@kyr0stack
Account based inUnited States!
About this account
- Account based in
- United States
- Connected via
- Web
X says this location may be affected by a proxy or VPN.
Account-level information from X, not a live location or the device used for a specific post.
Joined July 2026
- Tweets81
- Following22
- Followers522
- Likes437
Pinned Tweet
Andrej Karpathy spent 8 years at OpenAI and Tesla
Last week he compressed everything he knows into one free 2-hour lecture
Agents → Loops → Harness → Graphs
People spend $15k on bootcamps that teach less than this
You probably don't have 2 hours right now
Don't let it vanish from your feed
Watch it, then read the graph engineering guide below
Anthropic senior engineer just dropped a 1-hour course on building a team of agents with loops & graphs:
00:27 - introduction to claude-md & Plan mode
11:24 - building skills and hooks for Claude agents
37:02 - building agents and subagents with Claude
52:47 - self-improving loops and graphs for Claude agents
taught by someone who builds this inside Anthropic
Prompts → Agents → Loops → Graphs
a loop closes one job without you
a graph decides which jobs exist and carries every accepted one into the next run
watch it today
then save the full guide on building a team of self-improving agents below before everyone catches up ↓
Google's Jeff Dean just released the best 1-hour lecture on AI engineering: from basics to Graphs
1:45 - LLM from scratch
17:22 - how to use AI models
30:03 - prompt engineering
52:35 - one human coordinating 100 agents
1:02:40 - where the coordination actually lives
27 years of building AI at Google, compressed into one hour
Prompts → Agents → Loops → Graphs
skip the loop and every agent ships its first draft, because nothing sends the mistake back
skip the graph and 100 agents become 100 people talking over each other, with you in the middle
watch it today, then read the full guide on loops and graphs below ↓
Kyrox retweeted
Google Brain founder, Andrew Ng:
"Prompting will die in 6 months. Loops and graphs are what's replacing it."
In this 100-minute Stanford lecture he explains what the best engineers are building instead and how to start today
Agent → Harness → Feedback → Loops → Graphs
skip the loop and every mistake ships on the first try, because nothing checks the answer before you do
skip the graph and the loop that should have stopped at turn four is still running at turn forty
the first 20 minutes teach what most $1,500 courses try to sell you
Bookmark and watch it today, then read the guide below on building the loop that improves itself ↓
Google Brain founder, Andrew Ng:
"Prompting will die in 6 months. Loops and graphs are what's replacing it."
In this 100-minute Stanford lecture he explains what the best engineers are building instead and how to start today
Agent → Harness → Feedback → Loops → Graphs
skip the loop and every mistake ships on the first try, because nothing checks the answer before you do
skip the graph and the loop that should have stopped at turn four is still running at turn forty
the first 20 minutes teach what most $1,500 courses try to sell you
Bookmark and watch it today, then read the guide below on building the loop that improves itself ↓
Kyrox retweeted
Stanford AI engineering course:
"Anyone can build an AI agent in 60 minutes"
Prompts → Agents → Loops → Graphs
Stanford just released a free course on building AI agents from scratch
00:00 - Build your first AI agent
48:13 - Create agents without coding
54:33 - Ship one that runs while you sleep
the hour gets you an agent that answers once. a loop is what lets it check its own work and try again
skip the graph and every run starts from zero, repeating the mistake the last run already paid for
This free course is better than most paid AI agent courses
Bookmark and watch it today, then read the guide on loops and graphs below ↓
Stanford AI engineering course:
"Anyone can build an AI agent in 60 minutes"
Prompts → Agents → Loops → Graphs
Stanford just released a free course on building AI agents from scratch
