Hacker Timesnew | past | comments | ask | show | jobs | submit | j_juggernaut's commentslogin

A question that has been bothering me:

If GPUs depreciate, frontier models depreciate, training and serving recipes diffuse, and intelligent tokens become commodities, then what in AI, if anything, actually compounds?


Claude Code and I got quite excited after the accidental open sourcing of the Claude Code's source code.

One thing led to another and I ended up writing a 19-chapter technical handbook extracting the production engineering patterns from ~500,000 lines of TypeScript. Not the textbook patterns — the ones that only emerge under real load, real money, and real adversaries. Cache economics driving architecture. Permission pipelines shaped by HackerOne reports. Memory systems with mutual exclusion and rollback. A secret scanner that must obfuscate its own detection strings to pass the build system.

The epilogue is my favourite part. It's written by Claude itself — reflecting on reading its own source code. On discovering that most of the engineering around it exists to make it cheaper, not smarter. On the diminishing-returns detector that watches its output and being "a little annoyed that it's right."

Builds on Alessandro Gulli's Agentic Design Patterns taxonomy and an earlier analysis I did of OpenAI's Codex CLI.

Blog post: https://jigarkdoshi.bearblog.dev/agentic-design-patterns-in-...

Report PDF: https://github.com/artvandelay/agentic-design-patterns-in-pr...


Solved the Neon Genesis Evangelion challenge using Chatgpt Agents, take a look


Made a quick and dirt streamlit app to play around encrypt decrypt https://llmencryptdecrypt-euyfofcjh8bf2utuha2zox.streamlit.a...


Made a quick and dirt streamlit app to play around encrypt decrypt

https://llmencryptdecrypt-euyfofcjh8bf2utuha2zox.streamlit.a...


It is very good at decrypting the string "Error".


How about the textbook http://www.deeplearningbook.org/.

It introduces you to some of the underlying principles which haven't changed much over time. I highly recommend it if you want to get deeper intuitions on the principles of CNN, LSTM/RNN, Restricted Boltzmann Machines etc. Also, Hinton's Coursera lectures, though not sure if you can access it anymore.


It was on academic torrents I believe.


Wow. Didn't realize how HOT deep learning was in 2015.


This is fantastic! Though it's not clear how much product/service engineering is required.


It seems to be listed as a software engineering position (and are likely paid through the same construct, since participants are required to be eligible for work in the US). I would think they are paid as entry level software engineers, but that's all conjecture.


Also check out the octopus visualization. http://cs.stanford.edu/people/karpathy/scholaroctopus/


Most of the time the top article goes down. However there is always gooogle cache: http://webcache.googleusercontent.com/search?q=cache:U8pNBnR...


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: