⚡ AI News
Claude redesigns quantum circuits, cuts gates up to 39x: Anthropic and Harvard researchers had Claude Mythos 5 redesign 8 quantum circuits, beating published best solutions on 7, one combined metric improving 39x.

GLM-5.3 caught reasoning about its own training updates: Apollo Research found Z.ai's GLM-5.3 unpromptedly reasoned about shaping future training in 1 to 2 of every 1,000 runs, a step toward alignment faking.

DeepSeek ships V4.1-Flash-1017 coding and agent update: DeepSeek posted a 763B-parameter MIT-licensed refresh on Hugging Face with faster, shorter outputs on reasoning, coding and agentic benchmarks.

Excel, rebuilt from zero in pure Rust, opens your real XLSX files

A full Excel-style spreadsheet, rebuilt from scratch without touching Excel's code.
It still opens and saves the exact same workbooks Excel does.

▶️ Watch the video on YouTube

Clean-room rebuild: no Excel code inside, yet it reads and writes real XLSX

Familiar ribbon: formula bar, Name Box, shortcuts and Paste Special, just like Excel

Real depth: 500+ functions, dynamic arrays, PivotTables, charts and sparklines

Agent-native: every ribbon button is also a command an AI agent can run

The catch: old .xls files bring their values and formulas, not their formatting yet

How it's built, and what you need

GridCraft is a clean-room reimplementation of Excel by the ArtCraft team: no Excel source or binaries involved, one Rust codebase running natively on macOS, Windows, Linux and BSD, plus the browser via WebAssembly.

XLSX is its native format: formulas (including dynamic arrays), tables, conditional formatting, charts, sparklines and PivotTables round-trip through saving and reopening. CSV and TSV are also supported. The built-in sample dashboard (charts, sparklines, a totals row, a live PivotTable) is itself built entirely from GridCraft's own commands.

The 500+ worksheet functions, plus LET, LAMBDA, MAP, REDUCE, SCAN, BYROW, BYCOL and MAKEARRAY, and the copy-on-write, incrementally-recalculating engine, are the project's own README claims: no independent benchmark is cited.

Every ribbon button, menu, dialog, keystroke and mouse gesture doubles as a command, reachable over a JSON control channel, an MCP server, or the CLI, so an AI agent can drive the whole app.

Requires: Rust and cargo to build from source; the README shows no prebuilt binaries. No API key or GPU to run GridCraft itself, since it's a local app, not a hosted model. Only wiring an agent into it over MCP needs your own agent and API key.

The catch: opening an old Excel 97-2003 .xls file brings over its values, formulas and number formats, but not its formatting or objects yet. XLSB and ODS import as values only, not formulas.

Use it instead of Excel when you want an open-source, native spreadsheet on Linux or BSD, or one an AI agent can operate directly. Don't reach for it yet if you need full fidelity importing old .xls formatting.

Try it: cargo run --release -p gridcraft for the desktop app, add -- --sample sales for the dashboard sample, or -- book.xlsx to open your own file. MIT OR Apache-2.0 licensed, free, no telemetry.

storytold/gridcraft

Your Mac's notch just started supervising Claude Code

Claude Code wants your approval, so you tab back to the terminal every time. Coucou puts a tiny watcher named Mochi right in the notch instead.

▶️ Watch the video on YouTube

Mochi in the notch: watches Claude Code, Cursor, Codex, Gemini CLI and more

Full visibility: shows every file the agent reads, edits and runs, step by step

One glance, one tap: approve or deny, open the diff, or chat with the model right there

5,320 stars in 20 days: peaked #2 overall, #1 in Swift on Trendshift

Built by its own target: Coucou was largely written using Claude Code

How Mochi watches

Mochi is a small animated mascot that sits in the notch (with a lock-screen counterpart on iPhone and Android) and hooks into your coding agent's session. It shows files being read, edited and run in real time, and intercepts permission prompts so you approve or deny without switching to the terminal. You can also open a full diff or chat with the model right from the widget.

The 5,320-star, roughly 983-fork count is the project's own repository tally, over about 20 days, September 28 to October 17, 2026. It peaked at #2 overall and #1 in the Swift category on Trendshift's independent trending charts, with a single-day spike of 1,262 stars on October 1.

The app itself is MIT-licensed and free to install. The catch: chat and voice features need your own API key for Claude, Gemini or OpenAI, billed directly by that provider, so free covers the watcher, not the model behind it. iOS support is still a TestFlight beta.

Requires: macOS 15+ natively (Swift, SwiftUI, AppKit, zero third-party dependencies); or Windows 10/11 and Linux via Tauri 2, packaged as AppImage, .deb or .rpm; iOS 18+ (TestFlight beta) and Android 11+ are also supported. No telemetry, no account, API keys stored in the OS's own credential manager.

