Leo Amigoni

@nikitabier @BitcoinErrorLog @wirelyss How about allowing read only apps? But posting is on x official apps only? You probably have the stats but I’m sure read is 90%+ of use.

@BitcoinErrorLog @wirelyss 80% of my day is working on spam. If we open another unmonitored method to write to our API, the product would implode and this would be the last post you see that is authored by a human.

The best thing x could do rn is allow third party clients again. It allows other intelligent cracked teams to make the X experience better and more curated, then x can learn from it and make the base app better over time (or acquire the best one lol)

@TrungTPhan @grok how did he get I made?

Australian tech entrepreneur Paul Conyngham explains how he used ChatGPT/AlphaFold (spent $3,000 with no biology background) to create a custom MRNA vaccine to treat his dog’s cancer tumors. Unreal.

@TheAhmadOsman I highly disagree with this take their search results for me are better than any other provider.

the OG grifter AI company they’re so irrelevant that they’re trying to jump on this Mac mini trend like a cheap slop influencer this HAS NOTHING to do with local AI

@Teslaconomics Managed a fleet of 10k+ vehicles for 5+ years. In your proforma add, sales tax, registration, maintenance, cleaning costs (big one). Those don’t seem big but they are the most burdensome.

I plan on owning my own Tesla Robotaxi fleet one day. And the more I run the numbers, the more I realize this new business could become one of the most powerful income opportunities I've ever seen. This is how I'm thinking about it. Based on many analyst models and Tesla’s long-term vision, a reasonable base case assumption is about ~$30,000 per year in net profit per Robotaxi to the owner. This is after things like Tesla’s platform fee, charging, tires, maintenance, insurance, and cleaning. Of course, the network is still early and Tesla is just beginning to roll this out in pilot programs in a few cities, so there’s no official real-world owner earnings yet... but using reasonable assumptions around utilization, pricing per mile, and operating costs, the math starts to get really interesting. If one Robotaxi can earn around $30,000 per year, here’s what a fleet might look like: • $100,000 per year → about 4 Robotaxis • $500,000 per year → about 17 Robotaxis • $1,000,000 per year → about 34 Robotaxis It may sound a bit crazy at first, but when you break it down, it starts to make more sense. These vehicles could potentially drive 50,000 to 100,000+ miles per year in high demand areas. If the economics land somewhere around $0.25-$0.50 profit per mile after all costs, you end up right around that ~$30k per vehicle per year range. And remember, the Tesla’s Robotaxi network is going to work a lot like Airbnb for cars. You add your vehicle to the network, Tesla handles the software, routing, payments, and rider experience, and they take a platform fee (often modeled around 25-35%). The owner keeps the rest after operating costs. Another thing that makes this interesting is the expected cost of the vehicles themselves. Tesla has talked about the purpose-built Cybercabs costing roughly $25k-$30k and Elon told me production is starting in 1 month! If that’s even close to reality, a fleet capable of generating around $1 million per year could theoretically cost somewhere around $850k-$1M in vehicles. That ROI is pretty freakin good! Now to be clear, none of this is guaranteed. I'm just thinking out loud and sharing it with you... a lot still depends on regulations, how fast unsupervised FSD scales, demand in each city, insurance costs, and how Tesla structures the network. But if the system works the way Elon has described it for years, owning a Robotaxi fleet could become one of the most powerful forms of passive income I've ever seen. And I plan on sharing the numbers with everyone on 𝕏 when the day comes. Personally, that’s why I’m paying such close attention. Bc one day, owning a fleet of autonomous Teslas working for me 24/7 might be the modern version of owning a rental property, except instead of tenants, you’ve got robots driving people around all day while you sleep. This next book of Tesla is going to be so exciting!

@NotionHQ Yes!!!! Can’t wait to try this was missing this a lot!

Introducing Custom Agents. The AI team that never sleeps 🌙 They’re autonomous, built for teams, and easy for anyone to build. Give them a job, set a trigger or schedule, and they'll get it done 'round the clock.

