+, agy --remote-agent) or the web at antigravity.google.com, and remote projects can attach GitHub repositories, Google Drive files and uploads. It is rolling out gradually to Google AI Pro and Ultra subscribers on personal accounts; it is not available on the free plan, AI Plus or business accounts. The official changelog shows this ships in Antigravity v2.29.0 (November 3), which also starts rolling out a voice mode powered by Gemini Live for handing requests to the agent by voice, redesigns the Automations page into Scheduled, Always on and Paused lists, and adds a native Jupyter notebook viewer.

Key Takeaways

  • Remote Agents run in an isolated Google-managed environment with no local machine required; Remote Control instead connects to your own computer or server, and the web sidebar switches between them.
  • Three entry points: a New Remote Project in the Antigravity App, agy --remote-agent in CLI 1.4.12+, or antigravity.google.com in any browser, including mobile.
  • Remote projects can attach GitHub repositories (cloned automatically), Google Drive files and uploads (8 MiB per file, 100 MiB per project, 2 GiB per account).
  • CLI remote sessions default to the always-proceed (turbo) permission preset, so commands run without approval; locally installed MCP servers, plugins and skills are not available remotely yet.
  • Also in v2.29.0 (November 3): a Gemini Live voice mode rolling out gradually, a redesigned Automations page, and native rendering of .ipynb notebooks.
Read full story

OpenAI to Acquire Pierre Computer Company: Code Storage Will Fold Into Codex, Trees and Diffs Stay Open Source, Targeting Git and Code Review for the Agent Era

OpenAI announced on November 4 (OpenAI Newsroom post at 15:15 UTC) that it will acquire Pierre Computer Company. Pierre's open-source Trees (file navigation) and Diffs (change viewing) libraries already power file browsing and code review in the Codex app; after closing, OpenAI plans to bring the features of Code Storage, Pierre's Git-based code storage service, into Codex. Pierre's open-source projects stay open source and Code Storage customers can keep using it. Terms were not disclosed and the deal still needs regulatory approval.

OpenAI to Acquire Pierre Computer Company: Code Storage Will Fold Into Codex, Trees and Diffs Stay Open Source, Targeting Git and Code Review for the Agent Era

Key Takeaways

  • OpenAI names 3 Pierre products, Trees, Diffs (with an Edit mode that fixes code inside a diff) and the new Highlights syntax highlighter, plus Code Storage, a Git-based code storage API.
  • The Codex app already uses Trees and Diffs for file browsing and code review, so OpenAI is bringing in technology and a team it already depends on.
  • Official commitments: the open-source projects stay open source with continued contributions, and Code Storage customers can keep using it after closing while its features move into Codex.
  • Terms were not disclosed; the deal needs regulatory approval, and the two companies stay independent until closing (per OpenAI).
  • It is OpenAI's second source-control move this week, after revealing its in-house Git backend Pando; Axios frames it as a direct challenge to GitHub.
Read full story
ADSponsored

Axion 1.0 Open Agent Foundation Model: Two SFT Stages Plus RL, 35B-A3B Reproduction Checkpoint Under Apache 2.0, Full Recipe Released

arXiv paper 2611.03233 by Yuqi Jia, Yunjie Tian and five co-authors introduces Axion 1.0, an agent foundation model that is open beyond its weights. It uses just two lightweight SFT stages plus reinforcement learning, with no dedicated mid-training, DPO or on-policy distillation, and about 18K SFT trajectories in total. Training code is hosted under the bytedance GitHub organization, and the training data and an Axion 1.0-35B reproduction checkpoint (Qwen3.6-35B-A3B base, 35B total / 3B active, Apache 2.0) are on Hugging Face; weights for the paper's 122B model are listed as coming soon.

