THE CEO OF ANTHROPIC WAS ASKED WHAT A KID FINISHING HIGH SCHOOL SHOULD DO RIGHT NOW.
He didn't sugarcoat it.
"AI can already do the job of a junior lawyer. A junior financial analyst. A junior consultant."
"It will eliminate jobs. Probably a lot of them."
Then he gave his advice in one sentence:
"Learn to use AI."
Not a coding bootcamp. Not another degree. Learn to direct the thing that's replacing the junior roles.
14 free places to start today:
1. Anthropic's interactive prompting tutorial
github.com/anthropics/prompt…
2. Anthropic courses, from your first prompt to agents
github.com/anthropics/course…
3. Anthropic cookbook, recipes you can copy today
github.com/anthropics/anthro…
4. Microsoft generative AI for beginners, 21 lessons
github.com/microsoft/generat…
5. Microsoft AI agents for beginners
github.com/microsoft/ai-agen…
6. Hugging Face agents course, free with a certificate
github.com/huggingface/agent…
7. Google's hands-on generative AI notebooks
github.com/GoogleCloudPlatfo…
8. OpenAI cookbook, code for every common task
github.com/openai/openai-coo…
9. The prompt engineering guide everyone shares
github.com/dair-ai/Prompt-En…
10. Karpathy's neural networks zero to hero
github.com/karpathy/nn-zero-…
11. CrewAI, run your own team of AI workers
github.com/crewAIInc/crewAI
12. Microsoft AutoGen, multiple agents on one task
github.com/microsoft/autogen
13. Awesome LLM apps, hundreds of real projects
github.com/Shubhamsaboo/awes…
14. DeepLearning.AI short courses, one hour each
deeplearning.ai/short-course…
Total cost: $0.
You don't need another year of school to learn this. You need to start telling AI what to do.
The junior seat is changing fast. The people who learn this now won't be competing with AI for it. They'll be the ones running it.
Send this to someone graduating this year, then read the harness guide below ↓
Vlad retweeted
This Anthropic MCP paper is f*cking gold
Anthropic's engineers cut an agent's tool context from 150,000 tokens to 2,000. Same tools, same task. And the model wasn't the upgrade.
The upgrade: the agent stops calling tools and starts writing code that calls them.
tools → files → code → filter → answer
The 6 parts of code mode:
Part 1 → tools as files
Every MCP tool becomes a .ts file in ./servers.
The agent lists the folder and opens only what it needs.
Part 2 → load on demand
150,000 tokens of tool definitions down to 2,000.
A 98.7% saving in time and cost.
Part 3 → filter in code
A 10,000-row sheet gets filtered in the sandbox.
The model sees 5 rows.
Part 4 → loops in code
Polling Slack for "deployment complete" runs as a while loop.
No round trip through the model on every check.
Part 5 → private by default
Emails and phones turn into [EMAIL_1] and [PHONE_1] before the model sees them.
The real data still lands in Salesforce.
Part 6 → skills
Working code gets saved to ./skills with a SKILL.md.
The agent builds its own toolbox.
An agent that loads every tool burns its context before you ask anything. An agent that writes code opens 2 files.
I packed all 6 parts into one prompt. Drop it into Claude Code and it sets code mode up for you.
6 parts. 1 prompt. 98.7% fewer tokens.
Then read the enhanced edition of agent engineering below ↓
This is the entire OpenBot dev team. All three of them.
3813 PRs merged since August 13. New releases almost every day.
If you’ve ever updated OpenBot twice in one day, now you know who to blame.
@norbertbodziony @norbert_adamus @Sn13zka
Vlad retweeted
ok this paper is f*cking insane
Chinese researchers just put out a paper with a title that should make every agent framework nervous: "The End of Harness Engineering"
the argument fits in one line: hand-writing the program around the model is finished as a skill
a harness written by a person is one guess about one task on one afternoon
it ships, then runs for months unread and unscored
a harness written by the loop is a file that grades itself
a small 4B model reads what failed and proposes 8 edits
only the edit that scores best on held-out questions survives
the big model stays frozen the whole time
put Claude Fable 5.2 in that seat and every round rewrites the harness around it
so the human job shrinks to one artifact: the scoring set, the questions the harness gets graded on
frameworks turn disposable, and the exam becomes the job
the whole paper in one line: write the exam before the code
the builder's guide to the harness this loop starts from is below ↓
Vlad retweeted
🇺🇸 Microsoft just showed 60,000 employees the exit door... and asked them nicely to walk through it.