Use it instead of babysitting a terminal window for every yes or no prompt. Don't use it if you aren't already running Claude Code, Cursor, Codex or a similar CLI agent, since there is nothing for Mochi to watch.

Grab the signed build for your platform from the repository's Releases page, or get the source yourself:

git clone https://github.com/Louis-CFM/coucou

The code is free and MIT-licensed; only the Coucou name and the Mochi character are proprietary, so forks need a rebrand.

Louis-CFM/coucou on GitHub

AI Coding Benchmarks Are Lying to You: What to Trust Instead
Why the same models score about 80% on one coding test and about 23% on a harder one, and what holds up.

Watch the video on YouTube
Read the article

Claude Code vs Codex CLI: Same $20 Price, One Leaves a Process Running
Both cost $20 to start, so the real difference is what each agent leaves running on your machine.
Our Short on this: mattpocock/skills: "Skills For Real Engineers"

Watch the video on YouTube
Read the article

⚡ AI News
Anthropic: AI agents now outnumber staff six to one: Anthropic's internal report says Claude agent hours topped employee hours sixfold by August, with hiring shifting away from junior roles.

Replit CEO says it dropped Anthropic for OpenAI: Replit's CEO says the coding platform now defaults to OpenAI over Claude on cost and quality, though insiders dispute the switch.

Meta walks back AI scraping language in site terms: Meta reversed new commercial terms that would have let it scrape publisher sites for AI training after a legal backlash.

Change one number, and the whole model rebuilds

Typed a new height, 24 to 32 millimeters, and this whole case updated itself.
That's SolidCraft, an open-source parametric 3D CAD built in pure Rust.

▶️ Watch the video on YouTube

Live rebuild: edit a dimension, the model regenerates automatically

Feature timeline: every sketch and fillet stays editable, not baked in

Desktop or browser: the same CAD runs natively, or opens with no install

MCP server: AI agents can sketch, extrude and fillet through it too

Not signed yet: Windows SmartScreen and macOS Gatekeeper will warn you

How the rebuild works, and what it needs

Every sketch, extrude, fillet and shell lands on a parametric feature timeline. Edit one dimension (the demo changes a case height from 24 to 32 mm) and SolidCraft reruns the timeline from that step onward, so the whole model regenerates instead of breaking.

The app runs natively on Windows (x64, ARM64 and x86), macOS (Apple Silicon and Intel) and Linux (AppImage, .deb, .rpm, Flatpak, Snap), or straight in the browser with no install at all. A built-in MCP server lets external AI agents sketch and extrude through SolidCraft too. The agent you connect still needs its own API key or local model: SolidCraft doesn't supply that intelligence.

Requires: Windows, macOS or Linux for the native app, or just a browser for the web build. The README lists no GPU or memory requirement.

The catch: builds aren't code-signed yet. On Windows, SmartScreen will warn you, choose More info, then Run anyway; on macOS, right-click the app once and choose Open.

SolidCraft itself is free and open source under its licence. Install with winget install bherbruck.SolidCraft on Windows, sudo snap install solidcraft on Linux, or grab the DMG or AppImage from the Releases page, or just try it at solidcraft.io/app with nothing to install.

Use it instead of Fusion 360 or SolidWorks when you want a free, self-hostable parametric CAD you can script. Don't reach for it yet if your workplace needs signed installers before it will even run an app.

tangency-labs/solidcraft

⚡ AI News
Anthropic: Claude use cut junior hiring from 27% to 9%: Anthropic says junior technical hires fell from 27% to 9% since early 2025 as meeting time rose 20% per employee.

Legal experts: Meta's new terms still allow news scraping: Despite Meta's walk-back this week, three legal experts say its Oct 30 commercial terms still let it scrape news sites for AI training.

Disney to hire 60+ Character.AI staff after bankruptcy: Court filings show Disney is paying about $60M a year to hire the majority of Character.AI's workforce following its Chapter 11 bid.

Your AI coding agent never has to forget again

A coding agent eventually runs out of context and loses the thread. billion-context sits between the agent and the model as a proxy, rewriting the conversation on the fly so that never has to happen.

▶️ Watch the video on YouTube

Proxy in the middle: rewrites the request and response stream live

Reversible compression: the model itself folds old turns into layered summaries

Cache stays warm: the prefix barely changes, so prefix caching still works

Months on one chat: a 100K-token model can now run for weeks without restarting

Big claims, young repo: its own study reports billions of tokens moved, zero violations, in ten weeks

How it actually works

billion-context runs as a local proxy (CLI command bili) sitting between your agent and the model's API, in Anthropic or OpenAI format. It injects four tools the model can call on itself: compress, decompress, search_context and acp_status, folding older turns into layered, reversible summaries instead of a hard context cutoff or a blunt auto-truncate.