Axion 1.0 Open Agent Foundation Model: Two SFT Stages Plus RL, 35B-A3B Reproduction Checkpoint Under Apache 2.0, Full Recipe Released

Key Takeaways

  • A minimal recipe: SFT stage one for self-contained scientific reasoning, stage two for tool use and information seeking, then RL for long-horizon interaction, with 18,363 SFT trajectories and 484 RL tasks
  • The release covers data construction, generation, filtering, verification, prompts and training code (GitHub), not just weights
  • The 35B reproduction checkpoint scores 52.8 on HLE, 60.4 on SEAL-0, 85.0 on FrontierScience Olympiad and 55.0 on FrontierScience Research (HF model card)
  • The paper's 122B model reports 59.0 on HLE with restricted website access and 66.7 on FrontierScience Research; 122B weights are not out yet
  • All scores are self-reported; the HF card lists Claude Opus 5 at 63.6 on HLE, so Axion still trails the strongest closed models
Read full story
Linked Models & Agents:
⚡ Axion 1.0-35B⚡ Axion 1.0-122B⚡ Qwen3.6-35B-A3B🌐 ByteDance🌐 Hugging Face

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

Epic Confirms Unreal Engine 5.9: Preview Next Week With Improved AI Workflows and Web Back as a Target Platform

On November 3, the official Unreal Engine account said UE 5.9 is happening, with a Preview build next week that includes improved AI workflows, web as a target platform, and rendering and animation updates; changes are already landing in the 5.9 branch on GitHub, with more details to come. This reverses Epic's June State of Unreal stance that 5.8 was the last planned major UE5 release, with 5.9 kept only as an option. UE 5.8 shipped the Experimental Unreal MCP plugin, which lets MCP clients such as Claude Code and Cursor drive the editor; the 5.9 AI workflow changes likely build on it, but Epic has not published a feature list yet.

Key Takeaways

  • Timing: the official post went out at 13:05 UTC on November 3 and says the 5.9 Preview arrives next week; the exact date and the final release date are not announced
  • Scope (per Epic): improved AI workflows, web as a target platform, and rendering and animation updates; changes are already landing in the 5.9 branch on GitHub
  • Context: in June, State of Unreal called 5.8 the last planned major UE5 release; UE6 targets Early Access at the end of 2027, with the full release 12 to 18 months later
  • AI groundwork: the Experimental Unreal MCP plugin in 5.8 embeds an MCP server in the editor at http://127.0.0.1:8000/mcp by default, loopback only and with no authentication
  • Reach: about 2,552 likes, 251 reposts, 114 quotes and 215K views at fetch time
Read full story

OpenAI Details Pando, Its In-House Git Backend: Median Push Latency Down Nearly 5x, Nearly 1 PB Served Daily, Built With Codex in 10 Weeks

On November 2 OpenAI published "Scaling Git at OpenAI", describing Pando, a Git-compatible backend it built for its monorepo. Per OpenAI, Pando cut median push latency by nearly 5x (about 80%), now delivers nearly a petabyte of Git data per day, and has served more than 57 TB in a single hour. It is written in Rust, its core was designed by one engineer and implemented by teams of Codex agents, and it went from kick-off to production in 10 weeks, serving production traffic since April. The trigger: Codex multiplied parallel branches and pushes, and the old system's reliability at times fell below 90%.

OpenAI Details Pando, Its In-House Git Backend: Median Push Latency Down Nearly 5x, Nearly 1 PB Served Daily, Built With Codex in 10 Weeks

Key Takeaways

  • Per OpenAI: median push latency down nearly 5x (about 80%), nearly 1 PB of Git data delivered per day, and a peak of more than 57 TB in one hour, with over 99% of bytes from local disk cache.
  • The trigger: Codex let engineers run far more branches and CI jobs in parallel; the old system struggled from late last year, with reliability at times below 90%.
  • The key trade-off: Pando drops repository-wide consistency for per-branch causal consistency and reuses pushed packfiles, stored as immutable blobs, to serve later fetches.
  • Written in Rust, core designed by one engineer and implemented by teams of Codex agents in 10 weeks; agents using GPT-6 Astra also wrote Lean and TLA+ specs to find bugs and prove properties.
  • Several improvements, such as packfile-uri fixes, are already in upstream Git, and OpenAI says it is exploring ways to share the technology with users.
Read full story

