Guess who starting to seed the narrative.
truthsocial.com/@realDonaldT…
Numberonepal🐝 retweeted
This is f*cking insane. OpenAI CEO Sam Altman:
"We are going to see 10-person billion-dollar companies pretty soon
If I were 22 right now, I would feel like the luckiest kid in history"
In 22 seconds, he explains why the next billion-dollar company won't need a building full of people, just a few founders and their agents
ChatGPT → Codex → Agent Builder → Agents SDK → Evals → A 10-Person Company Run By Agents
Most people will feel motivated for 3 minutes, then go back to scrolling
The few who act will start building their company this weekend
Save this before it disappears from your feed
Everything below is free:
Find what to automate first
cdn.openai.com/business-guid…
How companies put AI to work
cdn.openai.com/business-guid…
Codex in the cloud
chatgpt.com/codex
Codex skills
github.com/openai/skills
Agent Builder (agents without code)
platform.openai.com/docs/gui…
Function calling (give your agents tools)
platform.openai.com/docs/gui…
Agents SDK for JavaScript
openai.github.io/openai-agen…
Agents SDK examples
github.com/openai/openai-age…
A customer service agent team you can copy
github.com/openai/openai-cs-…
Voice agents
github.com/openai/openai-rea…
Evals (check your agents' work)
platform.openai.com/docs/gui…
All of this costs $0
The 10-person billion-dollar company will be built by someone who opened these links, not someone who scrolled past them
Bookmark it and start with the first link tonight
Then read how to set up the agent team behind a tiny company in the harness engineering guide below ↓
Numberonepal🐝 retweeted
Your agent passed every test
The issue is still open
A better prompt won't fix it, because the model isn't the broken part
I broke down the harness, loop and graph around it: what each one owns, how they nest, and which one to fix first ↓
Numberonepal🐝 retweeted
This is f*cking insane. Anthropic CEO Dario Amodei was asked what a kid graduating high school should do now. His answer:
"It will also eliminate jobs, and probably a large number of them"
In 35 seconds, he names who gets hit first: entry-level law, entry-level finance, entry-level consulting
His own prediction: 50% of entry-level white-collar jobs disrupted in 1 to 5 years
Every past disruption gave people time to adapt. He says this one is deeper and coming faster
Prompts → Agents → Harness → Loops → The One Running the AI
His advice: learn to use AI. Using it won't be enough. You need a harness that runs it for you
You can start with repos bellow.
Every repo below is free:
Anthropic's plugins for legal, finance, sales, HR and data work
github.com/anthropics/knowle…
Anthropic's agents for analyst work: models, memos, research notes
github.com/anthropics/financ…
Excel, Word, PowerPoint and PDF skills
github.com/anthropics/skills
Autonomous financial research agent
github.com/virattt/dexter
Deep research agent
github.com/assafelovic/gpt-r…
Full-length research reports
github.com/stanford-oval/sto…
12 principles of agents that actually work
github.com/humanlayer/12-fac…
Batteries-included agent harness
github.com/langchain-ai/deep…
Claude Agent SDK
github.com/anthropics/claude…
Agent memory
github.com/thedotmack/claude…
Autonomous agent loop
github.com/snarktank/ralph
Browser control
github.com/microsoft/playwri…
Claude cookbooks
github.com/anthropics/claude…
Free agents course: 18 lessons
github.com/microsoft/ai-agen…
All of this costs $0
AI won't replace you. Someone with a harness will
95% will keep applying for jobs AI already does, the 5% who build a harness will be the ones running it
Bookmark it and send it to someone just starting their career
Then use the guide below to build your harness before everyone else does ↓
Did they forget to cheat in Guam?
drive.google.com/file/d/14aF…
Gimme an oar.
teapaw.org/WarClandestine/status/…
unavailable
THE 15% BAND
THE 15% BAND
Look at this chart.
59 races. Senate and governor.
States ordered from reddest to bluest in 2024.
The solid lines are 2024.
The dashed lines are 2026.
The shaded bands are what moved.
One formula fits all of it:
Republican 2026 = 0.85 × Trump 2024
Democrat 2026 = Harris 2024 + 0.15 × Trump 2024
For every 1,000 Trump points, 850 stayed Republican. 150 landed on the Democratic side.
The numbers:
Senate: Republicans kept ~85% of Trump’s share
Governor: ~86%
Variation explained: 88%
What makes it strange:
It didn’t matter how red the state was. Wyoming, Ohio, Illinois, Massachusetts: same 15% (p = 0.69). The Democratic gain was sized by Trump’s vote, not Harris’s. The Harris part is zero.
The 0.85 beat both standard election-swing models in every set of races.
Drop any single state and the multiplier stays between 0.846 and 0.853.
Why seats flipped:
At 0.85, any state where Trump got under about 58.5% falls below 50%. Texas, Kansas, Iowa, Ohio, South Carolina, North Carolina: all under that line. All flipped.
What this means:
Midterms are messy. This one isn’t. Two sets of races, different candidates, different campaigns, and the same 15% decrease almost everywhere.
A pattern this even demands answers at the ballot level: paper ballot hand counts, poll-book check-ins against votes counted, and voter files showing who actually turned out.
The numbers raise the question.
The ballots can answer it.




