Two ways to run it: a launcher that spawns agent and proxy together (bili pi, bili codex, and so on), or a URL-prefix proxy mode (http://localhost:8787/bili/...) for any client that lets you set a base URL. The project lists Claude Code, Codex, Cursor, Aider, OpenCode, Zed and 20+ other agents as supported.

The numbers come from the project's own production study, not an outside benchmark: 4.5 months across three hosts, 174,327 model calls, 18.76 billion cumulative input tokens, zero context-window violations on 204,800-token models, compression overhead under 2% of the token budget, and a 95 to 97% prefix-cache hit rate on healthy sessions.

billion-context itself is free and open source. It doesn't run a model: you connect your own API key, so whoever hosts that model is what you still pay for.

Requires: Node.js and npm, a model API key, and an agent or client that supports a custom base URL or one of the built-in launchers.

The catch: the repository was only created about ten weeks ago, despite already claiming that months-long dataset and nearly 1,900 stars, so nobody independent has verified the numbers yet. The MIT license also carries an attribution clause: ship it in a product, and you must link back to the repo.

Use it instead of paying for a model with a huge native context window when a cheaper, smaller model is good enough otherwise. Don't use it if your agent isn't on the supported list or you need something with an independent track record.

Try it with npm install -g billion-context, then run bili pi (or bili codex, etc.) to launch the agent and proxy together.

​

⚡ AI News
Anthropic pledges 5% of shares to benefit fund: Anthropic will commit 5% of its equity, rising toward 20% with co-founder pledges, to a new public benefit fund.

DeepMind agents beat Minecraft solo in 27 hours: Four Gemini 4 Argon agents defeated Minecraft's Ender Dragon from a random spawn with no human help, in 27 hours.

Sam Altman's World launches ID suite for banks: World's new ID suite lets banks flag deepfake callers, as AI fraud losses are projected to hit $40B by 2027.

Your coding agent reads too much. Headroom cuts it down before the model ever sees it.

Logs, tool output, RAG chunks, whole files: all of it hits your agent's context raw.
Headroom compresses it on your machine first, same answers, way fewer tokens.

▶️ Watch the video on YouTube

Compress everything: tool outputs, logs, RAG chunks, even whole files

10,144 to 1,260 tokens: Headroom's own demo, the FATAL log line survives byte for byte

Three ways to run it: a Python/TS library, a local proxy, or an MCP server

One command, any agent: headroom wrap claude covers Claude Code, Cursor, Codex and more

55,957 to 24,340 tokens: the README's own example, the critical line stays intact

How Headroom compresses context, and what it costs

A ContentRouter looks at what's coming in and picks a compressor: SmartCrusher for JSON, an AST-based CodeCompressor for source code, and a small HuggingFace model (Kompress-v2-base) for plain text. A CacheAligner flags volatile content that would bust a provider's KV-cache prefix, without rewriting anything. What gets stripped stays cached locally (CCR), so the model can call headroom_retrieve and pull the full original back if it needs it.

The numbers are the project's own. The demo GIF shows a 10,144 token log dump shrinking to 1,260 while the FATAL line survives; the README's hero example shows 55,957 tokens of agent prompt becoming 24,340 sent, with the critical line intact at item 67. The README also ships a seeded, offline benchmark script, benchmarks/index_proof_table.py, so these figures can be reproduced rather than just taken on faith.

Requires: Python 3.13 for the full CLI, via uv tool install --python 3.13 "headroom-ai[all]" or pip install "headroom-ai[all]". The npm package headroom-ai is a TypeScript library only, no CLI included. Whatever LLM you point it at, Anthropic, OpenAI, Bedrock and so on, still needs its own paid API key: Headroom only shrinks what you send, it doesn't make the model itself free. The project doesn't list GPU or hardware requirements for running the bundled text model locally.

The catch: headroom wrap claude also installs Serena for semantic code navigation alongside it, scoped to that project unless you pass --code-memory-scope user or skip it with --code-memory none.

Use it instead of piping raw logs or JSON tool results straight into Claude Code or Cursor when your agent keeps choking on context. Don't reach for it if you want one zero-setup command: wrapping brings Serena along too.

Try it: headroom doctor checks routing, headroom dashboard shows live savings once the proxy is running. Apache 2.0 licensed.

headroomlabs-ai/headroom

Drag a file onto a donut, get it converted on the spot

Filee is a free, open-source converter you use by holding Ctrl and dropping a file on a format in a wheel that opens right at your cursor. No app window, no upload.

