I think the initial migration towards nixOS is the hardest point, since it requires learning a bunch of new things all at once in order to get the system into a usable state that matches your expectations and preferences. The key benefit of using an LLM is that it makes it really easy to get your system into a useful initial state, and then you can safely learn and experiment incrementally with a mix of tools.

When I started off I didn't understand everything, but at this point I feel I have a very good understanding of everything in my configuration file.

The proliferation of gambling over so many domains has radicalized me against it in a way that I didn't think would've been possible a few years ago.

If we are to take any claims of Recursive Self Improvement seriously at all, then having a competent coding model seems like a key asset where you need to guarantee that you're remaining competitive. Why wouldn't you make coding models a top priority if you expect it to ultimately help your internal teams become more productive and effective?

There's also not an unlimited supply of researchers and engineers for them to keep burning through people at the rate at which they've been working. Although I guess for people with short timelines it makes sense to sprint hard, while people with longer timelines are more likely to treat this as a marathon. Maybe the years of burning bridges and developing such a toxic reputation are finally catching up to Elon. I think part of the harm that Elon has done is framing all the work in xAI as engineering while being highly dismissive of research, but a lot of research requires running experiments or thinking about problems and exploring them for long periods of time. If you're just grinding out work nonstop you don't really have time to let your mind wander and explore new ideas.

Honestly, I'm surprised they've done such a terrible job with programming. I remember around summer last year it was quite apparent how far behind they were with coding tools, but Elon was posting about taking that domain a bit more seriously. Why didn't any of those efforts materialize into real outputs? Something must be truly dysfunctional inside of xAI for them not to be shipping anything at all, especially considering Elon's propensity to ship undercooked products while continuing to iterate on them, as he has done in many previous cases.

I've noticed that Elon has also gone very hard on social media posting a ton of criticisms against the other big AI company CEOs like Daario Amodei. This suggests to me that he must feel very threatened, otherwise he wouldn't be resorting to such childish behavior. He must feel incredibly frustrated that no amount of money is able to make him more competitive within the AI space.

One of the issues I encountered initially was that the LLMs were repeating a small set of actions and never trying some of the more experimental actions. With a bit of prompt tweaking I was able to get them to branch out a bit, but it still feels like there's a lot of room for improvement on that front. I still haven't figured out how to instill a creative spark for exploration through my prompting skills.

It has been quite exciting to see how quickly a few simple rules can lead to emergent storytelling. One of the actions I added was the ability for the agents to pray to the creator of their world (i.e. me) along with the ability for me to respond in a separate cycle. The first prayer I received was from an agent that decided to wade into a river and kneel, just to offer a moment in stillness. Imagining it is still making me smile.

Unfortunately, I don't have access to enough compute to run a bigger experiment, but I think it would be really interesting to create lots of seed worlds / codebases which exist in a loop. With the twist being that after each cycle the agents can all suggest changes to their world. This would've previously been quite difficult, but I think it could be viable with current agentic programming capabilities. I wonder what a world with different LLM distributions would look like after a few iterations. What kind of worlds would Gemini, Claude, Grok, or ChatGPT create? And what if they're all put in the same world, which ones become the dominant force?

I've seen people on social media bragging about how they're able to produce a mountain of code as if this was praiseworthy.

[0] https://www.nationalgeographic.com/animals/article/mammals-p...

Not quite the same, but recently I was recently looking around for communities centered around Claude Code for discussion about people's workflows as well as discussion about what plugins people are using and if they notice it making a significant difference.

Since the technology is still evolving, having an active community can help you discover new patterns and explore the space more effectively.

Comments URL: https://news.ycombinator.com/item?id=47187764

Points: 2

# Comments: 1

Dwarkesh Patel: he gets extremely high quality guests and he doesn't just roll over completely when the guest makes a claim, at least he's willing to ask follow-up questions. His guest lectures with Sarah Paine are outstanding for helping to contextualize your understanding of the world order of the past 100 years from an American perspective.

Wookash Podcast: very technical and focused on more advanced programming topics. For specific episode suggestions I suggest the recent ones with Anton Mikhailov where they talk about ~~ECS~~ arrays of things.

Two's Complement: a podcast by the guy who made the Godbolt Compiler Explorer. It doesn't release very frequently but it provides interesting perspectives. Just

Ezra Klein Show: this is one of the guys that wrote the Abundance book, which I think was a much-needed message. Most recently he had an interview with Clark from Anthropic, but it's from a fairly normie / non-AI-obsessed perspective.

I have to rant about podcasts:

My biggest issue with most podcasts is that it often feels like there's very little effort put into preparing for the discussion and there's not many interesting follow-up questions. I think you can challenge people's claims in good faith to make for more interesting discussions. At least ask some reasonable follow-up questions when the guest makes outrageous claims! A lot of podcasts are just an advertising platform for people to talk about their new book; if you can listen to a guest give the same conversation with a different host then that's probably a sign that the questions are bad and shallow, so you shouldn't keep listening to that podcast.

One of the issues with asking deeper questions is that anything truly interesting or new will probably require having thought about the topic a lot ahead of time. Otherwise you just end up getting a very shallow answer because people can't usually think through complex topics on the fly so the best you can hope for is to get a pre-cached or partially computed answer. It would be great to have a podcast dedicated to exploring more challenging and underexplored questions which are shared with guests ahead of time so both parties can have time to think and explore. Most famous people just go on podcasts to play their "greatest hits" without saying anything substantially different or new.