HNHacker News
TopNewBestAskShowJobs

bottlepalm

2,527 karma · joined August 3, 2022

submissionscomments
bottlepalm··on Claude Fable 5
No, given it charged me the full amount in /usage and solved my problem impressively well compared to Opus/Codex both on xhigh.
bottlepalm··on Claude Fable 5
I just ran it on a tough reverse engineering problem I'm having that neither Claude Code 4.8 or ChatGPT Codex 5.5 could figure out. 30 minutes later Fable has it all figured out perfectly.
bottlepalm··on xAI is looking more like a datacentre REIT than a frontier lab
Grok isn't at the front of the frontier, but they are there for sure.
bottlepalm··on Google to pay SpaceX $920M a month for compute capacity at xAI data centers
Not really, the company reinvests the dividends, increasing the value of the company/stock.

The big difference is you pay taxes of dividends - you don't pay taxes on the stock going up year over year. Unrealized gains compound much faster than realized ones.

bottlepalm··on Pokemon Emerald Ported to WebAssembly (100k FPS)
I get nervous releasing just symbols for a game and here is a full disassembly. I have no idea how tolerant the rights holders are to this kind of stuff. I guess you just roll the dice, but the power is in their hands how far they take action.
bottlepalm··on Leap in DNA synthesis slashes time to build new genetic sequences
I can't be the only one reading this who doesn't have alarm bells going off in their heads.
bottlepalm··on When AI Builds Itself: Our progress toward recursive self-improvement
I'd use number of commits as a metric versus lines of code. A commit is generally a unit of work - regardless of the lines of code added/removed. It'd be interesting to see the metrics in terms of commits. I'm sure it's still an order of magnitude jump. Personally I'm flying with my own projects with AI, lots of commits, but I really try to minimize lines of code added. If I can remove and simplify existing code so the balance of lines added on commit are minimal - that's the path to a better quality app overall.
bottlepalm··on Artificial intelligence is not conscious – Ted Chiang
35 years old and just as relevant today - https://web.mit.edu/people/dpolicar/writing/prose/text/think...

A silicon alien coming to earth might poke us, we would say ouch, and just determine the ouch sound is just the result of a bunch of chemistry - not really conscious or feeling pain like it can, just emulating.

bottlepalm··on The real cost of owning a home
Money spent that isn’t transformed into equity is considered lost.
bottlepalm··on The real cost of owning a home
Taxes goes up, insurance goes up, repair costs goes up, and with a 30 year mortgage you lose like 50% the value of the home in interest payments.
bottlepalm··on Using AI to write better code more slowly
Ah the classic thinking that 'code documents itself'. It does not. Some devs are so full of themselves they think their code is so good that it is obvious what their intent was. It never is obvious, and just ends up as tech debt. Write comments.
bottlepalm··on Using AI to write better code more slowly
Yes exactly. I don't like Codex not writing comments - and even proactively removing useful comments! There was some change in the last month that causes Claude to write crazy long comments. I routinely have to ask Claude to 'tighten' up the comments before the final commit.
bottlepalm··on Using AI to write better code more slowly
Like I said, we either need more people or some paradigm shift in tooling that allows us to do more with less.
bottlepalm··on Using AI to write better code more slowly
Lets see, front end presentation, front end service, frontend api, backend to front end (BFF) api/routing, BFF logic, BFF api, backend routing, backend logic, backend database, worker routing, worker logic, worker storage.

And then the each of the service layers can be broken into layers themselves depending on the complexity of the business logic can be broken into layers as well. So yea a change in a worker can potentially bubble up through all the layers.

bottlepalm··on Using AI to write better code more slowly
How does that work? Isn't writing code and reviewing code things that happen in serial?
bottlepalm··on Using AI to write better code more slowly
> You design, Claude writes, Codex reviews, and Gemini doesn't get installed

hahahahaha

bottlepalm··on Using AI to write better code more slowly
I've worked in large teams for many years and yes it's just like that, but without the time constraint. PR's can only go back and forth so many times. Depending on the reviewer they may phone it in, or focus on different things depending on the person. You yourself aren't able to implement every piece of feedback due to constraints and it ends up as tech debt.

