Mostly Harmless Ideas
Subscribe
Sign in
Home
🔥Start here
🌟 Mostly Harmless AI
📚 Books
🧠 Computer Science
💻 Coding Lessons
✒️ Essays
💡 Philosophy
🌟 Insiders
✍️Technical Writing
🚀 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
•
Alejandro Piad Morffis
51
Share this post
No, LLMs Still Cannot Reason - Part II
blog.apiad.net
Copy link
Facebook
Email
Note
Other
52
Fine-tuning Large Language Models
Or how to actually train your own chatbot.
Sep 24
•
Alejandro Piad Morffis
22
Share this post
Fine-tuning Large Language Models
blog.apiad.net
Copy link
Facebook
Email
Note
Other
2
Why Large Language Models Cannot (Still) Actually Reason
Despite what OpenAI tells you...
Sep 19
•
Alejandro Piad Morffis
53
Share this post
Why Large Language Models Cannot (Still) Actually Reason
blog.apiad.net
Copy link
Facebook
Email
Note
Other
30
Optimizing LLMs
Techniques to make a large language model run on commodity hardware.
Sep 13
•
Alejandro Piad Morffis
18
Share this post
Optimizing LLMs
blog.apiad.net
Copy link
Facebook
Email
Note
Other
2
Agents as the Final Frontier in Large Language Modeling
Bringing LLMs to life with beliefs, goals, and intentions.
Jun 21
•
Alejandro Piad Morffis
28
Share this post
Agents as the Final Frontier in Large Language Modeling
blog.apiad.net
Copy link
Facebook
Email
Note
Other
8
Code Generation is the Next Milestone Towards AGI
How to turn a stochastic parrot into a general-purpose problem solver.
Jun 10
•
Alejandro Piad Morffis
16
Share this post
Code Generation is the Next Milestone Towards AGI
blog.apiad.net
Copy link
Facebook
Email
Note
Other
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
•
Alejandro Piad Morffis
16
Share this post
What you need to master Prompt Engineering
blog.apiad.net
Copy link
Facebook
Email
Note
Other
10
Make your LLM phone home
How to extend your LLM capabilities by integrating with any API
May 25
•
Alejandro Piad Morffis
14
Share this post
Make your LLM phone home
blog.apiad.net
Copy link
Facebook
Email
Note
Other
2
What can you do with a language model?
An exploration of the most exiting uses of LLMs, beyond the typical chatbot.
May 22
•
Alejandro Piad Morffis
14
Share this post
What can you do with a language model?
blog.apiad.net
Copy link
Facebook
Email
Note
Other
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
•
Alejandro Piad Morffis
26
Share this post
What is Retrieval Augmented Generation?
blog.apiad.net
Copy link
Facebook
Email
Note
Other
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
•
Alejandro Piad Morffis
29
Share this post
Why are LLMs so versatile?
blog.apiad.net
Copy link
Facebook
Email
Note
Other
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
•
Alejandro Piad Morffis
18
Share this post
The most important lesson in Machine Learning
blog.apiad.net
Copy link
Facebook
Email
Note
Other
16
Share
Copy link
Facebook
Email
Note
Other
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