The company is offering voluntary buyouts to workers in the U.S., Canada, India and the UK, all the way up to vice president level.
That's about 27% of its entire workforce of 223,000.
Meanwhile, its spending on AI data centers is expected to top $50 BILLION in a single quarter, up from $34.9 billion a year ago.
The servers are getting the raise, the humans are getting the buyout.
Source: CNBC / Writer: Julie
This is f*cking insane. SpaceXAI senior engineer (ex-Cursor):
"99% of people open one GrokBot, ask it a question and close the tab
I run 50+ GrokBot agents like a company. A Chief of Staff runs my day, 3 PMs hand out the work, 40+ workers ship it overnight, and I just check the results over coffee. That team does the job of 20 engineers"
In this 1-hour workshop, SpaceXAI builds that GrokBot team from scratch, step by step
GrokBot → Chief of Staff → PMs → 40+ Workers → Autonomous Company
At SpaceXAI, 97% of engineers already run a team like this, and the ones who do are getting $750K+ offers. The rest are about to compete with them
Worth more than any $5,000 agentic engineering course
Bookmark it and watch today
Then read how to build your own team of GrokBot agents in the harness engineering guide below ↓
Vlad retweeted
10 GitHub repositories to learn the Agentic AI concepts you need before 2027 👇
1- Harness Engineering
github.com/walkinglabs/aweso…
2- Loop Engineering
github.com/cobusgreyling/loo…
3- Context Engineering
github.com/yzfly/awesome-con…
4- Tool Design & MCP
github.com/modelcontextproto…
5- Agent Memory
github.com/mnemoverse/awesom…
6- Agent Orchestration
github.com/vivy-yi/awesome-a…
7- AI Guardrails
github.com/enguard-ai/awesom…
8- Agent Evals
github.com/benchflow-ai/awes…
9- Human-in-the-Loop
github.com/cloudflare/agents
10- Agent Observability
github.com/anhermon/awesome-…
These cover the production side of agentic AI:
→ Harness
→ Loops
→ Context
→ Tools
→ Memory
→ Orchestration
→ Guardrails
→ Evals
→ Human oversight
→ Observability
✅ Save this for your Agentic AI learning journey.
Join the tech community for more resources:
whatsapp.com/channel/0029Va9…
Follow for more developer resources, AI tools, interview prep, jobs & opportunities.
Vlad retweeted
One of my friend makes $1.2 million a year as an Anthropic engineer.
I asked him how he learned prompting so well. He sent me a video that was never supposed to get out. Their core team's prompting playbook.
You won’t find anything better about prompting than this 30 minutes video.
I watched it last night. Halfway through, I realized I've been using Claude completely wrong for two years.
Watch it, then read the article below.
Vlad retweeted
🇮🇶🇸🇾 Iraq's workaround for the Strait of Hormuz is to full-send tanker trucks packed with oil over the border into Syria towards Mediterranean ports
And it looks fking insane
Writer: Ian
Readers added context they thought people might want to know
This appears to be an AI generated video, with an implausibly sideways car at the end and more trucks than are likely available for this route.
The roads look somewhat different:
bloomberg.com/news/articles/…
Vlad retweeted
🇷🇺 He shoved the store robot, then the robot came for him.
It wasn't a cute glitch or a stumble, the staff LITERALLY had to grab it and drag it down while it kept moving.
This kind of clip used to be funny... now its not.
Writer: Val
Vlad retweeted
Andrew Ng just released a 2-hour course on full Graph Engineering.
How to go from one prompt to 100 agents that loop, improve themselves, and run without you:
0% → 09:14 - build your first AI agent
25% → 33:11 - run agents with loop engineering
50% → 1:02:46 - turn agent loops into graphs
75% → 1:30:15 - build agents that rewrite themselves
100% → 1:49:05 - run the entire graph system without you
Most people are still building one agent and calling it done.
