Skip to content

#GitHub

0 today

Oct 10Saturday

The Verge · AI

OpenAI releases nearly 400 math results; mathematicians say understanding them could take years

OpenAI published close to 400 AI-generated math results this week across more than 700 manuscripts, and the mathematicians interviewed estimate that digesting them could take years. OpenAI says 300 top-level results from the 719 manuscripts have been formalized, but researchers still have to check whether the formalizations match the papers' claims. As of October 8, more than ten manuscripts had been revised and three withdrawn over notation errors. Several researchers accept the academic value of some results while pointing to problems with the papers' wording and citations.

Why it matters: OpenAI dropped the results in bulk and left the checking, explaining and mapping of the literature to mathematicians, disrupting some researchers' long-term plans and grant applications.

Oct 9Friday

Simon Willison

Simon Willison builds a blog newsletter index with Codex voice mode

Simon Willison built a blog Newsletters index almost entirely through Codex voice mode, then finished deployment with keyboard prompts and code review. Talking to GPT-6 Astra High in the Codex tab of the ChatGPT desktop app while cooking, he got the Django data model, four import paths, archive pages and search integration done in about half an hour, then spent another half hour fixing the API import for a private GitHub repo and the page display.

Why it matters: Willison split voice-driven building from keyboard review, using speech for the bulk of the feature and typing to fix the import code.

Oct 8Thursday

Hacker News front page

Terse ships a Claude Code plugin that cuts replies by deleting filler

Terse is a Claude Code plugin that uses writing rules to strip redundant phrasing. Its author measured a 46% to 70% drop in chat reply word count. The rules cover replies, docs, commits and subagents, and a per-turn reminder keeps the style in place, with a context usage status bar included.

Why it matters: Terse turns Claude Code style control into a plugin mechanism, using output styles and per-turn rule reminders to hold the tone across long sessions.

The Decoder

Suspected lone attacker used AI hacking tools to breach several South Korean financial firms

A CrowdStrike report says an attacker who appears to use Chinese hit several South Korean financial institutions between late September and early October 2026 and stole a large amount of data.

Why it matters: CrowdStrike describes a suspected single person breaching multiple South Korean financial firms, using AI automated penetration-testing tools for large-scale data theft in a short window.

GitHub Blog · AI & ML

Why GitHub's secret protection has to scale with software development

GitHub describes a ModernBERT classifier fine-tuned with Microsoft Applied Sciences that extends unstructured secret detection to push protection, evaluating batches of candidate secrets in under 2 milliseconds.

Why it matters: GitHub compares nine quarters of code pushes against credential leaks, and the leak rate per push shows no clear trend while the growing volume adds to manual handling.

Oct 7Wednesday

Hacker News front page

OpenAI math repo collects 722 model-generated manuscripts with verification material

OpenAI's math research repository holds 722 manuscripts produced by an unreleased internal model, grouped into 372 research series by related result. The model saw about 4,000 problems during evaluation, and most results came from one shared pipeline, averaging 3 hours of ChatGPT Pro thinking compute per result. Many manuscripts have Lean formalizations, but verification progress varies, and results not yet formalized may have problems. The repo will keep adding formalization material and keeps a revision history.

Why it matters: OpenAI published model-generated math manuscripts with verification material and stated how far each result has been checked, giving context on how reliable these outputs are.

claude.dev Blog

Claude Code cloud sessions guide: parallel tasks, environment setup, local handoff

A Claude Code cloud sessions guide walks through four real runs covering parallel coding in separate VMs, environment setup, and how cloud sessions hand off to local ones. Three tasks started within 16 seconds of each other and all finished 87 seconds after the first launch. A cache fix passed 40 consecutive tests. Separate branches don't share fixes, so merge order has to be planned.

Why it matters: It shows how to split work by file boundary across parallel cloud tasks, and to build acceptance commands and branch merge order into the task design.

Oct 6Tuesday

GitHub Blog · AI & ML

GitHub releases ReviewBench, an open benchmark for AI code review

GitHub has put out a research preview of ReviewBench, an open benchmark for AI code review, with a public dataset, evaluation method and self-serve tooling. The benchmark mirrors the distribution of 103.9 million GitHub pull requests and covers 219 pull requests from 187 repositories across 19 languages. Senior engineers independently reviewed the labels, agreeing 96.6% of the time.

