The full Nature paper is open access. For those interested in more details, you can read the PDF directly here: https://
nature.com/articles/s4158
6-026-10265-5.pdf
… We also released the code for both AI Scientist versions for the community to explore. V1: https://
github.com/SakanaAI/AI-Sc
ientist
…
V2: https://
github.com/SakanaAI/AI-Sc
ientist-v2
…
SOFTWARE
-

AI Scientist Nature Paper and Code Released Open Access
By
–
-
Agents Need CLI-First Service Provisioning, Not Web UIs
By
–
When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, it was the plethora of services you have to assemble like IKEA furniture to make it real, the DevOps: services, payments, auth, database, security, domain names, etc… I am really looking forward to a day where I could simply tell my agent: "build menugen" (referencing the post) and it would just work. The whole thing up to the deployed web page. The agent would have to browse a number of services, read the docs, get all the api keys, make everything work, debug it in dev, and deploy to prod. This is the actually hard part, not the code itself. Or rather, the better way to think about it is that the entire DevOps lifecycle has to become code, in addition to the necessary sensors/actuators of the CLIs/APIs with agent-native ergonomics. And there should be no need to visit web pages, click buttons, or anything like that for the human. It's easy to state, it's now just barely technically possible and expected to work maybe, but it definitely requires from-scratch re-design, work and thought. Very exciting direction! Patrick Collison (@patrickc) When @karpathy built MenuGen (karpathy.bearblog.dev/vibe-c…), he said: "Vibe coding menugen was exhilarating and fun escapade as a local demo, but a bit of a painful slog as a deployed, real app. Building a modern app is a bit like assembling IKEA future. There are all these services, docs, API keys, configurations, dev/prod deployments, team and security features, rate limits, pricing tiers." We've all run into this issue when building with agents: you have to scurry off to establish accounts, clicking things in the browser as though it's the antediluvian days of 2023, in order to unblock its superintelligent progress. So we decided to build Stripe Projects to help agents instantly provision services from the CLI. For example, simply run: $ stripe projects add posthog/analytics And it'll create a PostHog account, get an API key, and (as needed) set up billing. Projects is launching today as a developer preview. You can register for access (we'll make it available to everyone soon) at projects.dev. We're also rolling out support for many new providers over the coming weeks. (Get in touch if you'd like to make your service available.) projects.dev — https://nitter.net/patrickc/status/2037190688950161709#m
-
Replicate releases Cog 0.17.0 for ML model containerization
By
–
a lot of people wondering what we've been up to after @replicate joined @Cloudflare . excited to share one of the major releases we've been working on together — cog 0.17.0 cog is an open-source tool to package up machine learning models into containers. it abstracts away the hard parts like CUDA dependency hell, optimizes model environments, and automatically creates an HTTP server that's ready to serve inference. you can deploy a cog container anywhere a Docker container runs, which includes your own k8s cluster, replicate, and soon…. workers ai. for now, enjoy this piece of the puzzle and a wonderful engineering story. we have lots more that we're working on and excited to bring to life! github.com/replicate/cog/rel…
→ View original post on X — @replicate, 2026-03-26 16:08 UTC
-
Microsoft Teams improvements spark collaboration tool innovation race
By
–
Microsoft already shipped some amazing MS Teams improvements, the door is open for others too! Slack folks should join the party in a few days, talking with the team there.
-
Project Memory Request
By
–
2/ PROVIDE CLAUDE WITH PROJECT MEMORY Act as a project context manager that retains all details about my project so I never have to repeat myself. Store the full project context and reference it automatically in every response moving forward. 1. Request
-
OpenClaw maintainer welcomes Telegram bot API streaming fixes
By
–
Talked with @durov and Telegram folks offered uncomplicated help, welcome @izhukov as new OpenClaw maintainer! First action point is to figure out why enabling the bot streaming API sometimes causes message dupes. This will make Telegram support so good!
-
Reducing VPS Infrastructure Costs for Cloud Services
By
–
we currently use a service that lets use easily spin up and down VPS's biggest thing is it costs a lot
-
Gemini Live Gets Its Biggest Update with Gemini 3.1 Flash
By
–
New in Gemini: Live's biggest upgrade yet
— Josh Woodward (@joshwoodward) 26 mars 2026
Faster responses.
Smarter responses.
More EQ.
More linguistic range.
2x longer context.
Android and iOS, powered by Gemini 3.1 Flash.
Enjoy! pic.twitter.com/Y6brhhJG9YNew in Gemini: Live's biggest upgrade yet Faster responses.
Smarter responses.
More EQ.
More linguistic range.
2x longer context.
Android and iOS, powered by Gemini 3.1 Flash. Enjoy! [Translated from EN to English]→ View original post on X — @demishassabis, 2026-03-26 15:54 UTC
-
Cloud Reliability Improvements and Technical Issue Resolution
By
–
Reliability for cloud has improved significantly the last few weeks. Can you share/dm me a link to the session where you had issues? What problem did you hit?
-

Mistral AI Launches Voxtral 4B TTS for Production Voice Agents
By
–

🎉 Congrats to @MistralAI on launching Voxtral 4B TTS — enterprise-grade TTS built for production voice agents. Day-0 support in vLLM Omni. 🌍 9 languages with natural prosody and emotional range 🎙️ 20 preset voices with easy adaptation to new ones ⚡ Ultra-low latency streaming, 24 kHz output in WAV/MP3/FLAC/AAC/Opus Blog 🔗 mistral.ai/news/voxtral-tts Model 🔗 huggingface.co/mistralai/Vox… Mistral AI (@MistralAI) 🔊Introducing Voxtral TTS: our new frontier open-weight model for natural, expressive, and ultra-fast text-to-speech 🎭Realistic, emotionally expressive speech. 🌍Supports 9 languages and accurately captures diverse dialects. ⚡Very low latency for time-to-first-audio. 🔄Easily adaptable to new voices — https://nitter.net/MistralAI/status/2037183026539483288#m
→ View original post on X — @guillaumelample, 2026-03-26 15:42 UTC