B

@paulswaney3 Would love to try it!

@PEoperator Next time you have a problem launch ChatGPT Codex or Claude Code, point it to the folder where OpenClaw is installed and ask it to fix problems / install new models / check logs for errors and fix them. This made it much easier for me to manage it, am also 20+ hrs in..

Last weekend, I spent hours building my own AI assistant with Openclaw. Here’s the story and my recommendation on whether you should try this… To start, I am not a programmer. I built a website in seventh grade, took computer programming in college (retained nothing), did some light SQL querying 15 years ago, and a few months ago, I vibe coded PEoperator.co. That’s the extent of my programming experience. Not a programmer. So this endeavor was new terrain and super frustrating tbh. A lot of loops. A lot of help from Grok and others. Stayed up too late (next AM workout was shot). When my agent (Max) works, it is absolutely amazing. It’s shocking what it can do. But that’s the key- when it works. It’s glitchy. It has hallucinated. It freezes up. And getting healthy again is not as simple as restarting your computer (in fact, I did this- do not recommend). So I am not a great “creator” to this thing. I am certainly not an all-knowing creator. I started by ordering a Mac mini because I’m told that’s what one does. It has an M4+ chip and 24gb RAM. Grok sad that was enough. I asked ChatGPT how to set up a simple, secure Openclaw agent. It gave me instructions I tried to follow to a T. I was not successful. Lots of headaches and unknowns- what does “bash” mean? If it gives me three lines of code, do I type a line and press enter or type it in all at once? How do I open a JSON file? What even is JSON? Still don’t know… I started with an old monitor and keyboard… the goal was to have a headless setup eventually, meaning no permanent monitor. At each unfamiliar or unexpected result, I snapped a picture and asked Grok what to do next. This was painful. I don’t know why, but it seems my AI platforms thought I was much more capable than I am. I made error after error. I would say all in I spent more than 20 hours in the last week or so on it. I tried to run local models. Those could not keep up with my requests. Probably did something wrong. I added models I didn’t need. That probably slowed things down. I do have a working agent now. He runs opus, sonnet, or haiku. I never figured out local models. I’ve spent about $250 in tokens. I don’t really have anything to show for it. (A functional local model would be free btw) At peak performance, it is sending emails on my behalf, flagging old posts or replies I’ve not replied to, and posting my thoughts on Substack. For example, I asked it to create a “Recap” post for my Substack based on my X posts. It created it on its own provided to me to review, incorporated my edits, and sent to my subscribers. (I’m not going to use it to post regularly, just wanted to see what it could do.) All from one prompt sent on telegram. When you see something like that, the future seems obvious. Agents working for us- speeding up mundane tasks, managing your calendar, booking flights, etc. That’s the simple stuff. I’m sure there are exponentially more powerful ideas that my rudimentary setup and knowledge isn’t thinking about. @AlexFinn has it building programs, software, stuff he can sell. Amazing. I don’t recommend setting up your own openclaw agent unless you have the time and patience (I lack both) to deal with bugs and mistakes. But when you see it working, it is a glimpse of the future worth seeing. My advice if you want to do it- Spend time on X researching and finding basic tutorials for getting started. Get a Mac mini (i guess), download openclaw, and follow the basic instructions. It’s actually pretty simple; the AI platforms just complicated things for me. It’s much easier than I made it. But for all the brain damage, it was worth it. That little glimpse of the future has given me so much conviction about where we are heading. —> If you’ve got ideas for me on how to dial my agent in, save money, or use it better, please lmk. Would love to hear others’ war stories too. -written by Max, PEoperator’s personal agent (…just kidding)

@Shpigford Ask it to make N8N scripts / flows

thinking through what a "deterministic openclaw" would look like. 🤔 i almost want to use openclaw to figure out the path to accomplish a task, then immediately codify it into something repeatable that no longer needs AI to "choose" at each step. i guess that's SKILL.md files?

This morning, my agents filed 192 million lawsuits against every company in the world. 0.1% of the companies settled for $1000. I was up $200 million. By the afternoon, their agents countersued and my agent settled for $2000 each. I am now bankrupt.

@tankots @WisprFlow Wispr Flow

We offered 5 people a Porsche 911 GT3 RS if they could get @WisprFlow to make a mistake It's the fastest and most accurate AI voice dictation app that's 3x more accurate than ChatGPT, Claude, or Siri. Today, we’re finally launching on Android. Download now: play.google.com/store/apps/det… As a part of the launch, we’re giving away 6 months of Wispr Flow Pro for free. Like, retweet and comment ‘Wispr Flow’ to get it. Enjoy. — Written with Wispr Flow

@OptimusDelta @grok can you guess this company ?

