Mostly Harmless Ideas
Subscribe
Sign in
Home
🔥Start here
🌟 Mostly Harmless AI
📚 Books
🧠 Computer Science
💻 Coding Lessons
✒️ Essays
💡 Philosophy
🚀 Sci-Fi
About
🌟 Mostly Harmless AI
Latest
Top
Discussions
No, LLMs Still Cannot Reason - Part II
The follow-up you didn't know you needed—and neither did I...
Oct 1, 2024
•
Alejandro Piad Morffis
60
Share this post
Mostly Harmless Ideas
No, LLMs Still Cannot Reason - Part II
Copy link
Facebook
Email
Notes
More
54
Fine-tuning Large Language Models
Or how to actually train your own chatbot.
Sep 24, 2024
•
Alejandro Piad Morffis
24
Share this post
Mostly Harmless Ideas
Fine-tuning Large Language Models
Copy link
Facebook
Email
Notes
More
2
Why Large Language Models Cannot (Still) Actually Reason
Despite what OpenAI tells you...
Sep 19, 2024
•
Alejandro Piad Morffis
63
Share this post
Mostly Harmless Ideas
Why Large Language Models Cannot (Still) Actually Reason
Copy link
Facebook
Email
Notes
More
30
Optimizing LLMs
Techniques to make a large language model run on commodity hardware.
Sep 13, 2024
•
Alejandro Piad Morffis
18
Share this post
Mostly Harmless Ideas
Optimizing LLMs
Copy link
Facebook
Email
Notes
More
2
Agents as the Final Frontier in Large Language Modeling
Bringing LLMs to life with beliefs, goals, and intentions.
Jun 21, 2024
•
Alejandro Piad Morffis
29
Share this post
Mostly Harmless Ideas
Agents as the Final Frontier in Large Language Modeling
Copy link
Facebook
Email
Notes
More
8
Code Generation is the Next Milestone Towards AGI
How to turn a stochastic parrot into a general-purpose problem solver.
Jun 10, 2024
•
Alejandro Piad Morffis
16
Share this post
Mostly Harmless Ideas
Code Generation is the Next Milestone Towards AGI
Copy link
Facebook
Email
Notes
More
1
What you need to master Prompt Engineering
High-level principles and reusable techniques to get the best out of a large language model with clever prompting.
May 31, 2024
•
Alejandro Piad Morffis
16
Share this post
Mostly Harmless Ideas
What you need to master Prompt Engineering
Copy link
Facebook
Email
Notes
More
10
Make your LLM phone home
How to extend your LLM capabilities by integrating with any API
May 25, 2024
•
Alejandro Piad Morffis
14
Share this post
Mostly Harmless Ideas
Make your LLM phone home
Copy link
Facebook
Email
Notes
More
2
What can you do with a language model?
An exploration of the most exiting uses of LLMs, beyond the typical chatbot.
May 22, 2024
•
Alejandro Piad Morffis
14
Share this post
Mostly Harmless Ideas
What can you do with a language model?
Copy link
Facebook
Email
Notes
More
9
What is Retrieval Augmented Generation?
The simplest and most effective way to make a large language model more accurate, knowledgeable, and robust in practical, domain-specific applications.
May 13, 2024
•
Alejandro Piad Morffis
26
Share this post
Mostly Harmless Ideas
What is Retrieval Augmented Generation?
Copy link
Facebook
Email
Notes
More
2
Why are LLMs so versatile?
Wait? Isn't this just autocomplete on steroids? Well, it is, but that is missing the whole point. Here's how LLMs really work.
May 6, 2024
•
Alejandro Piad Morffis
29
Share this post
Mostly Harmless Ideas
Why are LLMs so versatile?
Copy link
Facebook
Email
Notes
More
10
The most important lesson in Machine Learning
Most applied machine learning research looks beautiful in the paper, but fails spectacularly in real-life. They all fall prey to the same mistake: the…
Apr 25, 2024
•
Alejandro Piad Morffis
18
Share this post
Mostly Harmless Ideas
The most important lesson in Machine Learning
Copy link
Facebook
Email
Notes
More
16
Share
Copy link
Facebook
Email
Notes
More
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
