Techpreneur
Ranchi, India
Joined October 2013
- Tweets1.3K
- Following305
- Followers82
- Likes724
ABHISHEK SINHA retweeted
Anthropic engineer (ex-Google):
"I spent 14 years at Google and built 24 reusable skills for agents that I can use with any AI model
So I stopped prompting my agents from scratch. The repo has already reached ~100K stars on GitHub"
In a 40-min masterclass, Addy Osmani showed exactly how he uses his skills (~100K stars on GitHub) for his 24/7 multi-agent system
His workflow and this workshop will replace 15 hours of other paid videos on agent engineering
Watch it today, copy the GitHub repo - then read below how to use these skills for graphs ↓
ABHISHEK SINHA retweeted
STANFORD'S COMPLETE LLM COURSE IS FREE 📌
If you're serious about Generative AI, LLM Engineering, or Agentic AI, this is a great course to save.
COURSE OUTLINE
1. Transformers
youtube.com/watch?v=Ub3GoFaU…
2. Transformer-Based Models & Tricks
lnkd.in/gHTY27uH
3. Large Language Models
youtube.com/watch?v=Q5baLehv…
4. LLM Training
youtube.com/watch?v=VlA_jt_3…
5. LLM Tuning
lnkd.in/ga5tcchy
6. LLM Reasoning
lnkd.in/guBgZVRt
7. Agentic LLMs
youtube.com/watch?v=h-7S6HNq…
8. LLM Evaluation
youtube.com/watch?v=8fNP4N46…
9. Recap & Current Trends
youtube.com/watch?v=Q86qzJ1K…
OFFICIAL COURSE SYLLABUS
cme295.stanford.edu/syllabus…
The official Stanford syllabus confirms all 9 lectures and their topics, including RAG, tool calling, agents, LLM evaluation, RLHF, LoRA, reasoning, and current trends.
If you already know the basics, pay extra attention to:
Lecture 7 → Agentic LLMs
Lecture 8 → LLM Evaluation
ABHISHEK SINHA 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 ↓
ABHISHEK SINHA retweeted
This is the best site on the internet to learn how LLMs actually work.
Free. Completely.
0xkato.xyz/how-llms-actually…
Bookmark this site.
Then read this ↓
ABHISHEK SINHA retweeted
only engineers at Anthropic got to see this.
an internal AI engineering document leaked, it's saving solo devs $300,000 a year.
the shift it describes is simple, stop prompting, start building loops.
a loop doesn't need you, It generates a solution, evaluates the output, stores what worked, schedules what's next, optimizes from results, and runs the cycle again. No brief needed. No human in the middle. The system improves itself.
Generate → Evaluate → Remember → Schedule → Optimize → Recurse.
six layers. One loop. The human moves from operator to architect.
one person running this does the work of a team. The output compounds. Each cycle the system gets smarter.
that's exactly what Loops and Graphs are. Read the full breakdown below.
ABHISHEK SINHA retweeted
Google just dropped a 94-minute workshop
On moving AI systems from basic RAG to graph-based memory:
15:32 - Set up the production agent stack
28:00 - Turn disconnected data into a knowledge graph
41:00 - Build GraphRAG with semantic and hybrid search
58:00 - Extract graph context from images, text, and video
1:09:00 - Orchestrate specialized agents with Google ADK
1:20:00 - Give agents memory across sessions
Most teams are still stopping at RAG
Google is already teaching what comes next:
RAG → GraphRAG → Memory → Multimodal Agent Graphs
Built with Spanner Graph, Gemini, ADK, and Memory Bank
This workshop is worth more than most paid GraphRAG courses
Watch it today
Then read the full From RAG to Context Graphs roadmap below ↓
ABHISHEK SINHA retweeted
Don't waste 2 years learning to become an AI agentic engineer in 2026.
Andrew Ng, the godfather of AI, gave the complete playbook to become one from scratch.
1 hour course. Free:
• 00:00 - AI agent basics
• 12:12 - AI Agentic workflows & design patterns
• 53:27 - Practical tips for building AI agents
• 1:20:30 - self-improving AI agent loops
• 1:30:19 - multi-agent AI systems
I watched it last night.
Halfway through, I realized I could get into Anthropic in weeks, not years.
Bookmark now. Watch it. Then build your own AI agent.
ABHISHEK SINHA retweeted
Anthropic engineer:
"At Anthropic, all of our engineers are running hundreds of agents.
The way you do it is Graph engineering."
In 30 minutes he shows how Anthropic runs hundreds of agents at once, and exactly how graph engineering makes it possible.
The missing piece most people skip: how to wire agents into a graph that self-corrects every run.
Watch it, then try your first graph with the step-by-step guide below
ABHISHEK SINHA retweeted
Anthropic engineer:
"The fastest way to make an agent better isn't a smarter model.
