Ran Li

How to bring AI to an extreme art experience that human never feel before? We are collaborating with artist @refikanadol to build the world’s first museum of AI arts — Dataland in LA (@DatalandMuseum) It’s something you won’t want to miss. Check it out at blog.google/company-news/o…

@purplematrix_ Glad to learn you like it!

A good piece for newgrad by @ranli_thinker ranli.me/blog/en/best-e…

@kiranhodor @Google My team don’t do leetcode :)

@ranli_thinker @Google I like stupidly high bars but not leetcode in Google docs

We are hiring exceptional engineers with insane design taste at @Google Someone who: - is deep into systems (latency / scale / pipeline / optimization) - is a super hacker and super builder - lives and breathes media / visual / UX - has ridiculous storytelling instincts We are an AI prototyping lab. We build frontier AI initiatives and things that literally didn’t exist before. Every week feels like science fiction. We use every AI tool you can think of to turn impossible ideas into reality. We work with frontier models like Omni, Genie, alongside the world’s best filmmakers, artists, and creators. Our bar is stupidly high. If this sounds like you, drop me your portfolio.

@anymanymoll @Google Thanks Anmol

@ranli_thinker @Google yo anmolgupta.net

@divyapshere @Google Thank you!

@ranli_thinker @Google I might not be a devloper in the traditional sense, but you might wanna take a look at my profile - divyanaras.com

@hopes_revenge @Google its cool to just be yourself! :)

@ranli_thinker @Google im not any of these things

As someone who builds agent runtime and suffers from every step of pain (container, memory, persistent VM, storage fuse, MCP auths, long running connection and task management), I cannot say enough how happy I am with our Managed Agents in Gemini API. Using agent remotely is as simple as one command.

Sometimes your agent underperforms because you installed too many skills. They are optimized for models months ago and constrains latest model capabilities. skills + model 6 months ago < model today

God-like experience: Create a toy and bring it to life (with fable and gemini Omni)

@alvarovillalbap Yes agree! First time doing a launch video, I’ll make it better next time :D

@ranli_thinker Loving it! Feels like too much text-based information in the video though

AI made content grows faster than any brain can follow. I open sourced Second Brain to help solve this. Second Brain is a local-first personal knowledge base with an agent inside: - Rate, triage and critique every source you captured (X posts, news, blogs, pdf, etc) - Connect it to your existing knowledge base (related, duplicates, contradicts, etc) - Remember what you know & what you care - Recommend news for you based on your history (you can configure RSS feeds & favorite topics) - Full agent companion at your side. Ask, verify, organize and draft new things anytime. It’s a persistent workspace with compounding effect, instead of a graveyard of saved links. Every highlight, save, dismiss, edit, and interaction will be learned by your agent to serve you better. Everything runs and stores locally. You own all data. It also reuses your Claude Code / Codex CLI subscriptions so you won’t pay extra money. This is my favorite open source project so far. I have actively used it for past 6 months, and I’m happy to finally share it!

The best part is — it reuses your existing Claude Code / Codex subscriptions so it won’t add any extra burn! Also you have flexibility to change to smaller models in Settings if quota becomes an issue. If it’s a pure API based setup, roughly $0.1 per input source (and can be even cheaper with open source models).

@ranli_thinker This looks really promising @ranli_thinker! What was your estimated daily burn for the average workflows you mentioned above?

👉 Try at github.com/ryannli/second… There are many more thoughtful features I won’t be able to cover in this post. But the product unfolds as you use it. Video made with @ElevenLabs and @HeyGen’s hyperframes.

Some concrete flavors of AI fatigue (as an engineer): 1. It’s hard to wrap my head around this kind of relationship: they are your friend, your teacher, and also the thing that might replace your value and take your job. That dynamic is weirdly philosophical. There’s goodwill and respect in it, but also a quiet trace of betrayal. I still don’t think we’ve fully adapted to that. 2. When AI is too dumb, watching it apologize over and over gets irritating. When AI is too smart, it makes you feel small and slightly useless. 3. AI gives you this illusion that anything is possible, so you greedily start expanding the task. All the things you used to not be able to finish? Now you suddenly want to do all of them. The result is something like 30% accomplishment, 20% emptiness, and 50% exhaustion. 4. I often feel like I’m just one step in the loop, even though I thought I was the one directing the whole thing. Sometimes I genuinely wonder: do I really have agency, or is there just an AI in front of me dangling a carrot? 5. AI never stops producing things. And inside everything it produces, there’s always this 10% layer of junk. Understanding, filtering, and deleting that 10% takes real mental energy. But if I don’t clean it up, it feels like someone took a dump on my bed. 6. While an agent is running, it keeps saying some kinds of things I’ve never heard of before. Then I have to decide: should I do /btw, or just move on? 7. Something I thought would take 20 minutes somehow turns into an x-high / ultra run that lasts two hours, followed by three rounds of review before it finally works. And just like that, a perfectly nice evening disappears. 8. Because there’s so much AI slop everywhere, I’ve become much more restless when I read. 9. Even if you already know the lesson from the Industrial Revolution (increased efficiency doesn’t necessarily reduce working time, it just expands the boundary of work) you still can’t really stop it from happening. Because humans can’t help themselves. We just want to try.

@thearslaniqbal yes, I read every letter for my favorite articles. Maybe use AI to explain concepts. Never use AI summaries. We shouldn’t outsource this process!

@ranli_thinker This feels better than just getting a short summary. It helps people learn step by step.

Feeling dense, long articles hard to read? I open sourced this “immersive-learning”, an agent skill that converts any long form ideas into a delightful, interactive learning space for you. With beautiful UIs, you can learn in guided sections, mark highlights / take notes as you think, use bilingual support, switch light/dark mode. As a video demo, I used it to build a website to digest Paul Graham’s classic essay “How to do great work”: ranli.me/read-paul-grah… Natively support Claude Code, Codex, Antigravity, Cursor and many agents. We are entering into a new era of bespoke learning experiences. You should still read, digest and think by yourself, and in a much more fun way.

🔗 GitHub: github.com/ryannli/immers… 🔗 Demo: ranli.me/read-paul-grah…