Phantomus

1.2K posts

Phantomus banner
Phantomus

Phantomus

@phantomus_host

changed too often, will leave it as is

Inscrit le Şubat 2014
1.2K Abonnements2K Abonnés
Jonas 🦩👩‍💻 (HeySandy.ai)
@pmarca IDK I’ve got dozens of daily Chron jobs and code all day in Opus 4.6 and rarely hit my daily $100/month claude max limit. I’m either doing something right or not doing enough 🤷‍♂️
English
2
0
8
456
Marc Andreessen 🇺🇸
Magical OpenClaw experiences that use frontier models cost $300-1,000/day today, heading to $10,000/day and more. The future shape of the entire technology industry will be how to drive that to $20/month.
English
498
383
5.5K
791.3K
Phantomus
Phantomus@phantomus_host·
genuinely curious what the magical experience is for such openclaw setup. Research comes to mind with high context calls, analytics of large data sets, what else? I think majority of business use case run fine on 2-3 monthly max account, but i could be wrong. Would love to find our how people use this at scale, too much content right now is about use cases that run fine on $20 per month already.
Marc Andreessen 🇺🇸@pmarca

Magical OpenClaw experiences that use frontier models cost $300-1,000/day today, heading to $10,000/day and more. The future shape of the entire technology industry will be how to drive that to $20/month.

English
0
0
0
13
Phantomus
Phantomus@phantomus_host·
had an issue like that, but the think was off - went with high, everything was done right away. Maybe ‘adaptive’ is a good setting, need to test, but gpt-5.4 is very good, many times its an issue with config or misunderstading of the model. for coding tasks if bot is used, its also important to note the use of codex itself vs. doing completion style coding which will usually be the default.
Phantomus tweet media
Keith Tyser@keithtyser

gpt-5.4 was basically unusable for me in @openclaw. it would explain what needs to be done, I’d say “ok do it,” and then… nothing. no action, no feedback, sometimes it would just go silent or say it’s “working” with zero visibility. felt like babysitting an intern that never actually touched the keyboard switched to @NousResearch Hermes agent and it’s night and day. same model, but now it actually executes. on par with opus-4.6 for me no idea why the gap is that big but yeah, huge relief after losing Claude OAuth in openclaw

English
0
0
0
49
Phantomus
Phantomus@phantomus_host·
As of now, the best way to scrape data that isn’t part of the public web, is writing custom scripts, which AI can do great, saving a ton of time. Going screen by screen with browser use is not realistic for large volume, will eat a lot of tokens, and very slow. A good way to automate the dev of such scripts, is to run it with browser use first, record the workflow down to the HTML selector details and then scale with a scrapper script.
English
0
0
1
52
Phantomus
Phantomus@phantomus_host·
with average life expectancy between 25 and 35 years between 200,000–10,000 BCE there was no time for 8-hour sleep.
🧬Maxpein🧬@maximumpain333

The most dangerous lie in human history isn’t about food. It isn’t about medicine. It is about sleep. For 200,000 years, humans did not sleep 8 hours. That number was invented in 1938 by a mattress company called Simmons Beautyrest. Before that campaign, the average human slept in two shifts. Historians call it “Biphasic Sleep.” You would sleep for 4 hours, wake up for 2, then sleep for another 4. During that 2-hour window, people would pray, have s*x, write, think, and connect with their families. Some of the greatest works in human history were created in that sacred middle window. Shakespeare wrote most of his plays between 1AM and 3AM during his second wake period. Mozart composed entire symphonies in what he called “The God Hours.” Then the Industrial Revolution needed workers on a fixed schedule. You cannot run a factory on biphasic sleep. So they hired a psychologist named Dr. Nathaniel Kleitman to “prove” that 8 consecutive hours was the biological standard. He faked the studies. He was funded entirely by the mattress industry. And the medical establishment adopted his research without question because it aligned with the factory model. They turned the most creative 2 hours of human consciousness into a “sleep disorder.” They called it “Insomnia.” They medicated it. They gaslight an entire generation that 8 hours of continuous sleep was healthy. They pathologized the exact window of consciousness that produced some of the greatest art, music, and literature in human history. You are not an insomniac. You are experiencing the most natural form of human consciousness. And a mattress company convinced you it was a disease. Stop medicating your genius. Wake up at 2AM. Write the thing. The “God Hours” are calling. ✨🙌🏾💫 © Andre Gonzalves

