Thank you. It is just funny and interesting to note people seeing Homebrew as their choice of default package manager on linux! It shows that people clearly care about the technically better solution which has a very good UX over the native choices that linux distros made over years, be it apt or yum or something else.
I install homebrew as a first thing on my corporate amazon linux too as many system packages are lacking, and I couldn't get neovim in a different way.
How cool it will be to pick up some interesting book from this, and give me to llm and direct it to make it a modern multiplayer game. Has anyone tried this?
If you and I can understand this paper, or use the process to achieve something similar for the ends we care about, wouldn't that be enough? Why do you care who it is coming from and what their motivations are?
How likely will an LLM agent actually donates either using credit card or using Monero tokens ? I think, it is very clever, and I give a non-zero chance of a donation happening with this text.
If the prediction markets are between people, why do people bet against the mostly likely outcome at all ?
Real anecdote. For e.g, during Superbowl 2026. The markets were allowed bets to be placed until 6 minutes to close, when Seahawks were way ahead of New England Patriots.
The probablity of Seahawks winning was almost 99% and any person who places a 1000 dollar bet will make 1100 in 6 minutes. Where is the 100 dollar going to come from? Who loses that?
Since you built it, I am curious about the scientific accuracy of the movie, book and while taking the information GAIA DR3. I wanted to assume at least the stars part is science, but I think, there is a lot of fiction in that setting. Is this map the reality of what we know as science, since it came from GAIA DR3 dataset?
And, thank you very much. This is super cool and exciting. I wish such a one exists for Asimov's foundation universe (fiction).
This is correct. I have switched back to Cursor, with sota models, after I discovered that I lost control when I gave in to industry drumbeat of using cli based agents and which presented _something_ to review and then went back again in full swing.
In the other Project Gutenberg discussion, I started checking out science fiction stories, and came across this one.
Robert Sheckley wrote this in 1953, but the story has so much parallels to the modern day LLMs and their capabilities and limitations to humans.
> It's well established now that the way you put a question often determines not only the answer you'll get, but the type of answer possible. So ... a mechanical answerer, geared to produce the ultimate revelations in reference to anything you want to know, might have unsuspected limitations.
> how LLMs can make learning to code more productive,
> "LLMs make learning to code as important"
>> I don't see how you can get to "more important"
Oh, well, the semantics and I know it matters.
If you agree to the statement that "learning to code as important", then, it is pretty is a positive reinforcement to learn to code, rather than negative signal (don't learn as it a waste) or 0 signal (don't bother, it's a waste of time as you can prompt it away).
All I am saying is industry drumbeat is misleading us, and learning to code IS important, as much or more as we want to take our trajectory with us. Coding is not just typing code, which I have emphasized a lot in the post.
I do. He is responsible for one of the major breakthroughs in the world. He is as trustworthy as Elon Musk, Jeff Bezos, or Bill Gates is. Remember, they are playing the game of Business. The rules of the game are different than say rules of scientific breakthroughs.