Anup Jadhav

Horizon Length - Moore's law for AI Agents

This post from LessWrong critiques the idea of “horizon length” (a benchmark from METR that ranks tasks by how long

17 Oct

The boring secret to building better AI agents

Andrew Ng pointed out something interesting: the single biggest factor in how fast teams build AI agents isn't

16 Oct

Representation Engineering with Control Vectors

There's this technique called representation engineering that lets you modify how AI models behave in a surprisingly effective

16 Oct

RAG

Rethinking RAG: Meta’s REFRAG

For the past few years, retrieval-augmented generation (RAG) has been the workhorse architecture for grounded LLM applications. You retrieve relevant

15 Oct

Nobody Knows How to Charge for AI

I've been watching the AI SaaS pricing chaos unfold over the past year, and honestly, it's

13 Oct

Pace Layering Framework

I came across Stewart Brand’s pace layering framework because a former colleague and friend, Seb Wagner from Flow Republic,

10 Oct

AI Agents

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

09 Oct

AI Agents Are Finally Fixing Real-World Code Security Problems

I came across something genuinely interesting in code security this week: DeepMind’s CodeMender, an AI agent that doesn’t

09 Oct

Data in CSV Format Isn’t Always the Best for LLMs

When you feed a large table into an LLM, the way you format the input can change the model’s

07 Oct

Prompt Engineering vs Context Engineering

From Anthropic: https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents Prompt Engineering: Prompt engineering refers to methods for writing and organizing LLM

06 Oct

Why LLMs Confidently Hallucinate a Seahorse Emoji That Never Existed

Ask any major AI if there's a seahorse emoji and they'll say yes with 100% confidence.

06 Oct

Goodbye Manual Prompts, Hello DSPy

Today I learned about a smarter way to deal with the headache of prompts in production. Drew Brunig’s talk

05 Oct

Nemawashi (根回し)

There’s a Japanese concept called nemawashi (literally “root-walking”) that offers a way around the dreaded “big reveal” in engineering

05 Oct

AI agents are starting to do real work

Ethan Mollick argues that AIs have quietly crossed a line. OpenAI recently tested models on complex, expert-designed tasks that usually

04 Oct

Vibe Coding

Cargo Cult Vibe Coding

In the age of AI code generation, we risk trading craftsmanship for ritual It's the 1940s in the

04 Oct