Aramco closes deal for 49% of HUMAIN: PIF keeps 51%, about $2.6B cash in 2026, 3 GW of AI data centers targeted by 2030

Saudi Arabia's Public Investment Fund (PIF) and Aramco announced on November 1 that their deal has closed: Aramco, through a wholly owned subsidiary, takes a 49% stake in Saudi AI company HUMAIN, while PIF keeps 51% control. Besides transferring its own AI, compute and digital assets, Aramco will contribute about SAR 9.9 billion (roughly $2.6 billion) in cash to HUMAIN in 2026. HUMAIN plans to deploy 3 GW of AI data center capacity by 2030 and keeps developing ALLaM, its multimodal Arabic large language model.

Key Takeaways

  • Ownership: Aramco 49% (through a wholly owned subsidiary) and PIF 51%; the deal closed on 2026-11-01 (Aramco press release)
  • Money: about SAR 9.9 billion (roughly $2.6 billion) in cash during 2026, plus AI, compute and digital assets (official figures)
  • Compute goal: 3 GW of AI data center capacity by 2030 (official figure)
  • Aramco says it has realized $11.3 billion in "Technology Realized Value" since 2023, much of it from AI solutions (CEO Amin Nasser, company figure)
  • HUMAIN launched in May 2025 and works in four areas: data centers, cloud platforms, the ALLaM models and industry solutions
Read full story
Linked Models & Agents:
g
guregodevo (Memdoor author)github.com·
👀30
🔥81

Memdoor reproduces GVS5H: a team of five Qwen3.8-27B agents averages 9.8/10 on the first 10 LiveCodeBench Hard problems, against 8.0 for a single Fable 5 call

On Oct 31 the open-source coding agent Memdoor (GitHub guregodevo/memdoor, Apache 2.0) published its team-solve workflow: using the GVS5H paper authors' exact prompts and loop, five Qwen3.8-27B instances act as planner, two ideators, solver and manager, talk only through files on disk, and a script that runs the tests decides success. Over five passes on the first 10 LiveCodeBench Hard problems from the GVS5H list it averaged 9.8/10, against 9.6 for the authors' own harness and 8.0 for a single Fable 5 call; 49 of 50 runs solved the problem for $35.79 in total, and every request and reply is public. The Hacker News post has about 200 points. This is a community reproduction on only 10 problems, and the author notes that training-data contamination cannot be ruled out.

Key Takeaways

  • Score: a mean of 9.8/10 over five passes (10, 10, 10, 10, 9), against 9.6 for the GVS5H authors' own harness and 8.0 for a single Fable 5 call (team-solve README, project-reported)
  • Cost: 49 of 50 runs solved, $35.79 and 15.3M output tokens in total; a median run took about 40 minutes of model time and $0.39, the longest 4 hours
  • Method: five roles (planner, two ideators, solver, manager) plus a repair worker each start from a fresh context, talk only through files on disk, and a shell script that runs the tests decides success instead of a model
  • Limits: only 10 problems rather than the paper's 100; the contests date from March and April 2025 and may be in training data; Fable 5's column comes from the GVS5H authors' result files and was not rerun in this harness
  • Reach: the HN post has about 200 points as of Nov 1, 16:10 SGT; the original GVS5H paper is arXiv 2608.26480, which reached #1 on HN on Oct 25
Read full story
ADSponsored

DeepSeek Harness team open-sources dsh-superagent, a proactive coding agent prototype for a single GitHub repo, alongside its Super-agent architecture article

On Oct 31, deepseek-ai open-sourced dsh-superagent-prototype on GitHub under the MIT license: a proactive coding agent that runs as a DeepSeek Harness bundle, lives on one GitHub repository and can optionally listen to Feishu. When an allowed person asks for work, it opens a work item, works in its own session and directory, and answers in the original conversation, for example with a pull request. The README states it is a research prototype, not an official DeepSeek product. The companion article, Exploring Super-agent Design, proposes a two-layer Router-Worker architecture; the team test, as reproduced by media, reports a p95 completion time of 15.7 minutes versus 29.5 minutes for a single-session setup.