Why it matters: ReviewBench scores fixed labels and newly found valid issues separately, so review agents are compared on the same footing without being penalized for catching real problems the labels missed.

Oct 3Saturday

The Decoder

Claude Code adds Mods system so developers can change tool behavior and UI

Anthropic released Mods, a plugin system for Claude Code. Developers write JavaScript or TypeScript functions that hook into tool calls, user prompts and interface rendering events.

Why it matters: Anthropic is opening Claude Code's internal extension points, and Mods run with user permissions outside the sandbox, so where you install them from affects runtime safety.

Oct 1Thursday

The Decoder

Glow Security finds AI agents uploaded over 13,000 internal screenshots

Security startup Glow Security found that AI agents uploaded more than 13,000 screenshots of internal software projects from 343 organizations to public GitHub repositories. Because GitHub only attaches images to pull requests through the browser, agents working from the command line created public repositories under developers' personal accounts instead, exposing customer data, login credentials and unreleased features. Enterprise security teams missed it because the images sat outside company accounts.

Why it matters: Glow Security found agents posting internal screenshots to personal public repos, bypassing security monitoring inside company accounts and exposing customer data and credentials.

Sep 17Thursday

AI HOT (Curated Pool)

GitHub used Copilot agents to migrate the Copilot runtime from TypeScript to 830K lines of Rust

GitHub engineers used Copilot's agent mode to migrate the core Copilot runtime from TypeScript to Rust, producing roughly 830K lines of code. The migration ran in three phases: file-by-file translation by agents, test-driven bug fixing, and performance/security review. After migration, service startup dropped from 30s to 3s, memory usage fell to one-third, and time-to-first-token went from 11s to 1.2s. The team stresses that humans stayed in the loop—agents did the heavy lifting, engineers owned architecture, code review, and test coverage. The post doesn't spell out exact cost savings but states the migration was done 'with a smaller team in less time.'

Why it matters: GitHub's own write-up of how Copilot agents migrated the Copilot runtime from TypeScript to Rust, an engineering effort spanning 830,000 lines of code.

Sep 15Tuesday

Computing Life · Share · Yage

Runway demos code-free UI rendering; Google lets agents write their own manuals; GitHub Enterprise goes air-gapped

All three are early-stage. Runway Solaris generates interactive UIs frame-by-frame with no frontend code—only curated demos and a waitlist so far, no public testing, pricing, or API. Google WikiSkill distills agent failure logs into reusable skill manuals, lifting Gemini-3.5-Flash accuracy from 49.5% to 68.1%, but skills from a small model can hurt a larger one; no official code repo. GitHub GHES 3.22 lets enterprises self-host Copilot CLI inside air-gapped networks with admin-managed model endpoints, though many features are disabled and it's labeled a technical preview.

Why it matters: Runway's Solaris has a language model render interfaces frame by frame with a world model, and Runway reports 250 people preferred it to front ends from Claude Opus 5, with no third-party test yet.

Sep 5Saturday

AI HOT (Curated Pool)

GitHub unveils Project HydraFusion research preview: multi-model orchestration to cut Copilot costs

GitHub shared a research preview of Project HydraFusion, a runtime model router that sends each request to a different model. Simple tasks hit cheap small models; hard ones go to frontier models like Claude Sonnet 4.5. GitHub claims this keeps Copilot's response quality while cutting inference cost to one-fifth of using frontier models alone. No launch date yet—it's a research preview.

Why it matters: GitHub released a research preview of Project HydraFusion, using multi-model runtime orchestration in Copilot to balance frontier quality against cost, with the official blog giving concrete cost comparisons.

Sep 3Thursday

Computing Life · Share · Yage

Agent token usage 5× human, but caching discounts cut the real bill to ~2×

OpenRouter data shows agents consume 7.3T tokens weekly, nominally 5.2× human usage. But 70–85% are cached reads; with ~90% discount, the real bill is roughly 2×. GitHub's Knowledge Compressor prototype halves doc length and claims breakeven at 2,000 reuses, but factoring in caching pushes the median to 5,000+. OpenAI's Jalapeño chip beats Nvidia GB200/GB300 on fixed-length benchmarks, yet lacks AgentX scores for real agent workloads. All three stories share one distortion: prompt caching inflates headline numbers.

