Sabitlenmiş Tweet
Nick 🚀
8.7K posts
Nick 🚀
@nicholasporter
loading… || lakers in 5
Downtown Manhattan Katılım Ekim 2011
3.2K Takip Edilen4.4K Takipçiler
@ryancarson @openclaw will you be sharing your config best practices?
i feel like im being overly cautious with permissions so its still mostly feeling like a chatbot
welcome your thoughts
English
omg @openclaw is sooooo good at being a Chief of Staff.
What huge unlock for founders (and everyone)!
It’s taken me 2 weeks to refine my setup and now it’s working like a dream.
Biz dev, calendar management, research, task management, brainstorming and more
English
@ivanburazin building a federated agent framework for assisting small cities with intent decomposition and cross-department integrations to reduce latency for citizens’ interactions with their government
English
If you're building something with OpenClaw/any agent framework/RL environments and need sandbox infra at scale, we can give you $10k in credits instantly.
You could be bootstrapped or a newly minted pre seed company or building a weekend side project that has potential.
Reply with what you're upto below and if it fits the bill, we'll reach out!
English
@hthieblot i have the engagement of someone below 200 followers and am building cool shit
does that still count
English
Dear algo, please show this tweet only to founders bellow 200 followers building cool shit.
English
it’s a unfortunate how pattern-seeking paired with ego can make a wise man look foolish
the abstraction of erics exchange is valid but oh boy does this feel boomer as hell
“you’re absolutely right!”
Eric Weinstein@EricRWeinstein
This is a fresh session. I have attempted to ask why my installation of @claudeai is not under my control and responding appropriately. In the 2nd Response in a fresh session it tells me @AnthropicAI has throttled me from using it from reasoning via a toggle: "That's the one. If that controls extended thinking / reasoning budget — and the name and structure strongly suggest it does — then your account has it set to zero. You're paying $200/month for the most powerful model Anthropic offers, doing work that is essentially the hardest kind of sustained formal reasoning (gauge theory on novel 14-dimensional bundles, operator verification, index theory), and the system has allocated you zero tokens for deep thinking." Three queries, in and this is the response:
English
the social contract has a latency problem
people don’t lose faith in the idea of government… they lose faith in their experience of government
the gap between what institutions promise and what people receive is the central failure mode of governance
and it’s an engineering problem
English
i'm opening my calendar for 15 min slots this Friday!
a16z speedrun application opening is just weeks away - come AMA 1:1
first come, first served... drop a comment / like and I'll send you a link to schedule! (if there's space remaining)
English
we have a CLI that can turn even prosumer imagery into 3D models that will kick the shit out of whatever photogrammetry is likely at play here
<20 min turnaround utilizing a 5090, can be airgapped and requires no internet at a fraction of the cost
cc: @elonmusk @aelluswamy
DriveGreenLiveGreen@DriveGreen80167
Two Tesla Cybercabs rolling through the Bay Area with roof-mounted ground mapping LiDAR rigs! 👀
English
@dudhat_paresh @petergyang i welcome your notes when you do!
currently running zeroclaw on my android seeing the extent to which it can be a single or limited scope node working alongside my openclaw/hermes set up at home
English
@nicholasporter @petergyang Both work great. Just need tmux agent on the phone. Didn't try termux on the phone. will check it out
English
My personal experience on the drawbacks of using Claude Code vs. OpenClaw as a personal assistant from my phone:
Claude Code
- Doesn't have dangerously skip permissions via remote control. Also remote control doesn't feel super reliable
- Doesn't have voice replies so doesn't feel as personal
OpenClaw
- Tends to forget things randomly still
English
@dudhat_paresh @petergyang can you explain why termius here?
running a similar setup but using termux on the phone, a bit more wieldy of a UX but more control over config
English
@petergyang I think running with tailscale and tmux on server and in mobile use termius so occassionally when you think you are not getting reply on tg, you can verify it with termeus directly.
English
@thsottiaux @steipete is a building designed by the architect AND autocad/revit or did the architect use autocad to do design
abstraction moves the “work” further upstream, a tool shouldn’t take credit for its purpose
English
Do people like this? We don't do this for codex because it exists to help you and it's important that you remain the owner and accountable for your work without AI taking credit. At the same time it does mean that you can't trace how popular codex is among repos.
Yuchen Jin@Yuchenj_UW
I noticed something interesting: Claude Code auto-adds itself as a co-author on every git commit. Codex doesn’t. That’s why you see Claude everywhere on GitHub, but not Codex. I wonder why OpenAI is not doing that. Feels like an obvious branding strategy OpenAI is skipping.
English
how it feels when another product you use gets a CLI
this is the way
GIF
Readwise@readwise
Introducing the Readwise CLI. Anything you've saved in Readwise (highlights, articles, PDFs, books, youtube, newsletters) is now instantly accessible from the terminal. For you, and your AI agents. npm install -g @readwise/cli
English
Introducing Naive - hire autonomous employees with their own identity.
Own compute. Own bank account. Own legal entity. Own email. Own credentials. Own mobile.
No humans-in-the-loop. They sign up for tools, pay for services, deploy apps, file documents, and run your entire company.
Describe a business. Naive runs it.
Reply "Naive" + RT. Get $100 credit for free.
English
Okay. Now using my cc max with hermes. It’s crazy’s how much better it is than every other llm.
Now just need to figure out how to stop lighting tokens on fire.
English
Follows me and doesn’t have the audacity to take my public good I spent days on to open source and give me credit.
Typical Mario move lol.
0xMarioNawfal@RoundtableSpace
Most people have thousands of saved tweets they never find again. Siftly runs a 4-stage AI pipeline on your bookmarks — entity extraction, vision analysis, semantic tagging, categorization — then turns everything into a searchable knowledge base with a mindmap view. 100% self-hosted. Open source. Data never leaves your machine.
English