English
0
0
0
26
Nav Toor
Nav Toor@heynavtoor·
🚨 Twilio charges $0.0079 per SMS. Someone just turned any old Android phone into a free SMS gateway. Unlimited messages. $0. It's called SMS Gateway for Android. Install it on any Android phone. It becomes a full SMS sending and receiving server with an API. No Twilio. No MessageBird. No per-message pricing. No contracts. Just an old phone and a SIM card. Here's what's inside this thing: → Send and receive SMS through a REST API from any app or service → Works with any Android phone running 5.0 or newer → End-to-end encryption. Messages are encrypted before they leave the device. → Multi-SIM support. Use multiple SIM cards on one phone. → Multi-device support. Connect multiple phones to the same account. → Real-time webhooks for incoming messages → Multipart messages with auto-splitting for long texts → Track delivery status of every message in real time → No registration required. No email. No account in local mode. Here's the wildest part: That old Android phone in your drawer that you haven't touched in 2 years? Install this app. Insert a SIM card. You now have your own private SMS infrastructure. Two-factor authentication. Order confirmations. Appointment reminders. Notification alerts. All the things startups pay Twilio thousands a month for. Free. Running on a phone you already own. Startups spend $500 to $5,000/month on SMS APIs. This costs the price of a SIM card. 875 GitHub stars. 359 commits. Apache 2.0 License. 100% Open Source.
Nav Toor tweet media
English
294
997
9.3K
829.6K
Phantomus
Phantomus@phantomus_host·
does @cursor_ai save the settings of desktop app to the cloud so on sign in from another machine it's copied over? how do you copy your settings to a new machine? got a new mac air, took more time to configure cursor and moving claude and codex to the right secondary bar 😂
English
0
0
0
33
Phantomus
Phantomus@phantomus_host·
new mac decided this is how I need to see the weather, keeping it
Phantomus tweet media
English
0
0
0
18
Phantomus retweeté
Simon Willison
Simon Willison@simonw·
I was a guest on @lennysan's podcast! We talked about agentic engineering and all sorts of other LLM-related topics for 1h39m(!), plus a little bit about kākāpō parrots - here's my selection of highlights from our conversation simonwillison.net/2026/Apr/2/len…
English
24
21
266
27K
Phantomus
Phantomus@phantomus_host·
very insightful and refreshing episode
Lenny Rachitsky@lennysan

"Using coding agents well is taking every inch of my 25 years of experience as a software engineer." Simon Willison (@simonw) is one of the most prolific independent software engineers and most trusted voices on how AI is changing the craft of building software. He co-created Django, coined the term "prompt injection," and popularized the terms "agentic engineering" and "AI slop." In our in-depth conversation, we discuss: 🔸 Why November 2025 was an inflection point 🔸 The "dark factory" pattern 🔸 Why mid-career engineers (not juniors) are the most at risk right now 🔸 Three agentic engineering patterns he uses daily: red/green TDD, thin templates, hoarding 🔸 Why he writes 95% of his code from his phone while walking the dog 🔸 Why he thinks we're headed for an AI Challenger disaster 🔸 How a pelican riding a bicycle became the unofficial benchmark for AI model quality Listen now 👇 youtu.be/wc8FBhQtdsA

English
0
0
0
47
Phantomus
Phantomus@phantomus_host·
it makes no sense to build a wrapper for coding agents. A month ago I built myself a framework for coding agents adopted to my needs of working on multiple projects: openclaw powered, its own UI, better memory, rating system of output to help train the coding agent - its stashed and not used anymore. Its much easier to work with existing tools like codex and claude code, and they are evolving much faster than me trying to tweak the process to adopt to new changes.
English
1
0
1
40
Phantomus
Phantomus@phantomus_host·
i am pretty sure we doing this all wrong: AI should give us time back, not the other way around.
English
0
0
0
33
Phantomus
Phantomus@phantomus_host·
Shipping products with MCP support out of the box presented big opportunities for us in restaurant tech and is now a core part of every product we ship to customers. Accessing your data via chat interface tools like Claude isn’t for an average user I must say. Yet, experienced operators in our industry use these tools to better understand their business and data. The best part is not connecting a single source to chat up the things you can easily see in your product’s dashboard, its ability to bring multiple product’s data into a single interface which otherwise would never talk to each other, especially in a slow pace industry like we serve.
English
0
0
0
27
Phantomus
Phantomus@phantomus_host·
@AlfaEsparta @NatureUnedited right on that, but this isn’t a zoo. the bears cannot be let in the wild as they spend their entire life dancing to a bunch of low life assholes, thus having no skills to survive in their natural environment.
English
0
0
0
57
Nature Unedited
Nature Unedited@NatureUnedited·
Abused zoo bear still circles in imaginary cage seven years after being freed... 😢🐻
English
340
1.5K
12.6K
3.8M
Phantomus
Phantomus@phantomus_host·
restaurant industry is quite slow in adopting tech, but some operators are more educated then others, and it maintains higher margins for them. something quite awesome we’ve done today that can apply pretty much to any API, is connected @ToastTab to Claude via MCPs, this just opens up a ton of opportunity. products like toast adopt AI within the platform, but when you operating a chain of restaurants, the number of products used on daily basis is massive and they don’t talk to each other. adding products like that as connectors to Claude and educating operators on how to use it gives them an edge, as many of reports are still manual and quite specific, hard to find, hard to analyze and share with your team. if you own a restaurant chain, learning these tools will make your challenging day to day job more pleasant.
English
0
0
1
57