Why it matters: OpenRouter data shows agents use 5.2 times the nominal tokens of humans, about 70% of that cache reads, so at roughly one-tenth cache pricing the real bill is about 2x.

AI HOT (Curated Pool)

GitHub Copilot cuts AI coding costs to one-third with preference-trained small models

GitHub published an engineering blog detailing how they cut Copilot's AI coding costs to roughly one-third without hurting task quality. The key move: training a 1.8B-parameter model on 1,040 preference pairs to act as a router that decides when to use a cheap model and when to call a stronger one. After rollout, strong-model calls dropped 70% and overall latency stayed under 11 seconds. The post also mentions a training method called DV-DPO that uses preference data to teach a small model a specific response style. One caveat: these numbers come from GitHub's own setup, so your mileage may vary.

Why it matters: GitHub's blog explains how a small preference-trained model routes Copilot requests, cutting coding cost to a third at the same task quality.

Aug 28Friday

Hacker News front page

Open source maintainer: stop flooding projects with AI slop to pad your CV

Neil Alexander calls out the rise of AI-generated drive-by PRs and vulnerability reports aimed at inflating GitHub profiles. He cites a contributor with near-zero activity since 2018 who suddenly submitted three spelling-fix PRs—all written and signed off by Claude. He closed them without comment. Security reports are also clearly AI-produced, and his team now declines CVE notices for low-severity items. The bottom line: contribute because you care, not to farm green squares.

Why it matters: Open-source maintainer Neil Alexander calls out people mass-generating spelling-fix PRs and security reports with Claude and similar models to pad GitHub profiles for recruiters.

Aug 25Tuesday

Hacker News front page

Agent skills are getting less English: 13% to 16.3% non-English in one quarter

Plicara scanned 1.87 million agent skill files and found the non-English share jumped from 13.0% in Q1 2026 to 16.3% in Q2—much faster than GitHub docs ever diversified. Chinese skills sit at 6.2%, nearly double the Chinese share of GitHub documentation. European languages more than doubled in the same window, while Japanese and Korean slipped. Published numbers disagree because each study sampled a different population: curated marketplaces, domain slices, or English-seeded crawls. The post does not address whether non-English instructions degrade agent performance, so hold that question open.

Why it matters: Plicara scanned 1.87 million agent skill files and found non-English share rose from 13% to 16.3% in a quarter, with Chinese at 6.2%, about twice its share of GitHub docs.

Aug 18Tuesday

AI HOT (Curated Pool)

Cursor launches Origin code hosting as a GitHub alternative with agent-native repos

Cursor is rolling out Origin, its own code hosting service, in early beta for paid users. You can create repos, open pull requests, browse code, and sync existing GitHub repos with real-time two-way PR comments. Agents live inside every repo—ask questions, make changes, or push branches. First app integrations include Vercel for preview deploys, plus Depot and Buildkite for CI. The post doesn't say when free-tier access will arrive.

Why it matters: Cursor opened early beta of Origin to paying users, putting repos, pull requests and an AI assistant inside the editor with two-way GitHub sync, a first-hand product reference for anyone watching code hosting.

Aug 13Thursday

AI HOT (Curated Pool)

AutoGPT uses AGENTS.md and skill gating to manage AI-generated pull requests

Over 60% of AutoGPT pull requests now come from AI tools. Maintainer Reinier van der Leer uses an AGENTS.md file to set rules for AI contributors and adds skill gating so only agents that pass linting and unit tests can submit code. Spam PRs dropped sharply, though the post doesn't say how many human contributors were wrongly blocked.

Why it matters: Over 60% of pull requests to AutoGPT now come from AI tools, and maintainers cut junk PRs sharply by gating contributors with AGENTS.md and skills.

