Doctors are not asking for integration of alternative medicine into the standard of care. Patients are not asking for integration of alternative medicine into the standard of care. The public is not asking for integration of alternative medicine into the standard of care. The only people asking for integrative medicine are alternative medicine practitioners, their promoters and sympathizers for survival and business opportunities. The only way alternative medicine can survive into the distant future is by integration into standard medical care and these quacks know it. Don't fall for this nonsense.
The AI Engineering community is getting stronger every week!
Today, we had an amazing audience of software engineers looking to transition to AI.
I am honoured to be a part of their journey.
Cheers!
12 days to launch the AI Engineering Cohort Website.
Registrations will start on 31st January 2026.
The cohort will start on 28th February 2026.
Main topics:
Week 0. Setup + Core Math
Week 1. Terminology + MNIST
Week 2. Basics of LLMs: Tokenization, Vectorization, Attention
Week 3. Deep dive into LLMs: QKV matrices, Cross + Self + MH Attention
Week 4. LLM Coding: Causal Masking + Code GPT
Week 5. Think like an engineer: How massive models are trained to production
Week 6. Optimization Hacks: KV Caching, Quantization, LoRA
Week 7. The RAG Problem: What is RAG, Chunking, Reranking, Vector DBs
Week 8. The RAG Code: Safety + Guardrails, Code RAG
Week 9. AI Agents: ReAct Pattern, Tool Calling, LangChain, LangGraph
Week 10. Context Engineering: Memory Systems, MCP, Multi-Agents
Week 11. AI Engineering: Evals, Tradeoffs, Fine-tuning vs. RAG vs Prompting
Week 12. Thinking Models: Reasoning, Chain of Thought
Week 13. Multi-modal Models: Images + Video, CLIP, Diffusion Models
Week 14. Capstone Project: Build your own AI Project
Week 15. Career Goals: How to move to AI Engineering
----------------
Primary Audience: Software / AI Engineers
Number of Sessions: 32 Live Classes + 15 General Sessions
Involves Coding: Yes
Classes: Live
Tentative pricing: ₹1,20,000 / $1400
----------------
This cohort is for working professionals looking to gain job-relevant AI capabilities. The official website will be ready soon. We are working out the final details now.
We wish you an amazing year ahead.
Cheers!
How to write effective Claude Skills.
1. Add triggers (when should a skill fire) to the skill description.
2. Build a gotchas list. "This field is @request_id in the gateway and trace_id in billing. Same value."
3. Use the filesystem for progressive disclosure. Skill md -> references.
4. Give it scripts. Helper functions to avoid writing boilerplate.
5. Don't state the obvious. Claude will use code and search when needed. You needn't make everything explicit.
Engineers building agent workflows can go deeper on skills, MCP, and Claude Code at https://t.co/lsqvTnoxvE.
Cheers!
Source: https://t.co/eSidqSabc9
My first lightning talk on Maven.
It's reached third place. Thank you for the support 😁
If you are a software engineer, you will find this session useful.
Date: 20th June 2026
Time: 9:00 PM IST, Saturday
Link: https://t.co/jipSdOWbYd
Valuable lessons by Karthik Ramgopal (Distinguished Engineer at LinkedIn).
1. AI should only be used for tasks that can be done manually.
If you cannot do the task yourself, you can't validate, guardrail, or eval the output.
To make a reliable system, we need AI output to mimic human output.
2. Developer productivity is up. Getting a job is difficult.
The engineers most at risk are those who treat AI as a black box.
They skip the fundamentals (context engineering, retrieval, evals) and lose the ability to judge whether the work is right or wrong.
Strong fundamentals and knowing how to harness AI are essential. I really feel like plugging in my cohort here, but I will resist the temptation :p
3. Both juniors and seniors are learning AI together. We are all on the same boat.
Juniors entering the workforce are AI-native by default. Seniors carry years of real-world judgment but are ossified into old habits.
Drop the ego. Let the learning flow.
1. Transformers
1.1 Tokens
1.2 Vectors
1.3 Attention
2. Retrieval Augmented Generation
2.1 Chunking
2.2 Vector Databases
2.3 Query Rewriting
2.4 Chunk reranking
3. Agents
3.1 Short-term and long-term memory
3.2 Tool use
3.3 MCP
3.4 Orchestration
4. Evals
4.1 Manual Evals
4.2 LLM as a Judge
-------------------------------
If you are looking to transition into an FDE or AI engineer role, join the AI Engineering cohort here:
https://t.co/lsqvTnoxvE
Cheers!
Mastering RAG-based systems for software engineers.
Date: 20th June 2026
Day & Time: Saturday, 9 PM
If you are a software engineer, you will find this talk useful.
Register here: https://t.co/jipSdOWbYd
I see @veritasium has created a video on the Google Maps algorithm.
https://t.co/5SjFs9Mx8h
Here is my video:
https://t.co/4kRjNbNxdg
What do you prefer?