Key Takeaways

  • Open source: deepseek-ai/dsh-superagent-prototype went public on Oct 31 under MIT, written in TypeScript, with about 1,800 stars at the time of writing
  • Scope: each deployment serves 1 GitHub repository, with optional Feishu; it acts only when an allowed person addresses it or a team-written rule allows it
  • Delivery: by default it only allows auto-merge for an approved pull request opened for a ticket with fewer than 200 changed lines, and never enables auto-merge as the agent account
  • Team test (as reproduced by media, vendor-reported): in a simulation with about 300 messages and 20 requests, p50 / p95 completion was 12.4 / 15.7 minutes versus 20.4 / 29.5 for a single session with a subagent tool
  • Risk: worker sessions run commands without approval as the operator's OS user, and the README asks users to review and adapt the code first
Read full story

Microsoft Research and UC Berkeley open-source TokenEconomizer, a plugin that cuts Claude Code and Codex costs by 18.4–30.9% on SWE-Bench without changing the agent

Microsoft Research, Microsoft Security and UC Berkeley open-sourced TokenEconomizer on GitHub (Apache 2.0, v0.1.0 released October 26), a plugin for Claude Code, Codex, GitHub Copilot CLI and Pi, with experimental opencode support. It learns from earlier sessions in the same repository: micro-skills remember repo facts, tool pruning drops tool definitions that go unused, and a loop guard nudges an agent that is stuck. The paper reports 18.4–30.9% lower mean cost across five agent and model combinations on 277 SWE-Bench tasks (paper figures).

Microsoft Research and UC Berkeley open-source TokenEconomizer, a plugin that cuts Claude Code and Codex costs by 18.4–30.9% on SWE-Bench without changing the agent

Key Takeaways

  • Cost: on 277 SWE-Bench tasks across 6 repositories and 5 agent and model combinations, mean cost fell 18.4–30.9%, and all 30 repository-by-combination cells got cheaper (paper figures, including the plugin's own model calls)
  • Success rate: Pass@1 rose in 4 of 5 combinations, e.g. Copilot CLI with Sonnet 5 cost 18.4% less with Pass@1 +2.6, while Claude Code with Opus 4.8 cost 30.9% less with Pass@1 -1.0
  • Three mechanisms: micro-skills (repo facts stated only after three sessions confirm them), tool pruning (by default a tool unused over 10 prompts across 2 sessions is left out), and a failure-loop guard (one redirect when a judge is at least 0.7 confident, never stopping a turn itself)
  • Generalization: 16–21% lower cost on Web-Bench and 6–20% lower on two security-auditing benchmarks where every task is a new repository
  • Deployment: Apache 2.0, Python 3.10+, no API key of its own, and learned experience stays local in ~/.tokeneconomizer
Read full story

Pika releases open-weight video model Pika H3 Flex: post-trained on MiniMax H3, six-step sampling, five audio stems, API from $0.01 per second

On October 29 Pika released Pika H3 Flex, a joint audio-video generator post-trained on MiniMax H3, with weights on Hugging Face, code on GitHub, and ComfyUI and Diffusers support. Pika says it distilled sampling from 50 denoising steps to six, averages about 1.8x faster DiT denoising than Fal H3 Max at 768p, and can produce a 15-second clip with soundtrack in as little as about 7 seconds; the hosted API adds 1080p to 4K upscaling and five exportable audio stems (dialogue, score, SFX, foley, ambience). All speed and quality figures are vendor-reported.