@johnrushx Great on John! Thank u

@pvncher Amen!

Uncle bob nailed it The ai cannot read your mind, so there isn’t a reliable way to convey your idea for a product in a way that the ai perfectly delivers on it There’s no way out of working iteratively with them

@arscontexta Wow. This is incredible and inspiring! Thank u!

@AryanJabbari @CoenJacobs @obsdmd @kepano Why do u need it on a VPS?

@amigoni @CoenJacobs @obsdmd @kepano VPSes aren't normally Macs.

Anything you can do in Obsidian you can do from the command line. Obsidian CLI is now available in 1.12 (early access).

@CoenJacobs @AryanJabbari @obsdmd @kepano On Mac can’t you just leverage cloudsynch

@AryanJabbari @obsdmd @kepano Have a stupid amount of headless machines that I spend a lot of my time in via SSH. Would love to have direct access to some of my vaults in there for quick reference, or quick notes here and there. Nothing crazy. It’s just not syncing everything in a proper way.

@iannuttall Yep. Agreed.

🌶️ Hot take incoming I don’t think we need a team of 10+ agents/openclaws any more than we needed a team of 10+ custom subagents six months ago

@DavidOndrej1 I use both. Their app is second to none to chat with one voice

there's no point paying for Perplexity just give your OpenClaw access to an API key for OpenRouter and then set "perplexity/sonar-pro-search" as the default web search model and "perplexity/sonar-deep-research" as the default Deep Research model and you'll never have to visit the Perplexity website ever again plus, you just gave your AI Agent access to a super-powerful web search tools (much better than the built'in Brave API)

@arscontexta I’m trying various memory layers and running medium scale evals to measure accuracy. Experimenting with hindsight and the ClawdBot style layer which is probably closer to qmd

agent orchestration for knowledge work spent way too many tokens figuring out how to replace my ralph loop setup anyone else experimenting with this?

@arscontexta I am but I’m way behind u

@jonas I built a markdown vault system in swift for Apple ecosystem, compatible and an expansion of markdown, but haven’t tackled editor yet, but synching is there.

I've been thinking super beautiful lightweight git-backed collaborative markdown editor to use in lieu of notion, but where the docs are just stored in my repo in docs/*.md would be quite nice Does this exist or must I vibeslop it?

@nathanwchan How? Please? Cause I need to test coredata, foundation model inference, speech to text and text to speech. Cloudsynch, intents, widgets, lock screen and control panel interactions and live activities. Can we do those without Xcode? And no device?

iOS devs: you can completely replace using Xcode entirely with a simple combination of Codex skills and run actions. No MCPs or anything fancy needed. Ask Codex to help you build them. I'm 97% in the Codex Mac app now, and working to eliminate the last 3%.

@pvncher Can’t wait

Working on deep codex integration for this It's very cool to have codex able to work seamlessly through different folder roots!

@antirez So we should first translate prompts to Italian? Then send them? How do u say prompt Italian? @grok

Italian is an intrinsically understandable language, by people and machines.

@thymikee This is amazing. Thank you

Do yourself a favor and install skills too: 𝚗𝚙𝚡 𝚜𝚔𝚒𝚕𝚕𝚜 𝚊𝚍𝚍 𝚌𝚊𝚕𝚕𝚜𝚝𝚊𝚌𝚔𝚒𝚗𝚌𝚞𝚋𝚊𝚝𝚘𝚛/𝚊𝚐𝚎𝚗𝚝-𝚍𝚎𝚟𝚒𝚌𝚎 And give it a star on GitHub ⭐ github.com/callstackincub…

Introducing Agent Device: token‑efficient iOS & Android automation for AI agents 𝚗𝚙𝚡 𝚊𝚐𝚎𝚗𝚝-𝚍𝚎𝚟𝚒𝚌𝚎

The Codex App is basically freezing for me I can barely switch between threads? While codex code is quite good. Anyone else seeing the same?