vadansky

TIL; I always thought it was part of archive.org and I never understood why people hated it. Now I get it

Yeah, the price is so high and things are moving so fast I don’t wanna risk committing to something that becomes obsolete in a year. I wanna see the rumoured M7 first. Hopefully hardware demand doesn’t make waiting a stupid decision…

Do you have battery saving mode on? I think it blocks the background process that updates. I had the same issue but turning it off and waiting 1 minute started blocking all the certificates. This is for iPhone 13.

I was in the same boat, but then I tried out Pi which works with the OpenAI subscription and now I prefer it more. I wish Anthropic let you use a custom harness with a subscription but I heard people get banned and don't wanna risk it.

I think the goal is to make it easy to review. Like if I hate reading the code it wrote then it’s also a code smell there is something wrong with it.

I have a mix of heavily reviewed and more vibe-coded projects, and the ones where I manage the architectural choices end up working a lot better, even just for the LLM itself. I can get features built much quicker with less tokens and bugs. Meanwhile the more vibe-coded stuff always takes longer and sometimes gets bugs

Edit: To add to that, even in my "micro-mangaged" projects, the parts I didn't review end and treat like a block box temporarily up being the parts that introduce bugs.

I am surprised how many people like the actual writing part, it always felt to me like doing micro in an RTS game. I know a lot of people love that too but I always played RTS games to feel like a general. But I'm still in the camp of reading every single change the LLM does, so I feel like I get the best of both worlds, but maybe that will end up being a waste of time soon. Like if the job ends up being just writing and reviewing MD files for the agent to digest I'll hate it too.

With open weight models isn't this like trying to regulate encryption?

> is probably more like seeing the ending to a mystery novel

So math should switch to a Columbo methodology?

Has buying groceries online been normalized to this extent? I still feel dirty about it, but maybe I’m too old fashioned.

I get the sentiment but it feels like this right now: https://www.youtube.com/watch?v=bwcJNsoY50E

I played it on my Quest 2 so that's not really the price of admission

Now it's a 500 for me

You'd think this would be easy to organize with AGI

> Plan your own release announcement and blog posts and notify news outlets, MAKE NO MISTAKES

There are too many threads about the outage, I should vibe-code something to read all 3 and summor-Oh wait...

Sounds like it's worth waiting for M7 anyways, no point investing too much right now

https://news.ycombinator.com/item?id=48676795

It's a waste of tokens to do it post-hoc instead of fixing it upstream, but when I see a wall of text I just prompt "TLDR;"

Sorry for being lazy, but is there a rough breakdown like "You get sonnet level for M5 and Opus for M5 pro, etc.", or is it still speculative. Or put simpler, do you get Opus level for the 256GB M5 Max?

What about if everyone symlinked CLAUDE to AGENT and then added it to .gitignore to stop the free “advertising”?

To anyone like me that switches between Codex and CC based on limits, but prefers CC to Codex, PI has been really great to migrate over. It can customize itself very easily, I was expecting to have to clone the repo or whatever, but no you can just tell it "add a manual mode where you present all changes as diffs in VSCode, letting me edit them or save to accept" and it will do it.

I wish I could use my Anthropic sub with it but I heard you get banned, but at least you can use it with any other subscription or model.

Last time I tried some of these, none of them had the "manual mode" that CC has, where it shows you change by change as diffs and you can edit them before accepting and moving on to the next change. I like that because if it's going off pattern I can spot it early on and guide it correctly, instead of having to review the whole completed diff at the end when it's too late. I should spend the weekend checking them out again to see if they added that but I assume with everyone going full agent mode they probably didn't.

Set up SSH!

I might be crucified for saying this, but I actually have a Claude skill file for that. I have SSH turned on for the Steamdeck, I use Lutris so all the configs are in a database, so I just point Claude to the MD file and the game files and tell it to set it up for me. The main purpose of the skill file is really just to save the SSH, rsync instructions and give it lutris config examples like which version of proton works, etc.)

Cruelty Squad called

> Claude Plays Pokemon is suddenly going to get past Mt. Doom now.

I miss him... But for reference he did get past Doom and got pretty far in the strength puzzle too before he cut cut off. He was looping and just brute forcing it.

This, I'm working on a game engine as a hobby project. I can do one "big" feature over a weekend, most of it including designing and manual testing that it's working as expected, but then it takes me 2 weekends to break up the changes into smaller commits using jj, which also gives me the chance to review and understand the code myself. So it's a weird mix of fast and slow, but I think I've grown to prefer reviewing over writing so it works for a hobby project.

Surprised no one mentioned WizTree which is a lot faster than WinDirStat

It already refuses to read the AGENT.md/CLAUDE.md files, what's the point of giving it even more markdown it won't read until you yell at it.

If feels like the photoshop paint bucket tool.

If you draw a sloppy circle and fill it in, it'll "escape" and try to paint the whole canvas (and back in the day would get my slow computer stuck until I spam "esc").

You have to be able to draw a good circle to use it.

Seems like most people have settled on Opus 4.6 as the breaking point (me as well).

Once I can spend 10k to run Opus 4.6 at home, I'm done.