I made a personal black hole that makes you take breaks 🕳️ A shader for Ghostty that spawns a small black hole in your terminal - it drifts around, gravitationally lensing your text. The longer you work without stopping, the bigger it gets, until it's basically demanding you go touch grass Take a break and it quietly shrinks away

.@github my repo somehow got switched to private. I’m guessing it was @claudeai but I’m surprised it wouldn’t have asked me to double confirm by entering in the repo name or something. Just happened a few hours ago any way to restore to public? I had ~2800 stars and dozens (maybe hundreds) of forks after getting to #1 on hacker news. Please help!

Here is the analysis of the most sophisticated open-source strategies. Need to watch this one. p3institute.substack.com/p/f…

Super excited to announce that @arcee_ai is the first major American AI lab to replace AWS S3 with Hugging Face for ALL their models and datasets, public AND private 🔥🔥🔥 Multi-million $ partnership to support American open-source AI, let’s go!

Token costs are why there will be no saas apocalypse / good dev tools are cached intelligence for agents! The popular theory goes: agents can write code, so they'll just rebuild every tool from scratch and hit raw APIs. no more dev tools, no more CLIs, no more software layers. just agents and endpoints! We just tested this and the data says the opposite. We benchmarked Claude Code and Codex on real Hugging Face Hub tasks (~1,000 graded runs), with two setups: the agent-optimized hf CLI vs the agent hand-rolling curl or SDK calls from scratch. Hand-rolling burns up to 6x more tokens on multi-step tasks and fails more often (84% vs 94% task success). And that's just dropping one abstraction layer. It would obviously be orders of magnitude more tokens and a dramatically higher failure rate if the agent tried to bypass HF altogether and rebuild model hosting, versioning, and distribution from scratch. Every time an agent re-derives a workflow from raw API calls, you pay for that reasoning in tokens. every single run. a good CLI compresses that entire chain into a few high-level commands the agent can't get wrong. In a world where everyone is complaining tokens are too expensive, abstraction is leverage: thousands of hours of design decisions your agent doesn't have to re-reason about at inference time. Good tools are cached intelligence for agents! So no, agents won't rebuild everything from scratch. they'll gravitate to the most token-efficient tools, because that's what their owners pay for. The software that survives won't just be accessible to agents, it will be accurate and cheap for them to drive. We're seeing it happen with HF, which is becoming the platform for agents to use AI: ~49M requests in just two months, and growing fast! huggingface.co/blog/hf-cli-f…

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Pulled the trigger today and switched 100% of Lindy traffic to DeepSeek v4, churning from Anthropic models. Saves us millions of $ and we're actually seeing an *increase* in performance on many core use cases. Transformative for the business.

I'm starting a new event for Austin creators, builders, artists, and engineers! Bring whatever you're working on, show it off science fair style, or just come check out all the different projects. RSVP or apply to demo: austindemoday.com

Today we're announcing that hybrid agentic inference is coming to Perplexity Computer. Computer can split tasks between a local model running on your machine and frontier models in the cloud. This keeps private data on your device and maximizes token efficiency. Coming soon.

Introducing model routing to Factory. Factory Router picks the right model for every task, automatically. Maintain frontier performance while cutting costs by 25%.

The next evolution of Hermes Agent is here! Introducing Hermes Desktop: everything you love about Hermes, now native on your machine. First demoed in Jensen's GTC keynote, it's now in public preview.

Today, we're rolling out on-demand songs and diagrams in @oboelabs. You remember the alphabet from when you were 4, but you've already forgotten something you read this morning. That's because walls of text are the worst way to retain what you want to learn. Songs lodge in your brain for decades, and a good diagram can help a complicated concept click in seconds. Two new ways to learn, live today.