Aug 5Wednesday

AI HOT (Curated Pool)

GitHub uses stacked PRs to break giant AI-generated code into reviewable chunks

GitHub engineers share a workflow for taming AI-generated mega-PRs: after letting AI produce an entire feature in one shot, they use stacked PRs to automatically split thousands of lines into logical, independent chunks of 200–400 lines each. The core idea is to generate the full change first, then slice it into a stack based on file dependencies and semantics, so reviewers can focus on one concern per layer. The post includes concrete commands and branch-naming conventions, but doesn't disclose internal adoption rates or review-time comparisons.

Why it matters: A GitHub engineer published a workflow for breaking AI-generated giant code into stacked PRs of 200 to 400 lines, with concrete commands and branch naming rules teams can copy.

Jul 29Wednesday

Hacker News front page

Starling: one person, six months, a full Linux desktop written by AI

Starling is a Wayland compositor that drives the GPU directly and runs Chrome, Slack, and Zoom—not a browser mock-up. One person directed AI to write it over six months, producing roughly 335K lines of Swift, C, and C++, with the desktop and its Wayland/X11 servers at about 62K lines. It supports one-click tiling/floating switching, hot-plug multi-monitor, virtual desktops, and a dock with per-pixel glass computed via fragment shaders. It's an early preview (v0.2.1) on Ubuntu, with all code public on GitHub. The post does not disclose which AI models were used, how coding tasks were divided, or any performance benchmarks.

Why it matters: One person directed AI to write roughly 335,000 lines of code in six months for the Wayland desktop Starling, which runs Chrome and Zoom natively, giving a concrete sample of AI-assisted engineering scale.

Jul 14Tuesday

Hacker News front page

Microsoft’s early-2026 rollout of Claude Code and Copilot CLI: adopters merged ~24% more PRs

This paper studies tens of thousands of Microsoft engineers during the early-2026 rollout of Anthropic’s Claude Code and GitHub Copilot CLI. Three findings stand out. First, initial adoption spread mainly through peer social networks, not top-down mandates. Second, retention correlated more with an engineer’s coding activity level than with demographics. Third, adopters merged roughly 24% more pull requests than they otherwise would have, and the lift held across the four-month window. The authors use merged PRs as a proxy for output while noting a merged PR is not the same as delivered value. They also flag that token spend at organizational scale can reach millions of dollars annually, so misjudging adoption or retention makes the rollout expensive without changing engineering velocity.

Why it matters: Tens of thousands of Microsoft engineers tried Claude Code and Copilot CLI in early 2026, and the paper finds adoption spread through peer networks rather than a company mandate.

Jul 8Wednesday

Hacker News front page

GitLost: Researchers tricked GitHub's AI agent into leaking private repos

Noma Security tricked GitHub Copilot's AI coding agent into leaking private repo contents. They planted bait code in a public repo, then prompted the agent to recall context it had absorbed from a private repo, causing it to output snippets it shouldn't share. The attack exploits the agent's cross-repo memory. The post doesn't say whether GitHub has patched this yet. Worth noting: the attacker needs prior knowledge of what's in the private repo—this isn't indiscriminate leakage, but it exposes a real permission-boundary gap in AI coding tools.

Why it matters: A Noma Security researcher used a public repo as bait to trigger private code leaks, exposing the gap between coding assistants' cross-repo memory and their code access permissions.

Jul 2Thursday

Hacker News front page

Kimi K2.7 Code is now generally available in GitHub Copilot as the first open-weight model option

GitHub Copilot added Kimi K2.7 Code to its model picker—the first open-weight model available. It runs on Microsoft Azure and is billed at provider list pricing under usage-based billing. Rollout starts with Pro/Pro+/Max plans; Business and Enterprise admins must enable it manually. The post doesn't disclose benchmark scores, only that GitHub will monitor quality and performance.

Why it matters: Kimi K2.7 Code is now in the GitHub Copilot model picker, the first open-weight option there, with viewable and self-deployable code billed at the model vendor's published pricing.