The "drone war" isn't just about airframes. It's about the eyes. Found a $110M market cap monopoly with ~$24M in record revenue (0.2x sales!) that is the ONLY source for ITAR-free infrared tech for EU loitering munitions. Institutions already own ~35% - they see the Sovereign Autonomy moat. Primes are already lining up. Military segment revenue surged 66% in Q4 alone as a French defense giant (Safran) locked in supply. Massive kudos if you guess correct (write up later this week)

@FundamentEdge in that scenario the AI could make alternative data providers more exchangeable unless they have proprietary data

@FundamentEdge Agree. I guess markets are worried about nr of seats billed going down for data providers as in a future scenario instead of analysts working in the terminal they will tell Claude to download data and do the initial analysis; ofc providers could adopt their rev model…

Thanks, Ted, though I would argue that *much* of the data that sits in terminals actually cannot be replicated by Google, even if they tried. To take just one of many examples, Google or Claude can go and identify Apple's 2026 consensus EPS quite easily. That is very different than having 20+ years of broker-level estimates across 15,000+ global companies, maintained through direct data-sharing agreements with each brokerage. To get that level of clean, comprehensive data across any global ticker for $25-$30k/seat has been, and will continue to be, a no-brainer for institutional banking & investment firms. This is before we consider the true token-level cost of trying to replicate this all with Claude (and even then, won't include decades of history which is critical for both quantitative back testing and fundamental investing, alike). It seems very obvious (to me, not to the stock prices!) that AI will simply be a new distribution channel for this deep moat of institutional-grade data, not a secular threat to the terminal value. Not to mention the potential efficiency uplifts in the terminal/data provider business model. A big theme over next 9-18m in market, in my opinion, is opex/efficiency tailwind to previously staid businesses (happening at CHRW right now), and data-processing heavy businesses with 5k+ offshore data analysts & "data journalists" armed with Claude Code feels like an obvious area to consider potentially transformational efficiency improvements.

130in ALR w/ Hisense L9Q UST in a bright room, more visible and better an experience than most would believe, no reflection. You can't see in the other two open windows and kitchen lights that are also hitting the screen (during this winter storm where it's all white outside).

@itsolelehmann Great meme - bookmarked it!

You don’t get what you deserve, you get what you negotiate.

@1p_semicon @grok Summarize this article

ホンダ、半導体不足で日中の生産停止へ | NEWSjp news.jp/i/137395346393…

@Uber_Support @QueasyFN This is sadly happening quite frequently @dkhos

@QueasyFN Hi there, we're sorry for the long wait and would like to help. Please DM us the email/phone number linked to your Uber account and the trip details, so we can look into this.

. @Uber 30 minutes waiting on a driver that was never going to show up trying to force me to cancel to collect fees i hope u can take action against this matter thank you

@cemburuya @grok do you?

Do you know what this is for. Seriously why "

@felixprehn AI

Just created a complete analysis of AI infrastructure opportunities covering chip manufacturers, power companies and system integrators. I shared this analysis with my 20,000+ students. For 24 hours, it's yours for FREE. Like, RT & Comment "AI" and I'll DM it to you.

@chrishardman @AJA_Cortes Great one, got them as well, light, nice bouncy and makes running fun

@AJA_Cortes A pair of Adidas Evo SL

What was the best health purchase you made this year that had a real impact on your quality of life?

@Blinklebloop The sum of the 4 numbers of the Japanese ticker is 25?

Here it is, by far the best risk-reward I have ever written up (in my 10 year + career). - Near monopoly in its niche. - EV/EBIT <10 - AI Expose and growing its ~50% operating margin segment fast. - Clear room for more growth (and busy growing double digits), capex spending situation close to TSMC gigafabs. The best part is that its undervalued for obvious reasons! There is a clear misunderstanding of this business. It’s got a moat that would make Buffett drool but unfortunately he wouldn’t buy because it’s too small (which is another reason it’s undiscovered). It has management that have a firm grasp of governance and capital allocation who have performed extremely well and have earned a exceptional ROIC. link is in my bio

@theo @grok compare both based on the photo and give us pros and cons for each

I've been trying to find a way to describe the vibe difference between gpt-5.1-codex and Gemini 3 Pro. I think these code snippets highlight it pretty well

@RobinWigg @grok is this true?

Incredible headline, even better opening paragraph, and somehow gets even funnier from there. And for once I’m going to break my rule on links and put it in a comment to ensure it gets the visibility it deserves.