Reading Log

Articles, papers, and posts I've read, in reverse chronological order.

Managed with rlog ↗

Teaching kids GenAI using Scratch, course is structured super well but I think we should move past Scratch

Read on Jan 31, 2026

Useful dataset to get better OCR on handwritten math

Read on Jan 28, 2026
Agent Psychosis: Are We Going Insane?
Armin RonacherJan 18, 2026

Literally psychosis, cult-like faux-productivity hives, thousands of people burning millions BILLIONS of tokens on a race to the slop

Read on Jan 22, 2026
Read on Jan 21, 2026

This is so sick, I will be using this from now on.

Read on Jan 21, 2026

Looking into why so much bursty traffic to my blog comes from Ashburn, VA. Turns out its a huge data centre town.

Read on Jan 19, 2026

Hmmm

Read on Jan 19, 2026

Back to plumbing?

Read on Jan 16, 2026
Why Senior Engineers Let Bad Projects Fail
Lalit MagantiJan 13, 2026

Lalit super good at clocking and writing ab big tech internals.

Read on Jan 15, 2026
overtime work schedule in Mainland China, 9AM-9PM, 6 days per week
Contributors to Wikimedia projectsMar 31, 2019
Read on Jan 13, 2026

Useful advice... for free!

Read on Jan 13, 2026
The Logical Progression
@dialloibuDec 11, 2025

Great post, gamblification study can be extended to absolutely everything under the sun at this point

Read on Jan 12, 2026

Still super relevant nearly 20 years later

Read on Jan 11, 2026

Small window into FB culture, crazy to see how hard he had to work to get back into writing code and avoiding meetings, maybe without this move there would be no claude code

Read on Jan 11, 2026
a16z: The Power Brokers
Packy McCormickJan 9, 2026

Long but great. a16z paved the way for engineering-focused invesment even if others don't realise.

Read on Jan 11, 2026

Mostly generic, nothing here stands out as something that made OpenAI special, author kinda shit at writing, can't identify what people want to read

Read on Jan 11, 2026

No one is tryna go 10 ways with me on a flat in Battersea though

Read on Jan 11, 2026
Read on Jan 10, 2026
ezyang's blog
ezyang's blogDec 20, 2025

Another post that mentions importance of having good taste for SWEs

Read on Jan 8, 2026
ezyang's blog
ezyang's blog

Agents can't build context, they can only be fed context... author describes three options: heavy prompting and guidance (2024/early-2025), semi-independent agents (2025-now), continual learning (future)

Read on Jan 8, 2026

Claude being allowed to terminate conversations itself, user can't even respond! Alignment + safety measures, no paper though

Read on Jan 4, 2026

Don't interpret models in isolation, look at system as a whole

Read on Jan 1, 2026

How models refuse harmful requests

Read on Jan 1, 2026

Foundational model alignment paper: helpfulness vs harmlessness, fine-tuning, RLHF

Read on Jan 1, 2026
LLMs Get Lost In Multi-Turn Conversation
Philippe Laban et al.May 8, 2025
Read on Jan 1, 2026
The Year in LLMs 2025
Simon Willison
Read on Jan 1, 2026

LLMs reward existing top tier swe practices, need to explore managerial side!

Read on Dec 30, 2025

Guide on how to structure a technical pitch deck (ghostty)

Read on Dec 29, 2025

Inference, memory, hardware, chips, economics

Read on Dec 29, 2025
Groq Inference Tokenomics: Speed, But At What Cost?
Dylan Patel, Daniel NishballFeb 21, 2024

Super useful article on inference speed vs cost tradeoffs

Read on Dec 29, 2025

Great read, brilliant story telling but I wish it got into the "what we missed by not banking smarter" details

Read on Dec 29, 2025

A decent conclusion and overview of the AI space, can't help but feel so much time was/is wasted trying every new trend instead of sticking to a proven model/workflow

Read on Dec 29, 2025
We removed 80% of our agent’s tools
Vercel Andrew QuChief of SoftwareDec 22, 2025

1. Better reasoning -> less constraints on model 2. NEED a good semantic/memory layer

Read on Dec 28, 2025

Conflate larger PRs and LOC with velocity/productivity.. come on now Greptile I thought your PR agent was anti-slop?

Read on Dec 27, 2025

Groq foundational paper 2022 - read this to see where every author is, most went to Nvidia and Google

Read on Dec 25, 2025
Inside the AI Chip Race with Groq
Chamath PalihapitiyaMar 7, 2025

Chamath hosting Groq executives, useful for article

Read on Dec 25, 2025

Groq on agentic workflows, this is how I'm spending the holidays...

Read on Dec 25, 2025

2022 Groq presenting LPU and TSP papers

Read on Dec 24, 2025

Interesting paper by Perplexity on adoption and usage of AI agents, exposes the growing class divide

Read on Dec 23, 2025
How Long Contexts Fail
Drew BreunigJun 22, 2025

Good breakdown of model context failure

Read on Dec 23, 2025
Memex trails
Filip Hracek
Read on Dec 22, 2025

Google Search breakdown

Read on Dec 22, 2025
An Industrial-Strength Audio Search Algorithm
Avery Li-Chun WangOct 26, 2003

Paper on how Shazam works

Read on Dec 22, 2025
Context Engine. Now with full Commit history
Sylvain GiulianiJul 29, 2025
Read on Dec 21, 2025
How Semantic Search works
https://www.facebook.com/kdnuggets
Read on Dec 20, 2025
The Cloudflare Blog
@d0m96Dec 8, 2025
Read on Dec 18, 2025
AI agents are starting to eat SaaS
Martin AldersonDec 15, 2025

Good post but no concrete examples just predictions

Read on Dec 16, 2025
Why Software Is Eating the World
Marc AndreessenAug 20, 2011

An egghead gives surprisingly accurate market and cultural predictions in 2011

Read on Dec 16, 2025
The appropriate amount of effort is zero
Michael AshcroftAug 28, 2025

Anecdotal at best, high effort is important throughout life, especially during preparation, the swimmer and the runners trained excrutiangly hard to breeze through their races

Read on Dec 16, 2025

Bullish

Read on Dec 16, 2025

Hey this is quite good!

Read on Dec 15, 2025

All it took was 1 year at Google in 2000 to fund a lifetime of failures, lessons learned though

Read on Dec 15, 2025

Required reading for my first Show HN

Read on Dec 14, 2025
Read on Dec 13, 2025

Part of the process to get this extension to the people!

Read on Dec 13, 2025

Excellent pros and cons of raycast development, still holds up 3 years later.

Read on Dec 12, 2025

Claude definitely opts for complexity given an open-ended optimisation question. However prompt diff.

Read on Dec 12, 2025

Super useful, used it to create this very extension I am typing in right now!

Read on Dec 11, 2025
Read on Dec 10, 2025
Read on Dec 10, 2025

Useful discussion between msgspec and Pydantic founders on performance

Read on Dec 7, 2025

Best article on culture at Palantir

Read on Dec 4, 2025

More on PLTR FDEs and being a "founder factory"

Read on Nov 29, 2025