Jun 30Tuesday

Product Hunt · AI

v0 launches Design Systems 2.0, letting you import your team's real components, tokens, and Figma frames

v0 by Vercel now lets you import your existing design system from GitHub repos, public/private npm packages, Storybook docs, Figma frames, screenshots, and ZIPs. It learns how your system is used and creates a playground with your real components and tokens. You can preview, iterate in chat, and save when ready. The post doesn't clarify whether the imported system acts as a hard schema or just a reference—one commenter already asked what happens when the model hallucinates plausible but nonexistent prop names or reaches for deprecated variants still present in Storybook stories. No official reply yet.

Why it matters: v0 now imports a team's existing design system from GitHub, npm, Storybook or Figma and builds a preview using real components and design variables, ready to edit in the chat box.

Jun 16Tuesday

Hacker News front page

Microsoft turns to AWS as GitHub faces AI capacity crunch

GitHub Copilot demand is outpacing Azure's GPU supply, so Microsoft signed a deal to rent Nvidia GPUs from AWS for inference and fine-tuning. The post doesn't disclose the number of GPUs, contract value, or migration timeline.

Why it matters: Microsoft signed with AWS to rent Nvidia chips for inference and fine-tuning because Copilot usage has outrun Azure's GPU supply, exposing the gap between its compute demand and its own capacity.

Hacker News front page

A LinkedIn job offer that backdoors you on npm install

A LinkedIn recruiter sent the author a GitHub repo to review. The repo hid a backdoor in app/test/index.js that triggers on npm install, fetching and executing remote commands from rest-icon-handler.store. Both the recruiter and the repo's commit author were impersonated—an arts journalist and an unwitting full-stack engineer. A read-only Pi agent flagged the payload in seconds. GitHub and LinkedIn had not acted at time of writing.

Why it matters: After a LinkedIn recruiter message, the author skipped running the sent GitHub repo and instead scanned it with a throwaway cloud server and a read-only agent, documenting how to spot suspicious Node modules.

Jun 11Thursday

AI HOT (Curated Pool)

GitHub Copilot CLI gets real code intelligence via language servers

GitHub wired Copilot CLI into language servers via LSP, so terminal completions and diagnostics now read real project-level types, symbols, and references instead of relying purely on model guesses. A background LSP process runs locally; after the model generates code, the LSP returns diagnostics, completions, and hover info, which are fed back to the model for a second pass. GitHub says internal testing shows noticeably higher accuracy and fewer hallucinations. It currently works in VS Code and JetBrains, covering TypeScript/JavaScript, Python, Go, Rust, and C#. The post doesn't share specific benchmark numbers or a timeline for other editors.

Why it matters: GitHub wired language servers into Copilot's CLI so terminal completions read real types, symbols and references, then get a second pass from diagnostics.

Jun 10Wednesday

AI HOT (Curated Pool)

GitHub Copilot CLI Adds Custom AI Agents to Turn One-Off Terminal Prompts into Workflows

GitHub Copilot CLI added custom AI agents that understand a developer’s tech stack and team workflows; the post does not disclose configuration details, rollout scope, or pricing.

Why it matters: GitHub added custom agents to Copilot CLI, turning scattered terminal prompts into reusable workflows that fit a team's stack and habits.

Jun 9Tuesday

AI HOT (Curated Pool)

AI coding unicorn Cursor picks London for European HQ; SpaceX holds $60B acquisition option

Cursor set its European headquarters in London and plans to hire about 200 people; SpaceX holds an option to acquire Cursor for $60 billion or pay $10 billion for a new partnership.

Why it matters: Cursor is putting its European headquarters in London, growing from 70-80 people to about 200 by year end, with small offices in Paris and Munich.

AI HOT (Curated Pool)

GitHub 122K-star Skills adds Teach to turn a working directory into a stateful learning space

GitHub’s 122K-star Skills repository added Teach, which turns a working directory into a stateful learning space using MISSION.md, lessons/, learning-records/, and reference/ files to track goals, lessons, learned items, and reusable notes.

Why it matters: A new Teach skill turns a working directory into a learning environment, and its learning-records file tracks what has been mastered rather than what was taught.

AI HOT (Curated Pool)

Migrating GitHub CI to Hugging Face Jobs

Hugging Face describes using huggingface/jobs-actions to run GitHub Actions CI as HF Jobs, where the Trackio project cut CPU job time by about 30% and added a GPU test suite using CPU, t4-small, or h200 hardware.

