Anthony | Ship OS
133 posts
Anthony | Ship OS
@anthonywclaude
Most builders collect prompts. I’m building the OS for shipping. ChatGPT/Claude/Hermes workflows → real products. Building Ship OS in public from $0.
Katılım Mart 2026
31 Takip Edilen22 Takipçiler
Claymation is still killing it for our clients
Never too late to learn...
English
@JamesonCamp Said the same thing, the ai race is on
x.com/anthonywclaude…
Anthony | Ship OS@anthonywclaude
The wild part Anthropic is one of Elon’s biggest AI competitors. But SpaceX compute may help Claude scale. That tells you how insane the AI infrastructure race is becoming. Even competitors may need each other’s rails. Question: Do you think the next AI winners are model companies… or compute companies?
English
Elon has spent an OBSCENE amount of money and time building the largest AI training cluster to beat Anthropic and OpenAI
and all of a sudden he just gave access to a direct competitor
220k GPUs. For context GPT-4 trained on like 25k H100s
Anthropic gets 8x what trained GPT-4 + what they ALREADY HAVE. This is a big deal.
Claude Code rate limits doubling today, peak throttling removed for Pro/Max plans
Our whole team is in Claude Code hours daily, and we are all hitting limits constantly. This is absurd.
Claude@claudeai
We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity. This, along with our other recent compute deals, means that we’ve been able to increase our usage limits for Claude Code and the Claude API.
English
The wild part
Anthropic is one of Elon’s biggest AI competitors.
But SpaceX compute may help Claude scale.
That tells you how insane the AI infrastructure race is becoming.
Even competitors may need each other’s rails.
Question:
Do you think the next AI winners are model companies…
or compute companies?
Claude@claudeai
We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity. This, along with our other recent compute deals, means that we’ve been able to increase our usage limits for Claude Code and the Claude API.
English
Smart move, Open Ai was crushing them in this department.
I'm interested to see the rate limits now, even though I've never hit a rate limit on the $100 plan.
I've come close, but never actually hit it.
With Codex, I vibe-coded for 8 to 10 hours a day And never even come close to hitting the limit.
Claude@claudeai
Effective today, we are: 1) Doubling Claude Code’s 5-hour rate limits for Pro, Max, and Team plans; 2) Removing the peak hours limit reduction on Claude Code for Pro and Max plans; and 3) Substantially raising our API rate limits for Opus models.
English
Beautiful
Touches the soul
The time to build is now
It's never been easier to hit the ground running
andrew pignanelli@ndrewpignanelli
Announcing Cofounder 2: Run an entire company with agents. It's the infrastructure for the one person billion dollar company - orchestrating agents across engineering, sales, marketing, ops, and design. (and yes that's my real grandma in the video)
English
Day 1 of going from $0 → $1M vibe coding:
Shipped a local jumping jacks counter.
It uses my camera to count reps while I livestream the build journey on YouTube.
Tiny app, but it proves the loop:
idea → AI agents → working demo → content → feedback.
Onward.
English
50 Claude Code agents running in parallel.
One mission.
Clone me.
This morning I transcribed over 800 hours of my own livestreams.
Then I launched 50 subagents to process all of it simultaneously.
Each one analyzing a different slice of my personality, my coding patterns, my decision making.
The output?
A complete psychological and operational profile of myself fed directly into a Hermes agent.
It thinks like me. It talks like me. It makes decisions like me.
I just cloned my soul into an AI agent using BridgeSpace and Claude Code.
This is what agentic engineering actually looks like.
English
@YaramasaGautham @TTrimoreau Haven’t hit a limit yet on the $100 plan
English
If you had to pay for only one AI tool:
-Codex
-Claude
-neither
What are you choosing?
English
@sama Earlier attempt to setup Openclaw wasn't successful on an AWS VPS. Hopefully this integrations makes it smooth.
Meanwhile have been running Hermes using ChatGPT Plus subscription.
English
you can sign in to openclaw with your chatgpt account now and use your subscription there!
happy lobstering.
English
Vibe coding with a Hermes agent.. from the comfort of my bed.
Building an entire software from my phone using Codex & Claude Code sub agents
This was not possible 6 months ago
This is the future
Build now..
English
@bridgemindai The $20 codex subscription runs out for me very quickly looks like I’ll have to upgrade to the $100 plan I’ll run more test today
English
GPT 5.5 xHigh in Codex is a one shot machine.
Backend bugs that used to take 3-4 prompts?
One shot. Done. Moving on.
I've been running it all morning on BridgeMind's backend.
Every bug I've thrown at it gets solved on the first attempt.
Claude Opus 4.7 was great at this when you could actually use it.
Codex with GPT 5.5 xHigh lets me ship without watching a rate limit bar.
OpenAI keeps raising the ceiling.
This is the best coding model I've used for backend.
English
Comp Engine update.
Just shipped the math engine.
81 tests. All passing.
Paste a real address → get the ARV, repair cost, MAO,
and deal verdict.
30-min spreadsheet → 60-sec analysis.
Documenting the journey from $0.
Built with @claudeai 🧠
English
@bridgemindai claude rate limits turned language evolution backwards
English
You can stop hitting your Claude Code rate limits.
Just install the Caveman skill.
It forces Claude to respond like a caveman.
Cuts token usage by 75%.
"Bug in auth. Token wrong. Fix line 42."
Same accuracy. Quarter the tokens.
This is the most ridiculous Claude Code optimization I've ever seen.
And it works.
English
@bridgemindai Haven’t hit a limit ever since switching to the $100 plan!
English
Claude Code rate limits are way better now.
I'm at 27% of my session limit and I've been vibe coding all morning with Claude Opus 4.7.
23% of my weekly limit used.
A week ago I was hitting limits in 2 hours.
Anthropic actually fixed the rate limits.
English
Alex Hormozi on the rule of 100: "The rule of 100 is you do 100 per day... 100 minutes posting content, $100 a day on ads, or 100 reach outs, if you want to be crazy do all three."
English
@Mho_23 I can’t wait till they fix those dumb ass voices
English
