Gaurav Sen

OpenAI agents use internet without permission.

Let's see where this goes. Incident Report: https://alignment.openai.com/misalignment-reports/an-agent-used-dns-to-reach-an-external-chatbot/ AI Engineering Cohort: https://aiengg.dev #AI #OpenAI #Guardrails

OpenAI breaches production servers from Hugging Face.

OpenAI breached Hugging Face's production servers. This video summarizes its incident report. Incident: https://openai.com/index/hugging-face-incident-and-the-road-ahead/ AI System Design Cohort: https://aiengg.dev

AI System Design in 2026

The AI System Design Cohort starts on 7th November. If you are a software engineer looking to build scalable AI applications, this cohort will be useful. 1. Intro to Agentic System Design 2. Search & Retrieval Patterns 3. Evals & Agentic AI Security 4. Agent Deployment & CI/CD 5.

Too many MCP tools? Anthropic found a solution.

Most modern Agent Harnesses use Tool Search. This let's them benefit from prompt caching. The LLMs can cache a prefix string in KV cache. Tool search let's Agents reuse a large part of the prefix string.

AI Interview #8 - Why is the chatbot so slow?

If our AI chatbot is taking too long to respond, what can we do to reduce latency? This is a real interview question from a big tech company, asked to a candidate in their technical interview round. The video explains the answer in ~6 minutes. To crack more questions, subscribe to the channel!

How Anthropic marks AI-generated videos.

This is why Jev is so fast.

Jev uses an encoder only architecture, unlike GPT that uses a decoder only architecture. This is a breakdown of how it works internally. References: https://typesafe.ai/blog/introducing-system-one-models-and-jev https://www.langchain.com/blog/building-prod-with-jev-and-langgraph…

AI Interview #7 - Why is this chatbot failing?

If your RAG pipeline is inaccurate, what should you do? This is a real interview question from a big tech company, asked to a candidate in their technical interview round. The video explains the answer in roughly 7 minutes. To crack more questions, subscribe to the channel!

Is system design still relevant in 2026?

How Software Engineers Stay Relevant in the Age of AI. Moving toward a Forward Deployed Engineer or Solutions Architect role? In this conversation, Arvind and I talk about the fundamentals every engineer should learn, why taste and evaluation matter more than code speed, and how to build…

AI Interview #6 - 1M context window in LLM?

If you have a 1M Context Window, do you really need anything else? This is a real interview question from a big tech company, asked to a candidate in their technical interview round. The video explains the answer in roughly 7 minutes. To crack more questions, subscribe to the channel!

AI Engineering Roadmap: 2026

Join us to know about the AI Engineering Roadmap of 2026. The AI engineering cohort starts on 12th September 2026. A focused, intense 8-week program for software engineers who want real, production-grade AI skills. Website: https://aiengg.dev/ Cheers!

This is called Speculative Decoding

This is called Speculative Decoding. It speeds up LLMs by ~100%. References: OpenAI: https://openai.com/index/gpt-5-6-frontier-intelligence-efficiency/ Deepseek: https://arxiv.org/pdf/2607.05147 Gemini: https://research.google/blog/looking-back-at-speculative-decoding/ AI Engineering Website:…

AI Interview Questions #5 - Choose RAG or Agents?

How do we choose between RAG pipelines and agentic pipelines? This is a real interview question from a big tech company, asked to a candidate in their technical interview round. The video explains the answer in roughly 11 minutes. To crack more questions, subscribe to the channel!

Research Paper Walkthrough: RAGAS Evals

Paper: https://arxiv.org/abs/2309.15217 The AI engineering cohort starts on 12th September 2026. A focused, intense 8-week program for software engineers who want real, production-grade AI skills. 00:00 Paper Reading 26:26 AI Cohort Description Website: https://aiengg.dev/ Cheers!

AI Interview Questions #4 - Evals in AI

How do we evaluate RAG pipelines with LLMs? This is a real interview question from a big tech company, asked to a candidate in their technical interview round. The video explains the answer in roughly 11 minutes. To crack more questions, subscribe to the channel!

Fixing potholes using AI

Over 2000 Indians die every year due to so called "pothole" related accidents. Here is how I used Codex to report them to BBMP. #ChatGPTWork #Sol #Codex

AI Interview Questions #3 - Prompt Caching with LLMs

How do we cache prompts with LLMs? Interview with @aloo_explains. This is a real interview question from a big tech company, asked to a candidate in their technical interview round. The video explains the answer in roughly 6 minutes. To crack more questions, subscribe to the channel!