• Built for long-horizon coding & whole-repository work
• Multimodal Support (text, images, video, audio)
• 1M token context window
Also check out new $10/mo GOAT plan $70 credits.
🐐 Muse Spark 1.2 by Meta now live in Command Code
🔹 Muse Spark 1.2
• Available in plans: GOAT, Pro, Max
• $1.25 input, $4.25 output, $0.15 cache
🔹Muse Spark 1.2 Contributor
• Available in plans: Go, GOAT, Pro, Max
• Contributor is ~95% cheaper than 1.2
• $0.10 input, $0.20 output, $0.002 cache 
The board after Day 5: anishsharma 5 apps / 5-day streak, waela 5/5, davidvkimball 5/4, raimanncostigan 5/4, AshAmplifies 4/4, buildwithmaya 3/3. There are 26 days left to climb. Add your app to the wall at ntl-back-to-school.netlify.app/showcase! Day 6 starts tomorrow. 🎒
AshAmplifies holds four apps and a four-day streak, most recently British Orchard, and Day 5 isn't over yet. The 27 apps so far come in four shapes: 19 interactive, 3 static explainers, 3 simulators, and 2 games. Whatever makes the idea click counts.
buildwithmaya is three for three, and her apps add up to one coherent curriculum. Skillstax Copywriting Foundations joins Cold Email and Distribution Strategy, with short lessons, real examples, and something to do at the end of each one.
raimanncostigan went from data structures to ink wash overnight. His new jiangnan-rumeng renders a real-time Jiangnan water town where every bridge, roof, and boat traces back to photographs and an 18th-century scroll. Like Oddpedia before it, it runs in two languages.
davidvkimball hung a fifth plate at yahew.com today. The 88x31 Button revisits GeoCities in 1997, when an ad unit turned into a friendship token. His field guide to the old web now stretches from 1974 Teletext to the little badges at the bottom of a personal page. waela matches him at five apps and a five-day streak, and no two of hers are alike. Today she opened Tiny History: The Everyday Museum, which gives 24 ordinary objects a room and a label. It follows CTA Showdown, Conversion Rate Ripple, Flag to Place, and SEO or AEO Sorter.
anishsharma keeps the top spot with five apps in five days. Today's entry is QubitCraft, quantum computing made approachable. It joins Mechanics Visualizer, EZ Circuits, Datacenter Journey, and Pelagic Atlas, so his run now covers forces, circuits, servers, oceans, and qubits.
🎒 Netlify Back to School, Day 5 of 31. Six builders have deployed 27 teaching apps in five days. The assignment hasn't changed: build an app that teaches one idea, ship it, come back tomorrow. 🧵
we migrated the @val.town docs to val town, which was full of AX/DX/UX tradeoffs (to borrow @jim-nielsen.com's framing)
anthropomorphized potato pothole doodle by @jxnblk.bsky.social The full session lineup, including Anil's, is at www.renderatl.com/sessions Anil Bridgpal is putting the RenderATL audience inside his demo, so bring your phone. He'll ship a real app live on Netlify DB: production Postgres in one command, with no provider signup and no keys. Agent runs each get a fork of the database, so breaking production isn't possible.
#ZedEditor Download Zed and view the full changelog here:
zed.dev/releases/sta... You can now skip `pre-commit` and `commit-msg` hooks via the new "Skip Hooks" toggle in the Git Panel. Thanks mauriciord and tdgroot for the initial implementations!
The Project Panel now supports undo and redo for most file operations, in both local and remote projects.
Read the new blog post to learn more about sandboxing in Zed's Agent.
zed.dev/blog/sandbox... 🚀 Zed v1.14 is out! Zed's Agent now sandboxes its `terminal` and `fetch` tools by default. The sandbox prevents agents from writing outside project directories, modifying `.git`, or accessing the network unless you grant permission.
Early customers are already using Research Agent to prioritize indications, shape clinical strategy, design trials, develop laboratory methods, inform market entry, and strengthen patent strategy. Read the launch post and see examples of Research Agent in action: elicit.com/blog/introd... 
We created BioDecisionBench, a benchmark evaluating LLMs on reasoning failures in high-stakes pharma decisions. Elicit highlights more key considerations for decisions (76.7% coverage in Elicit Smartest mode vs. 68.8% for Claude Opus 5 Max). Read the eval blog: elicit.com/blog/biodec.... 
Capability 5: Knowledge that compounds over time
Improve each decision with Projects that keeps sources, context, instructions, and outputs connected in a single knowledge base. 
Capability 4: Transparency by default
Trust and defend every decision with transparent methods trail and sentence-level citations. 