It is the season of lists, so I looked at AI through Santa’s ledger instead of another hype story. This year was anything but simple.
www.anup.io/ais-naughty-...
#AIengineering #LLM #AIethics
Happy holidays, everyone!
www.anup.io/ais-naughty-...
#AIengineering #LLM #AIethics
Happy holidays, everyone!
AI's Naughty and Nice List
AI's best and worst moments came from the same companies in 2025
www.anup.io
December 24, 2025 at 5:43 AM
It is the season of lists, so I looked at AI through Santa’s ledger instead of another hype story. This year was anything but simple.
www.anup.io/ais-naughty-...
#AIengineering #LLM #AIethics
Happy holidays, everyone!
www.anup.io/ais-naughty-...
#AIengineering #LLM #AIethics
Happy holidays, everyone!
The AI coding advice that works for someone else probably won't work for you. Not because they're wrong, but because the tools aren't stable enough for best practices yet.
www.anup.io/why-ai-codin...
#AIEngineering #LLMs #SoftwareDevelopment #AICoding
www.anup.io/why-ai-codin...
#AIEngineering #LLMs #SoftwareDevelopment #AICoding
Why AI Coding Advice Contradicts Itself
If you don't know what you're doing, AI fails with death by a thousand cuts.
www.anup.io
December 20, 2025 at 4:16 PM
The AI coding advice that works for someone else probably won't work for you. Not because they're wrong, but because the tools aren't stable enough for best practices yet.
www.anup.io/why-ai-codin...
#AIEngineering #LLMs #SoftwareDevelopment #AICoding
www.anup.io/why-ai-codin...
#AIEngineering #LLMs #SoftwareDevelopment #AICoding
Scaling RAG in production isn't an LLM problem. It's a systems problem wrapped around a language model.
www.anup.io/rag-at-scale...
www.anup.io/rag-at-scale...
What It Takes To Serve 10,000 Queries A Day | Anup Jadhav
This is about what naive RAG actually does, why it falls apart under load, what advanced RAG adds, and the engineering work that makes a system stable at ten thousand queries a day.
www.anup.io
November 24, 2025 at 5:41 AM
Scaling RAG in production isn't an LLM problem. It's a systems problem wrapped around a language model.
www.anup.io/rag-at-scale...
www.anup.io/rag-at-scale...
Imagine a UI generated on the fly for every query. That’s the idea behind Google’s Generative UI paper. I unpack the architecture, the prompt, and why this shift matters for agent-first applications.
www.anup.io/understandin...
www.anup.io/understandin...
Understanding Generative UI
A Layered Walkthrough of the Generative UI paper everyone is talking about
www.anup.io
November 20, 2025 at 8:00 AM
Imagine a UI generated on the fly for every query. That’s the idea behind Google’s Generative UI paper. I unpack the architecture, the prompt, and why this shift matters for agent-first applications.
www.anup.io/understandin...
www.anup.io/understandin...
Senior developers are better at using AI agents than junior developers.
Not because they code faster. Because they already know how to delegate, communicate clearly, and spot when something looks right but isn't.
People management = AI management.
www.anup.io/senior-devel...
Not because they code faster. Because they already know how to delegate, communicate clearly, and spot when something looks right but isn't.
People management = AI management.
www.anup.io/senior-devel...
November 13, 2025 at 1:15 PM
Senior developers are better at using AI agents than junior developers.
Not because they code faster. Because they already know how to delegate, communicate clearly, and spot when something looks right but isn't.
People management = AI management.
www.anup.io/senior-devel...
Not because they code faster. Because they already know how to delegate, communicate clearly, and spot when something looks right but isn't.
People management = AI management.
www.anup.io/senior-devel...
Reading time: 2–4 days.
Which, to be fair, is still faster than fine-tuning.
huggingface.co/spaces/Huggi...
Which, to be fair, is still faster than fine-tuning.
huggingface.co/spaces/Huggi...
November 1, 2025 at 9:12 PM
Reading time: 2–4 days.
Which, to be fair, is still faster than fine-tuning.
huggingface.co/spaces/Huggi...
Which, to be fair, is still faster than fine-tuning.
huggingface.co/spaces/Huggi...
Fine-tuning dropped from hottest trend to <10% of AI workloads in two years. Now it's coming back. Not as hype, but as the last 10% that actually matters.
Turns out some problems need you to teach the model your language, not just describe it in a prompt.
www.anup.io/fine-tuning-...
Turns out some problems need you to teach the model your language, not just describe it in a prompt.
www.anup.io/fine-tuning-...
Fine-Tuning makes a comeback
Fine-tuning went from the hottest thing in machine learning to accounting for less than 10% of AI workloads in just a couple of years. Teams figured out they could get 90% of the way there with prompt...
www.anup.io
October 29, 2025 at 11:12 AM
Fine-tuning dropped from hottest trend to <10% of AI workloads in two years. Now it's coming back. Not as hype, but as the last 10% that actually matters.