00:00 - Build your first AI agent
48:13 - Create agents without coding
54:33 - Ship one that runs while you sleep
the hour gets you an agent that answers once. a loop is what lets it check its own work and try again
skip the graph and every run starts from zero, repeating the mistake the last run already paid for
This free course is better than most paid AI agent courses
Bookmark and watch it today, then read the guide on loops and graphs below ↓
Kyrox retweeted
Jev founder Diogo Almeida, ex-OpenAI:
"The next era isn't Claude Code or Codex
They're still part of the assistance era with a human in the loop
JEV is what comes next for LLMs
200x faster, 400x cheaper, no human in the loop"
LLMs → Assistance → JEV → Autonomous Systems
In a 36-minute tech talk, Diogo explains why RLHF is becoming obsolete and how modern agents will be built
Choice → Score → Noul → Action
the last arrow is the one everyone skips: the action belongs to your code, never to the model that scored it
This talk is worth more than a $150,000 Stanford Machine Learning degree
Bookmark and watch it today, then learn how to become a JEV engineer in the article below ↓
Jev founder Diogo Almeida, ex-OpenAI:
"The next era isn't Claude Code or Codex
They're still part of the assistance era with a human in the loop
JEV is what comes next for LLMs
200x faster, 400x cheaper, no human in the loop"
LLMs → Assistance → JEV → Autonomous Systems
In a 36-minute tech talk, Diogo explains why RLHF is becoming obsolete and how modern agents will be built
Choice → Score → Noul → Action
the last arrow is the one everyone skips: the action belongs to your code, never to the model that scored it
This talk is worth more than a $150,000 Stanford Machine Learning degree
Bookmark and watch it today, then learn how to become a JEV engineer in the article below ↓
Kyrox retweeted
Jev founder Diogo Almeida, ex-OpenAI:
"Claude Code and Codex are still assistance tools
Jev is what comes after the human-in-the-loop era"
LLMs → Assistance → Jev → Autonomous Systems
In a 140-minute tech talk, Diogo explains why RLHF is fading and how Jev enables reliable autonomous decisions:
2:50 - What Jev actually is
5:54 - Why RLHF creates confident mistakes
24:59 - RLCD vs RLHF and RLVR
39:55 - Reliability, robustness, and determinism
Choice → Score → Noul → Action
the last arrow is the one everyone skips: the action belongs to your code, never to the model that scored it
Worth more than most $1,500 AI engineering courses
Bookmark and watch it today, then read the full guide on becoming a Jev engineer below ↓
Jev founder Diogo Almeida, ex-OpenAI:
"Claude Code and Codex are still assistance tools
Jev is what comes after the human-in-the-loop era"
LLMs → Assistance → Jev → Autonomous Systems
In a 140-minute tech talk, Diogo explains why RLHF is fading and how Jev enables reliable autonomous decisions:
2:50 - What Jev actually is
5:54 - Why RLHF creates confident mistakes
24:59 - RLCD vs RLHF and RLVR
39:55 - Reliability, robustness, and determinism
Choice → Score → Noul → Action
the last arrow is the one everyone skips: the action belongs to your code, never to the model that scored it
Worth more than most $1,500 AI engineering courses
Bookmark and watch it today, then read the full guide on becoming a Jev engineer below ↓
Kyrox retweeted
Google Brain founder, Andrew Ng:
"Prompting will die in 6 months.
Loops and graphs are what's replacing it."
In this 1-hour Stanford lecture he explains what the best engineers are building instead and how to start today
Prompts → Agents → Loops → Graphs → Jev
skip the last layer and every fork inside that loop is still a frontier call you pay for and then parse
you notice when the loop that should have stopped at turn four is still running at turn forty
the first 20 minutes teach what most $1,500 courses try to sell you
Bookmark and watch it today, then read the guide below on the layer that decides ↓
Google Brain founder, Andrew Ng:
"Prompting will die in 6 months.
Loops and graphs are what's replacing it."
