gary

ai engineer with a sleep debt

no life, just prompts

[gary @0xgary]

This is f*cking insane. Anthropic engineer:

99% of people still use Opus 5.5 like Google.

The top 1% build harnesses that let swarms of Claude agents work, coordinate and improve on their own.

He runs his agents inside one harness, with Chief and PM agents managing the entire system.

In this 26-minute workshop, he shows how to get maximum output from Claude Code at minimum cost.

Model → Tools → Harness → Closed Loops → Self-Improving System

Worth more than every $1,000 vibe-coding course combined.

Watch it today.

Then read the full Harness, Loops and Graphs guide below ↓

[seeco @seeconvm]

https://t.co/7KKkUgUSki

[gary @0xgary]

This is f*cking insane. Anthropic CEO Dario Amodei was asked what a kid graduating high school should do now. His answer:

AI will cost jobs, and probably a lot of them

In 35 seconds, he names who goes first: entry-level law, entry-level finance, entry-level consulting

His own prediction: AI could wipe out up to 50% of entry-level white-collar jobs in 1 to 5 years

Every past disruption gave people time to adapt. He says this one cuts deeper and moves faster

Prompts → Agents → Harness → Loops → The One Running the AI

His advice: learn to use AI. Just using it won't be enough. You need a harness that runs it for you

Start with the repos below.

Every one of them is free:

Anthropic's plugins for legal, finance, sales, HR and data work
https://t.co/lrctveJwVF

Anthropic's agents for analyst work: models, memos, research notes
https://t.co/UcBFhPUDWQ

Excel, Word, PowerPoint and PDF skills
https://t.co/3cpMklhZfE

Autonomous financial research agent
https://t.co/8X85714Ie1

Deep research agent
https://t.co/dO98BkdFBK

Full-length research reports
https://t.co/YzJFF6tXn2

12 principles of agents that actually work
https://t.co/ItEeJdS5uM

Batteries-included agent harness
https://t.co/Ud6dbK7zCe

Claude Agent SDK
https://t.co/yFkJw3PsCf

Agent memory
https://t.co/QRyhVN8ixE

Autonomous agent loop
https://t.co/HTsxGfN4ev

Browser control
https://t.co/dMmD4HUgze

Claude cookbooks
https://t.co/cvEHbRDar9

Free agents course: 18 lessons
https://t.co/geB0ZallPi

Total cost: $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 ↓

[gary @0xgary]

This is f*cking insane. Anthropic CEO Dario Amodei was asked what a kid graduating high school should do now. His answer:

AI will cost jobs, and probably a lot of them

In 35 seconds, he names who goes first: entry-level law, entry-level finance, entry-level consulting

His own prediction: AI could wipe out up to 50% of entry-level white-collar jobs in 1 to 5 years

Every past disruption gave people time to adapt. He says this one cuts deeper and moves faster

Prompts → Agents → Harness → Loops → The One Running the AI

His advice: learn to use AI. Just using it won't be enough. You need a harness that runs it for you

Start with the repos below.

Every one of them is free:

Anthropic's plugins for legal, finance, sales, HR and data work
https://t.co/lrctveJwVF

Anthropic's agents for analyst work: models, memos, research notes
https://t.co/UcBFhPUDWQ

Excel, Word, PowerPoint and PDF skills
https://t.co/3cpMklhZfE

Autonomous financial research agent
https://t.co/8X85714Ie1

Deep research agent
https://t.co/dO98BkdFBK

Full-length research reports
https://t.co/YzJFF6tXn2

12 principles of agents that actually work
https://t.co/ItEeJdS5uM

Batteries-included agent harness
https://t.co/Ud6dbK7zCe

Claude Agent SDK
https://t.co/yFkJw3PsCf

Agent memory
https://t.co/QRyhVN8ixE

Autonomous agent loop
https://t.co/HTsxGfN4ev

Browser control
https://t.co/dMmD4HUgze

Claude cookbooks
https://t.co/cvEHbRDar9

Free agents course: 18 lessons
https://t.co/geB0ZallPi

Total cost: $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 ↓

[seeco @seeconvm]

https://t.co/7KKkUgUSki

[gary @0xgary]

Andrej Karpathy:

prompting is fading, and the graph is what's left

He walks through how to build one, step by step

Prompts → Agents → Loops → Graphs

skip a layer and it comes back as a failure you pin on the model

by the time you track it down the week is already gone

95% of engineers are still polishing prompts, the 5% building graphs will run everything

watch it today, then save the full graph guide below ↓

[gary @0xgary]

Andrej Karpathy:

prompting is fading, and the graph is what's left

He walks through how to build one, step by step

Prompts → Agents → Loops → Graphs

skip a layer and it comes back as a failure you pin on the model

by the time you track it down the week is already gone

95% of engineers are still polishing prompts, the 5% building graphs will run everything

watch it today, then save the full graph guide below ↓

[seeco @seeconvm]

https://t.co/7KKkUgUSki

[gary @0xgary]

This is f*cking insane. Andrej Karpathy (ex-OpenAI, ex-Tesla AI lead):

Bigger models aren't the answer. Tools and tight feedback loops are what decide if an agent works

In 16 minutes, he breaks down the stack that actually holds up: a small model, the right tools and a closed loop

