f0e4c2f7

This is actually the typical case when new projects drop on HN. Dropbox is the canonical example.

You gotta not take it personal. Announcing on HN is a gauntlet. People can be a bit prickly. Just a bit though. You get lots of good feedback too.

It's amusing to me this entire article is centered around brow beating this and other hypothetical software authors for starting things without doing a small amount of research first to understand the very basics of what they're getting into.

If the author of the article had done just a small amount of research about bend or it's author before writing the article they would have known pretty quickly what they were saying was incorrect.

I think the larger pattern here is that nuance is one of the most valuable commodities in the AI era. If you're hand waving stuff away without even missing , you're going to miss a lot of stuff in this cycle.

This article reminds me a lot of the famous hacker news Dropbox comment.

Very interesting. So how open is the neural band to hack on? Do you expect this to be something to get patched out eventually if you update? Seems like a really cool platform to develop against outside of the intended ecosystem.

Ahhhh yeah totally get that. Changes things considerably.

Have you considered setting up an agent environment like codex and having it work making on Android version for you? I know you said it's a very complex app and that probably makes it seem like it wouldn't be able to, but LLMs are really good when they have a very clearly defined end state to work toward, like an existing iOS app with code, screenshots etc.

I bet if you set Astra codex against this task on the $100 plan it would have it done at a speed that would shock you. Potentially even by the end of the day and mostly uninterrupted.

The SOTA models can reverse engineer whole codebases even from assembly now. If you have to specify with words what you want to do it's still hard but if you have a codebase to work from, you can pretty much arbitrarily convert apps and games into other languages / platforms now as if by transitive property.

I related a lot to the feelings in this article but over the past year I've come to a different conclusion than the author. In the end of the article he says that there are 3 paths available to him, but I believe there is an additional path to consider.

You can use the AI tools but still program by hand every day for practice and fun. Programming becomes deliberate practice to keep your skills and mind sharp. Like going to the gym, but for your brain. You can use the LLMs to push and challenge yourself, setting more aggressive and ambitious goals than you might have in the old days for learning.

I used to think of software dev like climbing a mountain. Hard, and I loved it. I loved it because of the difficulty. That was the most fun part. Getting to the top, the summit. That was incidental to me. I wouldn't even defend that as a good thing. Certainly not good engineering. It was just what I liked. Any good engineering was incidental to how fun the hard parts of the puzzle were.

Then LLMs came along and I thought "this is like a helicopter. You can go straight up to the top in a few minutes." While very practical, it also led to the feelings the author described. After months of handwringing and using the tools, having existential crises - I've arrived at a new conclusion:

It's not a helicopter. It's a jetpack. And it's still hard to use if you push it to it's absolute limit. Knowing just the right spot to grab the rock as you fly by. Taking as much risk as possible, but not too much. Pushing both the jet pack (or perhaps it's an iron man suit now with latest models) and the rock climbing knowledge as far as they will go. Screwing up, falling off the wall, and learning.

And with this jetpack you can get to places you never could have climbed to without it. Not just the top. Weird, interesting spots on the mountain.

That perspective, which I've taken to over the last month or two has helped me find the fun again. The existential crises have ended and I'm back to feeling about software dev the way I felt a few years ago. Boundless joy and excitement. Probably more now.

This feels like satire / parody. Praising LinkedIn. The text itself containing multiple LLM tells, especially in the parts complaining most about LLM writing.

Maybe not. Could just be kind of accidentally ironic with the author picking up LLM quirks from using them a lot.

Funny in either case.

I read this whole thing a couple days ago. Really long but super interesting. Worth reading imo.

A lot of handwringing about the security implications but I think the accomplishments of the swarm itself are the most interesting. Next rung up on the ladder of abstraction I suspect.

Having the same issue. I think they might have turned it off. Was looking forward to using this.

Lots of services have no desire to ever expose an API. This approach lets you step right over that.

If an API is exposed you can just have the LLM write something against that.

Ha! This is great. I've been waiting for someone to make this.

Giving an LLM a computer makes it way more powerful, giving it a kubernetes cluster should extend that power much further and naturally fits well with the way LLMs work.

I think this abstraction can scale for a good long while. Past this what do you give the agent? Control of a whole Data Center I guess.

I'm not sure if it will replace openclaw all together since kubernetes is kind of niche and scary to a lot of people. But I bet for the most sophisticated builders this will become quite popular, and who knows maybe far beyond that cohort too.

Congrats on the launch!

I don't like the premise of this game. If you're autistic, don't mask. Live authentically as yourself and find people who love you for who you are.

You'll annoy the hell out of some people, and thats fine. They can find other people to spend time with.

You can probably find a good community where you are, and if not just move to SF which is something like the autism homeland. Being autistic there is valorized and even imitated in sort of amusing ways.

Masking is a kind of hell, living someone else's life. Unmasking and living as yourself feels scary at first but the people who will love you that way can only find you if you live that way.

This looks cool and I wish you luck but I'd probably never use something closed source for this.

Been on the lookout for an open source version but they all seem kind of unessecarily bulky or otherwise poorly maintained.

Would be interested in suggestions anyone has for whole apps or libs that work well when glued together for this purpose.

Front page of HN. Funny to imagine thousands of people sitting in the office crossing their eyes at their computer screen right now.

There is a funny parallel I see with Kubernetes that I also saw a lot with Linux in the early years. There are thousands of packages and tools you can install on Linux (think phpmyadmin for example) and new users sometimes go wild installing every single package they read about.

After a while, the more mature Linux engineers start going the other way. Ripping out as much as possible. Stripping down to the leanest build they can, for performance but also to reduce attack surface and overall complexity.

Very similar dynamic with k8s. Early days are often about scooping up every CNCF project like you're on a shopping spree. Eventually people get to shipping slim clusters running and 30mb containers with alpine or nix. Using it essentially as open source clustering for Linux.