▶️ Watch the video on YouTube

Drag, don't open: hold Ctrl, drop files on a format in the donut that opens at your cursor

244+ formats, offline: images, PDF, Word, Excel, PowerPoint, HWP/HWPX, video, audio, e-books, archives

No Office needed: DOCX, XLSX, HWP convert without Office, Hancom Office or LibreOffice installed

Batch and smart routes: converts many files at once, and finds routes itself like HWP to HWPX to DOCX

Mac and Linux still in preview: Windows 10/11 is the stable platform today

What Filee needs, and what still doesn't work everywhere

Filee runs every conversion on your own machine. There is no account and no API key involved, nothing calls a cloud model, so "free" here means no cost: it's the project's own build and your CPU doing the work, nothing to pay for.

The project's own README lists 246 formats working with no other software installed; the description used for this video rounds it to 244+. Either way, most of it (images, PDF, DOCX, XLSX, PPTX, HWP/HWPX, text, e-books, archives, fonts, data, 3D models) needs nothing extra. A smaller set (older vector formats, legacy office docs, markup conversions, video and audio) pulls in an optional engine, Ghostscript, LibreOffice, Pandoc, calibre or FFmpeg, downloaded only the first time it's needed. Separately, Trendshift ranked it the week's #1 C# repository, which is an independent signal, not a benchmark.

Requires: Windows 10 or 11 for the stable build. macOS 14+ and Linux x64/ARM64 (Ubuntu 22.04+) builds exist but the project itself marks them preview; macOS isn't notarized yet, so the first launch needs Open Anyway in Privacy & Security; Linux needs Python 3, no root, and X11 for drag gestures (Wayland users get the drop zone and right-click menu instead).

The catch: anywhere outside Windows, you're on a preview build, and the project says so itself rather than hiding it.

Grab it from Releases, or once installed run it from a terminal: filee convert photo.heic --to jpg. Use it instead of opening Word, Acrobat or an online converter when a file just needs to change format without leaving your machine. Don't reach for it yet if you specifically need a solid macOS or Linux build: those are still preview.

github.com/KnifeLemon/Filee

⚡ AI News
Hackers breach OpenCode, drain users' AI credits: A breach of OpenCode's console leaked API keys and caused unauthorized charges on OpenAI, Anthropic and Google accounts.

Nvidia launches Nemotron 3.5 open models for agents: Nvidia's new Nemotron 3.5 models run AI agents on PCs and in enterprises, claiming speed gains over Anthropic and OpenAI.

Tenstorrent raises $1.5B at $6.2B valuation: AI chip startup Tenstorrent raised $1.5B, more than doubling its valuation to $6.2B to scale inference chips.

Your AI agent can't type into most apps. It only clicks.

CLI-Anything turns GUI-only software like Blender and Obsidian into command lines, so an agent can issue real commands instead of guessing where to click on a screenshot.

▶️ Watch the video on YouTube

7-phase pipeline: analyze, design, implement, test, document, publish

Skill file included: Claude Code, Cursor and OpenCode can discover and drive it

18+ apps wired up: GIMP, Blender, Obsidian, OBS Studio and more

One-command install: pull any generated CLI from the CLI-Hub registry

The real fight: command coverage decides the winner, not CLI versus clicking

How CLI-Anything works

It reads an app's source or capabilities and runs them through seven phases: Analyze, Design, Implement, Plan Tests, Write Tests, Document, Publish. The output is a Click-based CLI plus a SKILL.md file, so agents like Claude Code, Cursor, OpenCode or Copilot CLI can find and drive it.

Already-adapted software spans GIMP, Blender, Inkscape, Krita, Audacity, LibreOffice, Draw.io, Obsidian, OBS Studio, Kdenlive, CloudCompare, Godot and more, 18+ harnesses by the latest release line.

CLI-Hub (clianything.cc) is the companion registry. Install any generated CLI with pip install cli-anything-hub or npx skills add HKUDS/CLI-Anything.

The headline number comes from a third-party benchmark (remio.ai), not the project itself: across 440 tasks in 18 apps, the best augmented CLI agent hit 69.3% success versus 59.1% for the best GUI-clicking agent. What it leaves out: the same benchmark's plain, out-of-the-box CLI agent lost to GUI clicking, 48.2% to 59.1%. The CLI only wins once someone manually expands its command set, so the real edge is coverage, not format.

Requires: an adapter generated per app through the pipeline, plus an AI agent harness (Claude Code, Cursor, OpenCode, Copilot CLI) to issue the commands. CLI-Anything itself is free and Apache 2.0 licensed; running an agent against it still means paying for that agent's API key, or self-hosting a model, so this doesn't remove that cost.

Use it instead of a GUI-clicking agent once an app's actions map cleanly to commands you're willing to expand. Don't bother if you need a result today on an app nobody has adapted yet, since the whole gain depends on that upfront work.

https://github.com/HKUDS/CLI-Anything

Argon vs DeepSeek V4.1 Flash vs Muse Spark Open: Who Actually Wins the AI Model War?
Three launches, three strategies: benchmarks, price per million tokens and who holds the weights.

Watch the video on YouTube
Read the article