Andrew Ng is already teaching what comes next:
Prompt → Agents → Loops → Graphs → Self-Improving Systems
Single agents are the old workflow.
Systems that improve and run without you are the next one.
This 2-hour course is worth more than most $500 agent engineering courses.
Bookmark it and watch before everyone starts catching up.
Then read how to run 1,000 agents from one prompt below ↓
a community member built a fully private research portal, and the engine inside it is a headless Hermes Agent (we love it!)
type a query into a local web UI, and behind it a Hermes run does the whole research pass:
searching, fetching and crawling through a MCP server , then writing you a dated, styled HTML report. everything stays yours.
this is my favorite thing about Hermes Agent: it runs headless inside other software just as happily as it chats with you.
github.com/rpmalouin/AI-Rese…
Vlad retweeted
🚨 JD VANCE DECLARES THEY’RE ENDING THE DOLLAR AS RESERVE CURRENCY
JD Vance just confirmed it: the dollar’s global status is over because it lets Americans “consume too cheaply.”
This is not a casual statement to be made.
Every crisis was financially engineered to force the new system, just like 1971 when they killed gold convertibility. Even the COVID money printing came when the U.S. Repo market was about to collapse in 2019.
JP Morgan CEO warned that U.S. dollar will no longer be a reserve currency within the next 25 years.
China’s been on a massive gold-buying spree. Every central bank is doing the same. South Korea just started buying gold after 13 years.
Japan is the biggest threat.
BoJ’s Yuto apologized for the measures being prepared. The BoJ and finance minister threatened of bold actions to save the yen.
Then Boom, the US Treasury intervened and effectively took control of BoJ operations to stop Japan dumping its $1.4T in Treasuries, which would collapse the entire US debt market and trigger a global liquidity crisis.
Scott Bessent even warned the Fed: expand the FIMA facility for Japan… or watch the U.S. Treasuries implode.
Central banks, IMF, BIS and the biggest financial institutions engineer the financial crisis to get out of the mess they made.
Fiat Money is next.
Vlad retweeted
Anthropic just released a 4-hour course to getting a $500k AI engineering job:
00:15 - The right way to prompt Claude
33:21 - What makes Claude act dumber on your code
01:33:39 - How Anthropic use Claude every day
02:50:56 - The fix that makes Claude way smarter This
4-hour Anthropic free course replaces about 10 paid engineering courses.
Watch it today, then read the step-by-step guide on building loops below.
Vlad retweeted
Andrej Karpathy spent 8 years working at OpenAI and Tesla
Last week, he condensed everything he knows into one free 2-hour lecture
People spend $15K on bootcamps that teach less than half of this
You probably don't have two hours to watch it right now
Just don't let it disappear in your feed
Save it, watch it later, then read the guide below and build your first loop
Ilya Sutskever:
“My document gently flowed to where AI is today - and agents are the future”
He wrote the paper that made LLMs like Claude and ChatGPT possible - and explains it from scratch in 20 minutes
Never touched AI or use it every day - you need to watch this course
Watch - bookmark, then put the entire lecture into practice with the article below ↓
Vlad retweeted
A Chinese developer just explained the shift from Loop Engineering to Graph Engineering better than anyone.
most people are still building agents the way that's about to be obsolete.
> why single-agent loops break and go "goal blind"
> the 4 parts of a graph: nodes, edges, state, policy
> 3 topologies that run everything: diamond, supervisor, pipeline
> Anthropic's 5 official workflow patterns
the punchline: it's not how many agents you run. it's the determinism you build with verifiers, code fallbacks, and reality anchors.
I broke the same architecture down with Kimi K3. Full A-Z guide below.
Vlad retweeted
This is the best 2 hours on graph engineering ever recorded, Andrew Ng breaking down how to build agentic knowledge graphs from scratch:
9:14 - your first working agent
33:11 - how loops actually work
1:02:46 - turning loops into working graphs
1:30:15 - agents that improve their own code
1:49:05 - a system that runs the whole thing for you
I've seen $500 courses that teach less than this video alone.
Watch it, then take it further with my step-by-step guide on graph engineering below.





































