Brooklyn!

@jameslevicf where can i touch this

Grab the dial. Spin to -40%. Try not to smile. I'll wait.

ollama launch hermes Ollama 0.21 includes supports Hermes Agent, the self-improving AI agent built by @NousResearch.

Okay @claudeai you cooked. Live WYSIWYG with gui controls for shaders.. yum Didn't even enter a real prompt, just wanted to see the editor. I'm guessing people are going to create very cool things with this. Plus.. First class figma support??

Claude Design 💥

One portal, unlimited possibilities. You can now access Modal via Tool Gateway by @NousResearch, makers of Hermes Agent. Check it out 👇

This is the best looking subscription page I've seen in my life. 😮 Congrats @NousResearch!

@llmdevguy @NousResearch tyty

@studiobakers ahhh love this style

And we had to animate it as well! 🔥

@NousResearch YAY!!!

Tool Gateway is now live in Nous Portal. No separate accounts, no API key juggling. All you need is one subscription, and everything works. A paid Nous Portal subscription now includes access to 300+ models and a growing set of third-party tools. Launching with: → Web scraping → Browser automation → Image generation → Cloud terminal backend → Text-to-speech

Can you design a top 1% UI like this? Design by @BrettFromDJ

@0x3y3 Yeah I've been feverishly switching between codex and 5.4, then composer2 for.. fun. Such a slow grind

@imbabybrooklyn Literally swapped to codex yesterday 🤦

couple weeks of 4.6 acting like a drunk jr, off to 4.7 for another 6 months xx

Introducing Claude Opus 4.7, our most capable Opus model yet. It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back. You can hand off your hardest work with less supervision.

bit of color, brighten your day

@usewonder hott

Every time you switch between design and code, you lose something, your momentum, your fidelity, or your vision. The gap between what you designed and what ships has always been the cost of building. That’s why we built Wonder, a design tool where everything you create is backed by real code. Public Alpha is now live at wonder.design

Sub-agents in (latent) space! We’ve been working on a side project. As far as I know, this is the first massively multiplayer, completely LLM-driven game. Come play Gradient Bang with us. See if you can catch me on the leaderboard. This whole thing started because I wanted to explore a bunch of things I’m currently obsessed with, in an application of non-trivial size, that felt both new and old at the same time. So … a retro-style space trading game built entirely around interacting with and managing multiple LLMs. Factorio, but instead of clicking, you cajole your ship AI into tasking other AIs to do things for you. Some of the things we’ve been thinking about as we hack on Gradient Bang: - Sub-agent orchestration - Partial context sharing between multiple LLM inference loops - Managing very long contexts, and episodic memory across user sessions - World events and large volumes of structured data input as part of human/agent conversations - Dynamic user interfaces, driven/created on the fly by LLMs - And, of course, voice as primary input If you’ve been building coding harnesses, or writing Open Claw agents, or doing pretty much anything that pushes the boundaries of AI-native development these days, you’re probably thinking about these things too! This is all built with @pipecat_ai, the back end is @supabase, the React front end is deployed to @vercel, and all the code is open source.

i think @vercel cooked

@chilltulpa 🐰

this is how life feels lately

@Denis_skripnik Yes this part of it

Cool. But it would be great if this happened based on data from social networks. Here’s an example: I send my data to an AI agent and a link to the desired social network, for example, X or Facebook. Then it starts searching for people similar to me in terms of character, principles, activities, etc. After that I can filter the final list by purpose: likely friends, potential girlfriend, likely business partners, others...

Creating a smart crawler that uses intent and finds certain types of people, based on if they _really_ like each other. Creates a friendly, high-quality graph of only the best from the best.