It's the right Loop and Graph around it."
In 1 hour she breaks down what agentic engineering looks like at Anthropic, and why it's nothing like what most people imagine.
The missing piece most people skip: a better model improves one run, a better loop improves every run.
Watch it, then read the full guide on loops and graphs below.
ABHISHEK SINHA retweeted
Ken Griffin built Citadel into $67B fund and hires PhDs out of Stanford and MIT. He watched agentic AI do their month work in an afternoon and admitted it sent him home depressed.
The interesting bit is what he was describing. A six-part research loop.
Find, code, test, deploy, autopsy, learn.
Five of those six are done. Free. Available tonight.
Prompt to backtested strategy in 12 seconds. Prompt to live broker in 90.
The Greenwich quant doing that same work costs $650,000 a year and clears one hypothesis a month.
The sixth exists nowhere. Not at Citadel, not at Man Group, not in any repo.
It's the part where the machine remembers what already failed.
Every losing test dies in a log file. The next agent starts blind. Negative results are the most valuable data in quant research and literally nobody stores them.
This loop broken down in my article below. Read it before someone builds the last one and stops explaining how.
ABHISHEK SINHA retweeted
Learn AI for free directly from top companies.
1 - Anthropic:
anthropic.skilljar.com
2 - Google:
grow.google/ai
3 - Meta:
ai.meta.com/resources/
4 - NVIDIA:
developer.nvidia.com/cuda
5 - Microsoft:
learn.microsoft.com/en-us/tr…
6 - OpenAI:
academy.openai.com
7 - IBM:
skillsbuild.org
8 - AWS:
skillbuilder.aws
9 - DeepLearning.AI:
deeplearning.ai
10 - Hugging Face:
huggingface.co/learn
Comment "Learning" if you find this helpful.
Repost so others can take help.
Must bookmark for future reference.
ABHISHEK SINHA retweeted
I just recorded the COMPLETE CLAUDE 3D WEB DESIGN Course
❤️🔥 Dedicate 1 hour to this. The COMPLETE Claude AI Design Course teaches you to DESIGN and BUILD ANY 3D Game or Website.
Those who watch it tonight will wake up tomorrow with a new skill.
Watch it and save it to your favorites now.
ABHISHEK SINHA retweeted
Sam Altman (CEO of OpenAI):
"You no longer need to write prompts."
In just 38 minutes, he explains how to use ChatGPT at a level that most people can't even imagine.
It's a talk he gave to Stanford students. A friend sent me the recording last night.
After watching it, I realized I was only taking advantage of about 15% of what this tool can really do.
Watch it in full and then read the guide I leave below on how to create a system that prompts itself.
Follow @AnishJaitwar for more
ABHISHEK SINHA retweeted
Google just released a free 2-hour course on full Graph Engineering.
How to go from one prompt to 100 agents running inside one graph:
17:44 - Build your first AI agent
39:30 - Run agents with loop engineering
1:12:38 - Turn agent loops into graphs
1:34:26 - Build agents that throttle themselves
1:55:05 - Orchestrate the full multi-agent system
Most people build one agent and stop there.
Google is teaching the full stack:
Prompt → Agents → Loops → Graphs → Multi-Agent Systems
Single agents are the old workflow.
Self-regulating agent graphs are the new one.
This 2-hour watch is worth more than most paid agent engineering courses.
Bookmark and watch it today
Then read the full architecture below ↓
ABHISHEK SINHA retweeted
Google Brain founder, Andrew Ng:
"Prompting will die in 6 months.
Loops and Graphs are what's replacing it."
In 2 hours, he shows exactly what the best engineers already build instead, and how to start building it yourself.
The missing piece most people skip: how to connect those loops into a graph that compounds every time it runs.
Watch it, then read the full guide on loops and graphs below.
One of the best innings ever 🙏🏻🇮🇳. Brilliant from @IamSanjuSamson 🇮🇳
Semi-final spot on the line, and the boys handled it beautifully!
Handling the final overs well in both innings gave us the edge. Sanju Samson’s calm presence at the crease was wonderful to watch. That kind of presence lifts a side.
Brilliant effort from everyone. On to the semi-finals! 🇮🇳
47
💯
You might see me criticising him, the government, or a policy tomorrow
But today, when some of the safest and most prosperous places in the world are being bombed, we can pause and acknowledge that
India is stable
India is safe
India is in fact growing
Navigating 1.4 billion people through a volatile world run by unpredictable mad men without dragging ourselves into chaos is a momentous task
Critique when needed,
Credit when due
And today, a moment to say thank you 🙏
32
Amazingly
A proud day for India!
Micron Technology’s Semiconductor ATMP facility was inaugurated in Sanand earlier today.
Here are some glimpses from the occasion…
@MicronTech
@MicronCEO
15