Turns out some problems need you to teach the model your language, not just describe it in a prompt.
www.anup.io/fine-tuning-...
Turns out some problems need you to teach the model your language, not just describe it in a prompt.
www.anup.io/fine-tuning-...
Stop trying to understand research papers in one read.
Pass 1: Abstract + intro + conclusion (is this even relevant?)
Pass 2: Full read, flag gaps
Pass 3: Revisit with fresh context
It's a workflow, not a puzzle. Treat it like one.
www.anup.io/how-to-read-...
Pass 1: Abstract + intro + conclusion (is this even relevant?)
Pass 2: Full read, flag gaps
Pass 3: Revisit with fresh context
It's a workflow, not a puzzle. Treat it like one.
www.anup.io/how-to-read-...
How to read research papers
Most engineers read research papers like blog posts, expecting instant clarity. That’s why so many give up halfway through. The trick isn’t to read harder but to read differently. This https://blog.co...
www.anup.io
October 28, 2025 at 10:49 AM
Stop trying to understand research papers in one read.
Pass 1: Abstract + intro + conclusion (is this even relevant?)
Pass 2: Full read, flag gaps
Pass 3: Revisit with fresh context
It's a workflow, not a puzzle. Treat it like one.
www.anup.io/how-to-read-...
Pass 1: Abstract + intro + conclusion (is this even relevant?)
Pass 2: Full read, flag gaps
Pass 3: Revisit with fresh context
It's a workflow, not a puzzle. Treat it like one.
www.anup.io/how-to-read-...
Built a crisis support voice AI in 90 minutes at a hackathon and won. Full breakdown of the build + 7 tactics for shipping fast.
www.anup.io/eliza-redux-...
www.anup.io/eliza-redux-...
Eliza Redux: A Real-Time Voice AI Crisis Support Agent
I built a crisis support voice AI Agent in roughly 90 minutes at a voice AI hackathon and won. Here's how I did it, and the tactics that made it possible.
The Challenge
Crisis hotlines have four ma...
www.anup.io
October 27, 2025 at 4:20 PM
Built a crisis support voice AI in 90 minutes at a hackathon and won. Full breakdown of the build + 7 tactics for shipping fast.
www.anup.io/eliza-redux-...
www.anup.io/eliza-redux-...
Want to know the difference between MCP and A2A checkout this talk delivered at the London AI Engineers meetup
www.anup.io/mcp-a2a-the-...
#MCP #A2A #AIProtocols
www.anup.io/mcp-a2a-the-...
#MCP #A2A #AIProtocols
MCP + A2A: The Protocols Making AI Agents Actually Work Together
I presented this at the AI Engineer meetup in London. It is a short, practical overview of why agent interoperability matters now, and how two protocols, MCP & A2A, make it workable today.
www.anup.io
October 26, 2025 at 9:31 AM
Want to know the difference between MCP and A2A checkout this talk delivered at the London AI Engineers meetup
www.anup.io/mcp-a2a-the-...
#MCP #A2A #AIProtocols
www.anup.io/mcp-a2a-the-...
#MCP #A2A #AIProtocols
Reposted by Anup
So true! Software release on Friday 😁😂🤣
www.youtube.com/shorts/Iojxt...
www.youtube.com/shorts/Iojxt...
Software Release on Friday // click5
YouTube video by click5 Interactive
www.youtube.com
October 25, 2025 at 6:21 AM
So true! Software release on Friday 😁😂🤣
www.youtube.com/shorts/Iojxt...
www.youtube.com/shorts/Iojxt...
I tested ChatGPT Atlas vs Perplexity Comet on real automation workflows. Atlas won on reliability, so I'm switching over for now.
anup.io/atlas-unshru...
#atlas #openai #Perplexity #comet
anup.io/atlas-unshru...
#atlas #openai #Perplexity #comet
Atlas Unshrugged
ChatGPT Atlas vs Perplexity Comet: Real-World AI Browser Showdown
When OpenAI announced Atlas, I was curious. I've used Comet AI browser from Perplexity heavily for research, comparisons, and automat...
anup.io
October 25, 2025 at 8:49 PM
I tested ChatGPT Atlas vs Perplexity Comet on real automation workflows. Atlas won on reliability, so I'm switching over for now.
anup.io/atlas-unshru...
#atlas #openai #Perplexity #comet
anup.io/atlas-unshru...
#atlas #openai #Perplexity #comet
Your AI strategy doesn't need another slide deck. It needs experiments that teach you what actually works in production.
www.anup.io/stop-plannin...
www.anup.io/stop-plannin...
Stop Planning Your AI Strategy and Start Running Experiments
Earlier this year, I watched a Fortune 500 financial services company spend $4 million and eight months on their AI transformation. They brought in a major consulting firm. They ran a pilot program. T...
www.anup.io
October 25, 2025 at 8:48 PM
Your AI strategy doesn't need another slide deck. It needs experiments that teach you what actually works in production.
www.anup.io/stop-plannin...
www.anup.io/stop-plannin...