Big Model → Small Model → Right Tools → Closed Loop → Self-Improving Agent

Most people keep paying for a bigger model. The loop is what makes a small one dangerous

Beats any $500 AI course this year

Bookmark it and watch today

Then read the "Harness, Loops, Graphs" guide below - the closed loop is the harness ↓

[gary @0xgary]

This is f*cking insane. Andrej Karpathy (ex-OpenAI, ex-Tesla AI lead):

Bigger models aren't the answer. Tools and tight feedback loops are what decide if an agent works

In 16 minutes, he breaks down the stack that actually holds up: a small model, the right tools and a closed loop

Big Model → Small Model → Right Tools → Closed Loop → Self-Improving Agent

Most people keep paying for a bigger model. The loop is what makes a small one dangerous

Beats any $500 AI course this year

Bookmark it and watch today

Then read the "Harness, Loops, Graphs" guide below - the closed loop is the harness ↓

[seeco @seeconvm]

https://t.co/7KKkUgUSki

[gary @0xgary]

This is f*cking insane. Anthropic CEO Dario Amodei, the man building this AI:

AI could erase half of all entry-level white-collar jobs in the next 1-5 years

Entry-level lawyers, consultants and finance professionals are among the first in line

He says it on camera, with a straight face, no sugarcoating

Chatbots → Agents → AI Employees → Whole Departments Run by AI

The people still standing won't be the smartest ones in the room. They'll be the ones running the agents

Beats any $3,000 AI career course

Bookmark it and watch today

Then read the "Harness, Loops, Graphs" guide below - that's how you end up running them ↓

[gary @0xgary]

This is f*cking insane. Anthropic CEO Dario Amodei, the man building this AI:

AI could erase half of all entry-level white-collar jobs in the next 1-5 years

Entry-level lawyers, consultants and finance professionals are among the first in line

He says it on camera, with a straight face, no sugarcoating

Chatbots → Agents → AI Employees → Whole Departments Run by AI

The people still standing won't be the smartest ones in the room. They'll be the ones running the agents

Beats any $3,000 AI career course

Bookmark it and watch today

Then read the "Harness, Loops, Graphs" guide below - that's how you end up running them ↓

[seeco @seeconvm]

https://t.co/7KKkUgUSki

[gary @0xgary]

This is f*cking insane. Nvidia founder and CEO Jensen Huang:

"Nobody writes prompts anymore

The new job is building loops and graphs

The engineers who stopped prompting are already years ahead, and the rest will end up working for them"

In this 50-minute talk, Jensen explains why prompting is over and what the best engineers are building instead

Prompts → Agents → Loops → Graphs → AI Workforce

Using AI doesn't mean writing better prompts into a chatbot

It means loops that do the work, and graphs that run the loops without you

95% of people are still polishing prompts, the 5% who build loops and graphs will run everything

Worth more than any $2,000 AI course

You probably think you don't have 50 minutes right now

Don't let this vanish from your feed

Bookmark and watch it today

Then read the full harness engineering guide below before everyone catches up ↓

[gary @0xgary]

This is f*cking insane. Nvidia founder and CEO Jensen Huang:

"Nobody writes prompts anymore

The new job is building loops and graphs

The engineers who stopped prompting are already years ahead, and the rest will end up working for them"

In this 50-minute talk, Jensen explains why prompting is over and what the best engineers are building instead

Prompts → Agents → Loops → Graphs → AI Workforce

Using AI doesn't mean writing better prompts into a chatbot

It means loops that do the work, and graphs that run the loops without you

95% of people are still polishing prompts, the 5% who build loops and graphs will run everything

Worth more than any $2,000 AI course

You probably think you don't have 50 minutes right now

Don't let this vanish from your feed

Bookmark and watch it today

Then read the full harness engineering guide below before everyone catches up ↓

[seeco @seeconvm]

https://t.co/7KKkUgUSki

[gary @0xgary]

This is f*cking insane. Anthropic engineer:

"You're not supposed to prompt Opus 5.5

You're supposed to build a system that prompts itself. At Anthropic, 90% of our engineers have already built these systems"

In this 30-minute talk, she shows exactly how Anthropic builds agents that remember, fix their own mistakes and get sharper with every run

Prompt → Agent → Memory → Self-Correction → System That Improves Itself

Prompting is a skill. Building systems that prompt themselves is leverage

Your prompts stay the same tomorrow. Her agents get better every run

95% of people are still rewriting prompts by hand, the 5% who build self-improving systems will run everything

Worth more than any $2,000 agent course

Bookmark it and watch tonight

Then read the harness engineering guide below ↓

[gary @0xgary]

This is f*cking insane. Anthropic engineer:

"You're not supposed to prompt Opus 5.5

You're supposed to build a system that prompts itself. At Anthropic, 90% of our engineers have already built these systems"

In this 30-minute talk, she shows exactly how Anthropic builds agents that remember, fix their own mistakes and get sharper with every run

Prompt → Agent → Memory → Self-Correction → System That Improves Itself

Prompting is a skill. Building systems that prompt themselves is leverage

Your prompts stay the same tomorrow. Her agents get better every run

95% of people are still rewriting prompts by hand, the 5% who build self-improving systems will run everything

Worth more than any $2,000 agent course

Bookmark it and watch tonight

Then read the harness engineering guide below ↓

[seeco @seeconvm]

https://t.co/7KKkUgUSki