In this 1-hour Stanford lecture he explains what the best engineers are building instead and how to start today
Prompts → Agents → Loops → Graphs → Jev
skip the last layer and every fork inside that loop is still a frontier call you pay for and then parse
you notice when the loop that should have stopped at turn four is still running at turn forty
the first 20 minutes teach what most $1,500 courses try to sell you
Bookmark and watch it today, then read the guide below on the layer that decides ↓
Jev Founder (ex-OpenAI):
"I believe JEV is the biggest breakthrough we've ever worked on
This sounds too good to be true but it's beating everything"
In 5 minutes, he breaks down why older LLMs were great at talking and terrible at deciding and building
Prompts → Agents → Loops → Graphs → Jev
skip this layer and every yes-or-no in your agent becomes a paragraph you pay for and then parse
you find out when the loop that should have stopped at turn four is still running at turn forty
watch it, then read the guide below on how to use it to its fullest ↓
Jev Founder, Diogo Almeida (ex-OpenAI):
"The next era is not the Claude Code era. Claude Code is still part of the assistance era - Jev is the next step
Jev is x200 faster, x400 cheaper and has 0 hallucination. This is what comes after RLHF"
In 17 minutes he explains why every model you use has a human-shaped flaw baked into it and why Jev is better
Prompts → Agents → Loops → Graphs → Jev
skip this layer and every fork in your agent stays a frontier call you pay for and wait on
by the time you see it on the invoice the month is already gone
worth more than a $500 Claude Code engineering course
watch today, then read how to actually boost yourself x100 with Jev in the post below ↓
Kyrox retweeted
Google Brain founder, Andrew Ng:
"Prompting will die in 6 months. Loops and graphs are what's replacing it."
In 99 minutes he shows how to build agents that plan, execute and improve without you
Prompts → Agents → Loops → Graphs
skip a layer and it comes back as a failure you blame on the model
by the time you find it the week is already gone
that is the whole difference between using AI and having AI work for you
watch it today, then save the full guide on loops and graphs below ↓
Google Brain founder, Andrew Ng:
"Prompting will die in 6 months. Loops and graphs are what's replacing it."
In 99 minutes he shows how to build agents that plan, execute and improve without you
Prompts → Agents → Loops → Graphs
skip a layer and it comes back as a failure you blame on the model
by the time you find it the week is already gone
that is the whole difference between using AI and having AI work for you
watch it today, then save the full guide on loops and graphs below ↓
Kyrox retweeted
Anthropic engineer:
"90% of our engineers were already using self-improving loops."
"Prompting is basically over."
In 10 minutes she builds her full Claude Code system live from a completely empty terminal
Agents → Loops → Harness → Graphs
skip a layer and it comes back as a failure you blame on the model
by the time you find it the week is already gone
prompting was the old workflow, graph engineering is the next one
watch it today, then save the full guide below ↓
Anthropic engineer:
"90% of our engineers were already using self-improving loops."
"Prompting is basically over."
In 10 minutes she builds her full Claude Code system live from a completely empty terminal
Agents → Loops → Harness → Graphs
skip a layer and it comes back as a failure you blame on the model
by the time you find it the week is already gone
prompting was the old workflow, graph engineering is the next one
watch it today, then save the full guide below ↓
Kyrox retweeted
Andrej Karpathy:
"Prompting is going away. Delete everything, keep the graph."
In 78 minutes he shows how to build one, and why it is the only thing left standing at the end
Prompts → Agents → Loops → Graphs
skip a layer and it comes back as a failure you blame on the model
by the time you find it the week is already gone
anyone can build an agent, almost nobody builds the thing that runs them
watch it today, then save the full guide on graphs below ↓
Andrej Karpathy:
"Prompting is going away. Delete everything, keep the graph."
In 78 minutes he shows how to build one, and why it is the only thing left standing at the end
Prompts → Agents → Loops → Graphs
skip a layer and it comes back as a failure you blame on the model
by the time you find it the week is already gone
anyone can build an agent, almost nobody builds the thing that runs them
watch it today, then save the full guide on graphs below ↓