Manthan

You type a question into ChatGPT and hit send.

A voice agent can pass every eval you wrote for it and still be broken in production.

Every time you ask Cursor “where do we handle authentication?”

The first time I tried to plug a memory layer into a voice agent, the thing slowed down by hundreds of milliseconds on the first turn and never recovered.

The first time I built a voice agent and got on a call with it, the thing felt like talking to someone over a satellite phone in 2003.

The first time I asked ChatGPT what it remembered about me, it listed 33 facts.

Most “AI optimization” demos are fun to watch for the same reason benchmark tweets are fun to watch: they show you the win, not the search.

If you’ve read my previous posts on ChatGPT memory, Claude memory, and Clawdbot memory, you already know I keep coming back to the same question: how do these agents actually remember?

Most “autonomous AI research” demos look impressive for the same reason magic tricks do: you only see the interesting part.

OpenClaw is an open-source personal AI assistant (MIT licensed) created by Peter Steinberger that has quickly gained traction with over 32,600 stars on GitHub at the time of writing this blog.

Agentic systems are already being deployed for complex tasks: building software, conducting research, analyzing data, and automating workflows.

TL;DR: Modern LLMs use subword tokenization (BPE, WordPiece, or Unigram) to balance vocabulary size with sequence length.

TL;DR: LLM as a judge works well when you (1) use reference based evaluation over pointwise scoring, (2) debias pairwise comparisons by swapping positions, (3) ensemble across multiple models, (4) require reasoning before scores, and (5) calibrate against…

When I reverse-engineered ChatGPT’s memory system, I found it uses pre-computed summaries injected into every prompt.

When I asked ChatGPT what it remembered about me, it listed 33 facts from my name and career goals to my current fitness routine.

I have never relied on traditional interview processes to get a job.

Memory has become one of the most talked about topics in the AI community.

LLMs are prediction engines.

Building multi-agent systems with existing frameworks is painful.

This is a non-technical post that I feel fit to share as the year 2024 has come to an end.

Hello World!

Ah shit, another blog series from yours truly.

Yeah, I have been away for half a year now.

CricLang is a fun programming language created for cricket enthusiasts.

Welcome to the third and final part of my series on replication in distributed systems.

In the first part of the series, we laid the foundation of replication in distributed systems.

Welcome, fellow nerds, to the 1st part of a blog series on replication.

Have you ever thought about why databases are so complex internally and why we can’t use a text file to store the data?