HackerLangs
TopNewTrendsCommentsPastAskShowJobs

morgango

no profile record

comments

morgango
·2 mesi fa·discuss
I am a paying user of Warp and really enjoy it when it behaves.

I do struggle with having AI forced on me at times, when I press a key errantly and seem to be driven away from the command line and deeper and deeper into AI-land with questions and "are you sure ...".

My ESC key is wearing out.
morgango
·4 mesi fa·discuss
A young Kim Catrall had a Vulcan commentary on this: https://www.elastic.co/customers
morgango
·4 mesi fa·discuss
Astrid! Or more accurately, Jasika Nicole.
morgango
·4 mesi fa·discuss
That is the sound of someone else's lunch being eaten.
morgango
·5 mesi fa·discuss
For the low, low price of $5/month.
morgango
·5 mesi fa·discuss
Completely worth it to me. It would be an incredible value at twice the price and part of my daily workflow on all machines.
morgango
·5 mesi fa·discuss
Be a System of Record, not just a Wrapper™ is excellent advice.
morgango
·6 mesi fa·discuss
https://archive.is/C2FPC
morgango
·7 mesi fa·discuss
Having a pretty, intelligent, well spoken young woman present it doesn't hurt either.

And in no way do I want to take away from her insight and skill in popularizing and communicating these concepts. Clearly she is good at what she does.
morgango
·8 mesi fa·discuss
Are we nearing the capability to build something like the Mind's Game (from the Ender's Game book)
morgango
·9 mesi fa·discuss
Welp, there goes my productivity for a year.
morgango
·9 mesi fa·discuss
That was incredibly difficult to read. Text would be nice.
morgango
·9 mesi fa·discuss
Capitalism is based largely on coercion. The overwhelming majority of people would not be doing what they do most of the time if their needs were already met.
morgango
·10 mesi fa·discuss
Seatec Astronomy
morgango
·3 anni fa·discuss
Very astute observation.

It is sometimes worth it to take people who are unhappy in their job and/or not performing well and give them a package when they are available. I would guess there are 20 of these people at any company of that size, not just WOTC.
morgango
·3 anni fa·discuss
I asked ChatGPT this question, and asked it to simplify as much as possible.

Fine-tuned Models: Imagine you have a super-smart robot that can talk about anything. But you want it to be really good at talking about, say, dinosaurs. So, you teach it more about dinosaurs specifically. That's what fine-tuning is – you're teaching the robot (or model) to be really good at a specific topic.

Vector Databases and Embeddings with LLM: This might be a little tricky, but let's think of it this way. Imagine you have a huge library of books and you want to find information on a specific topic, say, ancient Egypt. Now, instead of reading every book, you have a magical index that can tell you which books talk about ancient Egypt. This index is created by magically converting each book into a "summary dot" (that's the embedding). When you ask about ancient Egypt, your question is also converted into a "summary dot". Then, the magical index finds the books (or "summary dots") that are most similar to your question. That's how the vector database and embeddings work.

So, if you want your super-smart robot to be really good at one specific topic, you use fine-tuning. But if you want it to quickly find information from a huge library of knowledge, you use vector databases and embeddings. Sometimes, you might even use both for different parts of the same task!