RSS Parrot

Multi-Agents Are Out, PID Controllers Are In

http://timkellogg.me/blog/2025/03/06/pid-controllers

Published: March 6, 2025 00:00

My hottest take is that multi-agents are a broken concept and should be avoided at all cost. My only caveat is PID controllers; A multi agent system that does a 3-step process that looks something like **Plan, Act, Verify** in a loop. That can work.…

Target Practice: Resumes, But Better

http://timkellogg.me/blog/2025/02/20/target-practice

Published: February 20, 2025 00:00

I recently got a job, but it was a bear going through rejections on repeat. It almost felt like nobody was even looking at my resume. Which made me think 🤔 that might be the case.

LLaDA: LLMs That Don't Gaslight You

http://timkellogg.me/blog/2025/02/17/diffusion

Published: February 17, 2025 00:00

A new language model uses diffusion instead of next-token prediction. That means the text it can back out of a hallucination before it commits. This is a big win for areas like law & contracts, where global consistency is valued

Recursive Improvement: AI Singularity Or Just Benchmark Saturation?

http://timkellogg.me/blog/2025/02/12/recursive-improvement

Published: February 12, 2025 00:00

A fascinating new paper shows that LLMs can recursively self-improve. They can be trained on older versions of themselves and continuously get better. This immediately made me think, “this is it, it’s the AI singularity”, that moment when AI is able to…

S1: The $6 R1 Competitor?

http://timkellogg.me/blog/2025/02/03/s1

Published: February 3, 2025 00:00

A new paper released on Friday is making waves in the AI community, not because of the model it describes, but because it shows how close we are to some very large breakthroughs in AI. The model is just below state of the art, but it can run on my laptop.…

USA Could Win By Rolling Back AI Export Controls

http://timkellogg.me/blog/2025/01/28/deepseek

Published: January 28, 2025 00:00

This might sound crazy to just about everyone, but I think Trump could maintain an AI lead for the United States by immediately rolling back Biden-era export controls on AI chips, like the NVIDIA H100. Hear me out!

Explainer: What's R1 & Everything Else?

http://timkellogg.me/blog/2025/01/25/r1

Published: January 25, 2025 00:00

Is AI making you dizzy? A lot of industry insiders are feeling the same. R1 just came out a few days ago out of nowhere, and then there’s o1 and o3, but no o2. Gosh! It’s hard to know what’s going on. This post aims to be a guide for recent AI develoments.…

Powershell Users Like To Vomit

http://timkellogg.me/blog/2025/01/05/sh-v-psh

Published: January 5, 2025 00:00

In a stunning new study, PowerShell users insist that they like to vomit. How can this be? It's all about the data, and why you absolutely should question the data.

Normware: The Decline of Software Engineering

http://timkellogg.me/blog/2025/01/02/normware

Published: January 2, 2025 00:00

There’s a common refrain that “AI won’t replace software engineers”, often with the resolution, “you’ll be replaced by software engineers that use AI”, implying that AI will be used to make software engineers more productive and efficient. I argue that…

Explainer: Latent Space Experts

http://timkellogg.me/blog/2024/12/24/latent-experts

Published: December 24, 2024 00:00

A new paper just dropped from Google DeepMind, Deliberation in Latent Space via Differentiable Cache Augmentation. I don’t think this paper is very readable, but it also seems quite important so I wanted to take a moment to break it down, as I understand…