Sounds like management and mentoring might be a satisfying diversion at this point in your life.

For sure. It's been amazing honestly and I feel like it has really accelerated my learning. Enough that I'm trying to get really serious about making the most out of this new leverage seemingly out of nowhere.

I use it a lot for mapping out of the initial concepts but I find one of the best use cases is after understanding the basics, explaining where I need to learn more and asking for a book recommendation. The quality of my reading list has gone up 10x this way and I find myself working through multiple books a week.

Great for code too obviously, though still feels like early days there to me.

Building using LFS has been on my list of "I really should probably do that just to learn" for about 20 years now. I'll get around to it! This year I'm finally learning Lisp (and really enjoying it).

Really cool idea. Novel, I imagine a lot of people would play this. I would suggest a social media campaign with short form videos. Seems like something that has the potential to go viral or at least make a lot of money.

There is one clear answer in my opinion:

There is a secondary market for OpenAI stock.

It's not a public market so nobody knows how much you're making if you sell, but if you look at current valuations it must be a lot.

In that context, it would be quite hard not to leave and sell or stay and sell. What if oai loses the lead? What if open source wins? Keeping the stock seems like the actual hard thing to me and I expect to see many others leave (like early googlers or Facebook employees)

Sure it's worth more if you hang on to it, but many think "how many hundreds of M's do I actually need? Better to derisk and sell"

I'm a big fan of the reading list and structure of teachyourselfcs.com

Fortunately big tech jobs are available in EU too. Highest salaries might trickier without moving to US, shouldn't be too hard to transfer to US once you get a job at one if you want to. Making quite a high salary without moving is possible too (though still need to be a in a major metro that has big tech companies.)

This is fairly straightforward imo. Most money is in big tech. Look at levels.fyi to get an idea of the roadmap.

Big tech hires mostly off leetcodes. There are other factors too.

Your journey begins with practicing leetcodes and reading all the books on teachyourselfcs.com

Study dilligently. Watch YouTube courses too but this should be considered supplemental.

Apply for big tech jobs. This will probably take several trys, especially in this market. Just keep applying and studying.

Once you're at a big tech company keep studying, learn from the smartest people you meet, and ship a lot. After a promotion or two apply to Meta (or someone else if they're paying more on levels.fyi at that point, but Meta pays especially well)

Start giving presentations at conferences. At higher levels in big tech this is encouraged and sometimes even expected as part of promo packets. Also practice your writing. Starting on writing a technical book on a subject your an expert in by this time would be good.

Keep shipping, keep learning, keep getting promoted. Once you're on that track you're well on your way to $1M/yr TC.

I'm not sure why but it seems like most of the high quality AI content is on twitter. On average seems to be around ~4 months ahead of HN on AI dev approaches.

I would suggest following / reading people who talk about using Claude 3.5 sonnet.

Lots of people developing whole apps using 3.5 sonnet and sometimes cursor or another editor integration. The models are getting quite good now at writing code once you learn how to use them right and don't use the incorrect LLMs (a problem I often see in places other than twitter unfortunately.) They seem to get better almost weekly now too. Just yesterday Anthropic released an update where you can now store your entire codebase to call as part of the prompt at 90% token discount. Should make an already very good model much better.

Gumroad's CEO has also made some good YouTube content describing a lot of these techniques, but they're livestreams so there is a lot of dead air.

https://www.youtube.com/watch?v=1CC88QGQiEA

https://www.youtube.com/watch?v=mY6oV7tZUi0

There have been some papers showing that RLHF makes models more palletable to use but reduces performance on evals and in other various ways.

I couldn't find the one I was looking for but this is one of them.

https://arxiv.org/abs/2310.06452

Edit:

This tweet also has a screenshot showing degraded evals from RLHF from base model.

https://x.com/KevinAFischer/status/1638706111443513346?t=0wK...

This is a bit of a Zen thing you're describing. A lot of different approaches and theories on getting to the same thing here I would say. It's hard to think of specific advice here beyond "just start doing it" which does not seem very helpful. Maybe a good insight here is "practice will make it easier."

I think ultimately for me this mindset was cultivated at a pretty young age with some writing and art I happened to come across. I love content like that and seek it out now. I think you can become more and more growth mindset oriented with time. I'll share some of the things I've liked on the topic here, maybe that will be useful:

http://www.catb.org/~esr/faqs/hacker-howto.html

https://www.goodreads.com/quotes/7727986-mountains-should-be... (this is a quote, but recommend this whole book)

https://www.amazon.com/Mindset-Psychology-Carol-S-Dweck/dp/0...

https://youtu.be/etEJrznE-c0?si=Eaq8aycm8Yxn1v56

This book is so good. It's about building early computers but it feels just like tech does today in the way it's described. Which make it feel like this bigger context you're reading into. That even before computers were mainstream, there were still those who tinkered.

Two things are especially memorable to me. One is a casual remark in the book that they found the best way to get things done is to pair someone very experienced and cynical with someone very inexperienced and naive. Combined they would get lots done together compared to either alone. I think this is still true today.

The other thing is the intro. It's about the head of the project getting a group together and renting a sailboat on vacation. On the sailboat the get tossed and at times feel like they barely survived and it ends with someone saying "if this was his vacation...what did this man do for fun!?"

Currently listening to this series of interviews about Neuralink:

https://www.youtube.com/watch?v=Kbk9BiPhm7o

Would be interested to hear the experiences of someone who has used this.

When I was a kid there was this new thing that came out called Wikipedia. I couldn't convince anyone it was useful though because they pointed out it was wrong sometimes. Eventually they came around though.

AI is like that right now. It's only right sometimes. You need to use judgement. Still useful though.