So AI definitely changes the game. I feel like we almost need something higher level for reviewers to review changes faster. Todays code is starting to feel like assembler. Too much of it, too low level. We need even higher level constructs to be able to more in less time. I'm just not sure what that is.

bottlepalm··on Using AI to write better code more slowly
Quality is 100x more important than cheaper/faster.
bottlepalm··on Using AI to write better code more slowly
No, I find it stimulating. With AI I'm moving faster and producing code at a higher quality than ever before.

Don't get me wrong I used to enjoy writing code by hand, but I don't think I would anymore. I don't like writing code for the sake of writing code - I like building things, I like being productive.

bottlepalm··on Using AI to write better code more slowly
I do multi-task a bit while AI is running, sometimes working on another feature with AI in parallel, but jumping between reviewing different feature iterations is draining, though not much different than the real world juggling PR reviews for a team of devs.
bottlepalm··on Using AI to write better code more slowly
I think you're projecting.
bottlepalm··on Using AI to write better code more slowly
This is where the human element is critical, but cause it'll infinite loop review feedback if you let it and the code will easily go off the rails into an over engineered mess. That's why I review the code before/after as well as review the actual feedback itself - and often give the feedback to different AI to get its opinion as the other AI doesn't have a vested interest in it and can be more critical. At some point though you do have to cut them off and ship.
bottlepalm··on Using AI to write better code more slowly
Oh course it's not black and white, there are many shades of grey in how detailed the design of a feature can be. Often even if I know low level details, I'll only give the AI high level requirements because I want to see how it would do it. Often it comes up alternative/better ways of doing what I planned and I incorporate those ideas into the final design.
bottlepalm··on Using AI to write better code more slowly
I don't have it automated, but I score on minimizing lines of code added, readability of the code, and quality of the architecture.
bottlepalm··on Using AI to write better code more slowly
The problem is that I manually review the code before/after the review, as well as review the items to review themselves. You could easily put AI into a review infinite loop if you let it, and you also risk the code base going off the rails if you let AI go wild.

It's actually happened a few times where I need to back out entire features because AI went too far and I lost control/understanding of what the code is doing. Many people will give up at that point and let AI do everything - that is a mistake, at least right now and how you end up with unmaintainable vibe spaghetti slop.

bottlepalm··on Using AI to write better code more slowly
It is.. but so is dealing with issues at runtime, going through weeks of revisions, and dealing with technical debt.
bottlepalm··on Using AI to write better code more slowly
$200/month split between Claude Code Max and Codex Pro. Given how many hours a month I spend programming, my hourly rate, the amount of time saved, and the productivity/quality boost - I would pay a whole lot more if I had to.
bottlepalm··on Using AI to write better code more slowly
Refactoring is the natural evolution of a growing application. Refactoring too soon, too fast is what we call over engineering. Too little refactoring and your code becomes spaghetti slop. Regardless - the application will change across all layers across its lifetime.
bottlepalm··on Using AI to write better code more slowly
Semantics. In reality yes it is the v3 version equivelent in terms of maturity and iteration. I know because I've been doing this for a long time. We are getting to v3 and beyond faster than ever before.

In the new world there is no time to put out v1 quality code and it is borderline reckless given how easily things are getting hacked now. You need to be putting out heavily reviewed code that covers all the corner cases on the first release.

bottlepalm··on Using AI to write better code more slowly
Unfortunately the projects are still too big. Projects with hundreds of thousands to millions of lines of code can't be maintained by a single person reviewing all the the changes. And AI only increases the speed of iteration and the amount of code to review.

We may need some sort of paradigm shift - like more powerful frameworks or even higher level languages that allow us to review less, but more functional code blocks.

← PreviousPage 9 of 34Next →