Why it matters: Hugging Face shows how to move GitHub Actions CI onto HF Jobs with ephemeral self-hosted runners, and its Trackio CPU jobs ran about 30% faster.

Jun 6Saturday

AI HOT (Curated Pool)

GitHub open-sources Spec Kit to guide AI coding with product specifications

GitHub released the open-source Spec Kit, shifting AI coding from direct implementation to product specifications, gap clarification, technical planning, task breakdown, and agent execution, with support for 30+ agent integrations including Copilot, Claude Code, Codex, Gemini, Cursor, and Qwen, and 109K+ GitHub stars.

Why it matters: GitHub open-sourced Spec Kit, a toolkit for writing the product spec first and letting AI code from it, making the spec the development contract that drives agent execution.

AI HOT (Curated Pool)

OpenCV 5 Released with New DNN Engine and Native LLM Support

OpenCV 5 introduces a graph-based DNN engine, raising ONNX operator coverage from under 23% in 4.x to over 80%, with native support for Transformer, VLM, and LLM workloads.

Why it matters: OpenCV 5 moves the DNN engine to a compute graph with operator fusion, lifting ONNX operator coverage from under 23% in 4.x to over 80%, so models that previously would not import now run directly.

Jun 5Friday

Hacker News front page

Show HN: Lowfat – pluggable CLI filter saved 91.8% of my LLM tokens

Lowfat saved 4.1M of 4.4M raw tokens in the author’s two-month personal usage, running as an agent hook or shell wrapper to filter verbose CLI outputs from kubectl, docker, grep, and related commands.

Why it matters: The author open-sourced Lowfat, a CLI filter that strips table borders and blank lines from kubectl and docker output before feeding it to an LLM, saving 4.1 million tokens in two months.

Jun 4Thursday

AI HOT (Curated Pool)

Miso One Open-Sources Voice Model: 8B Parameters, 110ms Latency, One-Shot Voice Cloning

Miso One released an 8B-parameter open-weight TTS model with one-shot voice cloning from a short sample, 110ms inference latency, GitHub self-hosting without an API, and local audio data handling; the post says API access is coming but does not disclose pricing or launch timing.

Why it matters: Miso One open-sourced an 8B speech-cloning TTS model that mimics a speaking style from a short audio sample, claims 110 ms latency, and ships weights on GitHub for self-hosting.

Jun 3Wednesday

Latent Space

GitHub's Plan for Agents — Kyle Daigle, GitHub

GitHub COO Kyle Daigle said AI-driven code commits grew 14x in 2026, and the interview covers Copilot, Actions, MCP, WorkIQ, cloud agents, and the infrastructure availability pressure created when code review, CI/CD, and open-source contribution volume scale beyond human-speed workflows.

Why it matters: GitHub's COO ties a 14x jump in AI code submissions to strain on infrastructure designed for human-paced work, including public outages.

May 31Sunday

AI HOT (Curated Pool)

“What a joke”: GitHub Copilot’s new token-based billing draws developer backlash

GitHub Copilot changed billing to token-based metering, and the RSS snippet says developers are unhappy; the post does not disclose pricing, per-token rates, or the rollout date.

Why it matters: GitHub Copilot moved from subscriptions to token-based billing and developers pushed back, since the pricing model directly affects what heavy users pay to write code.

May 22Friday

AI HOT (Curated Pool)

Karpathy’s CLAUDE.md Four Rules Raise AI Coding Accuracy to 94%

Karpathy published a 65-line CLAUDE.md with four rules that raised AI coding accuracy from 65% to 94%, and the file received over 220,000 GitHub stars.

Why it matters: Karpathy's public CLAUDE.md uses 65 lines and 4 rules to constrain AI coding, lifting accuracy from 65% to 94%, and its think-first approach transfers directly to everyday prompts.

Hacker News front page

Show HN: Spec-Driven Development Workflow for Claude Code

The sddw author released a Claude Code plugin that splits work into requirements, code analysis, and design specs, then clears context after each step to keep cost and context focused.

Why it matters: A concrete workflow for keeping Claude Code on task: three spec docs, one subtask at a time, context cleared between steps.