Denis Nekliudov

@GonzalezJulius @sahasv_01 @AndrewYNg @openclaw @NousResearch So it is like Hermes but for Dummies? :)

@sahasv_01 @AndrewYNg @openclaw @NousResearch Seems like a level higher on the execution of work. Openclaw is incredible but if you use it you know that its ability to have high quality output is something you need to build. Seems like Andrew may be looking to make quality more easily accessible

Announcing OpenWorker! An open-source agent that doesn't just chat with you, but delivers finished work -- like hand you a polished document, send a slack message, or update a calendar entry. Ask it to prepare a customer brief, untangle your calendar, draft a report, or triage a Slack alert. It works across your files and everyday tools, produces the deliverable, and checks in before doing anything consequential. OpenWorker runs on your Mac, with Windows support coming soon. It does not lock you into any one model. Bring your own API key and run it with GPT 5.6 Sol, Claude Fable, Gemini 3.6, an open weight model (like Kimi, GLM, DeepSeek, Inkling), or Ollama to keep your data local. Your data does not leave your machine except through an LLM provider and integrations that you choose. @rohitcprasad and I are building OpenWorker because AI coworkers are an important way to get work done, and we want there to be an open, privacy-preserving, model-independent option. Check it out and let us know what you think! Try it out: openworker.com (requires your own API key) Source code: github.com/andrewyng/open…

@AndrewYNg Love the OSS spirit! Do you have plan to add some server to it to coordinate jobs while laptop is closed or communicate between machines and other devices?

This is exactly where we are with AI today: we're bolting it onto existing processes instead of inventing entirely new ways of working. THAT is where the real juice is 🧃 youtu.be/sRvrXL83N-c

Steam engine analogy: electricity didn't replace steam quickly because people just swapped the motor instead of redesigning the factory. Took 50 years. Same with computers — people typed, printed on paper, before realizing you could go fully digital.

Watched this video — great ideas, fully aligned with my thinking. Thread on the AI supercycle and why we're getting it wrong 🧵

My best friend died recently. And I happen to have hundreds of hours of audio messages between us. How ethical would it be to clone his voice and feed all his thoughts I have into RAG? Would it negatively impact my mental health talking to a virtual checkpointed clone of him?

Time for mt Tam climb 🏔️ 🚲 is coming soon 100mi, 9kft elev, easy 🤙 marincentury.redpodium.com/2026-marin-cen…

Can someone explain why people around are still driving their Teslas themselves? Are they too stingy to pay 100/mo to waste no mental energy during commute anymore ?

@doooyle Dude, I am using my kindle scribe for exact same purpose. Compile pdf with the agent -> send to Kindle. No paper wasted No phone distraction

surprised more people aren't doing something like this Codex now creates a "newspaper" for me every morning Unread messages, calendar, surf report, news Anything I can do to stay off my phone until later in the day is a priority

Everyone: AI will take my job Reality for ages: someone else will take your job Do nothing really changes: younger, smarter, faster are always producing job insecurity

Wow. Dude just put additional display on the laptop kb (touch monitor?) Never seen such setup before Are there two screen laptops on market?

@mark_k :/ the ad made using camera not the gpu… idk, feels outdated

Awesome vibe coding ad, with Gilfoyle from Silicon Valley! 😂😂

Doom scrolling but make it educational 🤓 Introducing Short Video Overviews in NotebookLM! Turn your most complex sources into 60-second, vertical videos that deep dive into any concept. Rolling out now to Google AI Ultra and Pro subscribers on mobile & web (free users soon!)