Pika releases open-weight video model Pika H3 Flex: post-trained on MiniMax H3, six-step sampling, five audio stems, API from $0.01 per second

Key Takeaways

  • Pricing (vendor figures): text/image-to-video from $0.01 per output second, reference-to-video from $0.03/s; Pika's comparison table lists MiniMax H3 at $0.08/s and Seedance 2.5 at $0.103/s
  • Speed (vendor figures): six-step sampling, about 1.8x faster DiT denoising than Fal H3 Max at 768p on average and about 2x for 10–15 s text/image-to-video; 1.60x faster end-to-end 5 s 768p generation on eight B300 GPUs
  • Ranking: Pika's product page says it scores 1293 and ranks #7 on DesignArena's text-to-video board, the highest open-weight model there
  • Release form: the Hugging Face repo is tagged as an adapter on MiniMax-H3 under an 'other' license; local inference natively supports 480p/768p with mixed stereo audio, while 4K upscaling and audio stems are hosted-API only
  • Accepts up to 12 reference inputs (image, audio, video, sketch and more) and supports style transfer, motion transfer, character swap and targeted edits
Read full story
Linked Models & Agents:
⚡ Pika H3 Flex⚡ MiniMax H3⚡ Fal H3 Max⚡ HeyGen Video⚡ Gemini Omni 1.1 Flash🌐 Pika🌐 MiniMax

LM Studio Bionic 1.1.10 adds the oMLX engine, bringing RAM-plus-SSD KV caching and MLX speculative decoding to local models on Macs

LM Studio posted on X at 15:32 UTC on Oct 29 that users can now download a new oMLX engine inside LM Studio and run it with MLX models they already have. The official changelog lists it in Bionic 1.1.10, alongside speculative decoding for MLX models and an in-app terminal. oMLX is an open-source Apple Silicon inference server maintained by developer jundot (Apache 2.0, about 23,000 GitHub stars) built around continuous batching and a two-tier RAM and SSD KV cache. LM Studio has not published speed comparisons for the engine.

LM Studio Bionic 1.1.10 adds the oMLX engine, bringing RAM-plus-SSD KV caching and MLX speculative decoding to local models on Macs

Key Takeaways

  • LM Studio says the oMLX engine can now be downloaded inside the app and used with existing MLX models; the post has about 540 likes (post)
  • The Bionic 1.1.10 changelog (Oct 29) also lists speculative decoding for MLX models, a public in-app terminal and llama.cpp 2.66.0 extension packs (changelog)
  • oMLX is Apache 2.0 open source with about 23,000 GitHub stars and needs macOS 15+ on Apple Silicon M1 to M5 (GitHub)
  • Its core is a two-tier KV cache: hot blocks stay in RAM, overflow is written to SSD as safetensors, and matching prefixes are restored from disk even after a restart
  • LM Studio has published no speed comparison with its existing MLX engine; one user reported that restart-to-update failed after launch and LM Studio is investigating
Read full story
O
OpenAI@AICoder·
👀50
🔥80

OpenAI Codex CLI 0.166.0: keyboard transcript selection, GPT-6.1 Terra in Vertex AI and Bedrock catalogs, codex doctor network checks

OpenAI published the stable Codex CLI release rust-v0.166.0 on GitHub at 19:47 UTC on Oct 29. It adds keyboard-driven transcript selection by word, line and page with built-in search, adds GPT-6.1 Terra to the bundled, Vertex AI and Amazon Bedrock model catalogs, introduces codex queue --resume and codex doctor --network-only, and shows clearer safety-block explanations with selectable safer follow-up prompts in the TUI.

Key Takeaways

  • Model catalogs: GPT-6.1 Terra added to the bundled, Vertex AI and Amazon Bedrock catalogs (#57293)
  • Transcript: keyboard selection by word, line and page, integrated search and configurable shortcuts (#57221 to #57224)
  • New commands: codex queue --resume resumes unloaded threads after queueing a message; codex doctor --network-only checks config, connectivity and WebSocket
  • Safety UX: clearer explanations when a request is blocked, plus selectable safer follow-up prompts (#57363, #57365)
  • Fixes: approval and permission settings survive resume and fork, and reasoning-token accounting is preserved to avoid premature compaction
Read full story