HN user
Unfortunately we’re in the phase where even if you write things yourself, be it prose with em dashes or code with velocity, you’re given a demerit. And, if you are using AI, the work is still treated as less valuable, even if it brings value.
@dang can we prune some of these search and aggregator tools? Some are clearly not being kept up to date.
I understand where you’re coming from, but anecdotally the same thing happened to me except I have less clarity on why and no refund. I got an email back saying my appeal was rejected with no recourse. I was paying for max and using it for multiple projects, no other thing stands out to me as a cause for getting blocked. Guess you’ll have to take my word for it to, it’s hard to prove the non-existence of definitely-problematic prompts.
I experienced this with lobsters and deleted my account there. They describe it as a garden party, which is accurate. And it’s very easy to ruffle the feathers of those at the garden party if you dare question the politics.
Given one’s ability to trade in-game assets for real world ones, it’s not very different from any other virtual assets and so I agree with the appeal decision to treat it as something that can be stolen.
What’s needed to make it at least 121x productivity?
I upvoted you because I would like to know the response to these approaches
That’s reasonable, thanks!
speaking of claude code in Ghostty, I’ve noticed I can’t drag and drop images into the prompt when the session is within a tmux pane. I miss that, coming from the mac terminal app, which allowed me to do so. I’d be willing to look into this myself, but mention it in case someone already knows where to start looking.
@mitchellh what did you use for the memory visualizations? Looks nice, and the website plays well with mobile. Whats the stack?
my gut reaction is to see if there’s a way to pay to upgrade to a bigger model, only to remember that there’s no upgrading of the human brain
this might be one of the most sociopathic things I’ve ever read
Trading uncrontrolled population growth for TikTok sounds like a deal with the devil.
With regard to AI, why not throw this whole article in an .md file and point CLAUDE.md to it? Codex is better at following rules so maybe you’d have more luck with that. But yeah, AI won’t code your way by default. People expect way too much out of the interns, they need direction.
I have an out-there hypothesis I’d want to test. Much of the population has one or more MTHFR mutations, which can increase homocysteine if left untreated and that’s been linked to increased risk in stroke. Treatment includes more B vitamins. I wonder if the declining nutrition in foods and lack of B vitamins has anything to do with this.
Interesting to see all the people in this thread who had a stroke. I had a mild and then moderate cerebellar stroke within a 7 day span about two years ago. I remember being on the stroke neurology floor of the hospital with a lot of bed ridden people who had also suffered them. I know because, within 24 hours, I was doing hourly walking laps with my nurses because I was bored. In other words, I was one of the lucky ones. Within a week I was back at work — not because I felt pressured to by them, they were completely understanding, but because I had no more symptoms that were experienced simply because I was sitting down to work.
I also see some advice about listening to your body after the fact, which I fully agree with. In my case, without going into too much detail, the stroke might not have happened if I had listened to my body beforehand, as it was caused by an injury I could have prevented.
So if I could give any advice from this place of experience it would be to listen to your body, and try to hear it when your fears and ego are shouting.
It started as a mix of self-imposed pressure and actually enjoying marking tasks as complete. Now I feel resistant to relaxing things. And no, I definitely don’t get paid more.
Lol this person talks about easing into LLMs again two weeks after quitting cold turkey. The addiction is real. I laugh because I’m in the same situation, and see no way out other than to switch professions and/or take up programming as a hobby in which I purposefully subject myself to hard mode. I’m too productive with it in my profession to scale back and do things by hand — the cat is out of the bag and I’ve set a race pace at work that I can’t reasonably retract from without raising eyebrows. So I agree with the author’s referenced post that finding ways to still utilize it while maintaining a mental map of the code base and limiting its blast radius is a good middle ground, but damn it requires a lot of discipline.
Are you open to code contributions? I’d like to see this sooner than later and would be willing to help.
This is a fantastic writeup with great visuals
Claude writes 99% of my code, I’m just a manager and architect and QC now.
ChatGPT and its consequences have been a disaster for the human race
Replace ChatGPT with ‘knives’ or ‘nuclear technology’ and you will see this is blaming the tool and not the humans weilding them. You won’t win the fight against technological advancements. We need to hold the humans that use them accountable
In my experience limiting myself to two projects in parallel is most productive, with a clear primary project whose agent’s completion take precedence over the other’s. It lets me still have concurrent work going on, but I’m very clearly still taking care to be precise and targeted with my prompting. Too many things going on, and I’m no longer optimizing for doing the task but for having as much parallel execution and progress as possible, and that’s a trap of perceived productivity.
The physical performance kind. Conversely beet root, L-Citruline, and supplemental NO are commonly used for ED. That’s why medications like tadalafil and sildenafil work. NO relaxes your blood vessels and increases blood flow generally.
You must carefully not leaving any recursive functions not annotated with #[recursive]
Isn’t the same true of forgetting #[stacksafe]?
This reminds me of certain Haskell patterns where you selectively make some operations strict instead of lazy for similar reasons. I’m glad this library exists, but I’m sad the Rust compiler itself doesn’t have better support for recursion.
If you have trouble in bed, ask yourself if you use Listerine. It kills your mouth’s microbiome and lowers your Nitric Oxide production [0].
Curious, if you’re integrating with their POS why is it a subscription instead of taking a percentage of sales?
The author got too big for their britches and was drunk on perceived power. No need to have many parallel agents going on. Focus on one project and implementing features one at a time and dogfooding and testing. Shipping any code, vibed or not, then saying it blew up is not the LLMs fault. I can’t believe I’m saying that. It’s the shipper’s responsibility to make sure it works. Of course if you are a manager and let your junior ship code it will blow up…
And yes I know AI is marketed as more. But it’s still people’s fault for swallowing the PR and shipping crappy code then complaining about the lies. Stop deflecting responsibility for your work
Lots of in-depth analysis, but I think the author is very clearly emotionally invested to the point that they are only drawing conclusions that justify and support their emotions. I agree that we’re in a bubble in the sense that a lot of these companies will go bankrupt, but it won’t be Google or Anthropic (unless Google makes a model that’s an order of magnitude better or order of magnitude cheaper with capability parity). Claude is simply too good at coding in well-represented languages like Python and Typescript to not pay hundreds of dollars a month for (if not thousands, subsidized by employers). These companies are racing to have the most effective agents and models right now. Once the bottleneck is clearly humans’ ability the specify the requirements and context, reducing the cost of the models will be the main competitive edge, and we’re not there yet (although even now the better you are at providing requirements and context, the more effective you are with the models). I think that once cost reduction is the target, Google will win because they have the hardware capabilities to do so.
Mean time to shipping features of various estimated difficulty. It’s subjective and not perfect, but generally speaking I need to work way less. I’ll be honest, one thing I think I could have done faster without AI was to implement CRDT-based cloud sync for a project I have going. I think I’ve tried to utilize AI too much for this. It’s good at implementing vector clock implementations, but not at preventing race conditions.