Archive - Mostly Harmless Ideas

October 2024

All Mostly Harmless Books at +80% off

Celebrating my birthday with the biggest discount ever.

Oct 28 •

Alejandro Piad Morffis

Why everyone should learn to code

Oct 25 •

Alejandro Piad Morffis

Turn your Substack into a Technical Book

The most underrated business model for technical writers.

Oct 18 •

Alejandro Piad Morffis

No, LLMs Still Cannot Reason - Part II

The follow-up you didn't know you needed—and neither did I...

Oct 1 •

Alejandro Piad Morffis

September 2024

Fine-tuning Large Language Models

Or how to actually train your own chatbot.

Sep 24 •

Alejandro Piad Morffis

Why Large Language Models Cannot (Still) Actually Reason

Despite what OpenAI tells you...

Sep 19 •

Alejandro Piad Morffis

New update for How to Train your Chatbot

Over 170 pages of practical advice on understanding and using large language models.

Sep 13 •

Alejandro Piad Morffis

Optimizing LLMs

Techniques to make a large language model run on commodity hardware.

Sep 13 •

Alejandro Piad Morffis

August 2024

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts