alasano

Running 2 is enough to slow it down to a crawl unless I'm not doing anything else and just letting agents work.

I've definitely tried optimizing with lower memory as you suggest but the margin is so small given normal usage of the computer at the same time that it really doesn't make a difference unfortunately.

So that's 2 emulators + a few terminals of pi/Claude, Firefox open, vscode and usually docker but nothing too heavy there.

What's are the odds that the M7 Max goes above 128GB? (Presuming the rumors about Apple skipping the M6 Pro/Max are true)

What are you doing with yours? I recently started using Android/iOS emulators locally and combined with anything else my M1 Pro 32 GB feels unusable.

Definitely grabbing 128 GB + for the next machine.

These M7 rumors and that they're skipping the M6 Pro/Max rumors are really making me try to stretch my M1 Pro until next year.

I'm gonna max out most of the specs on the next one I get, would feel insanely wasteful to do that now.

I'd like to subscribe to your Denmark vs Switzerland fun facts, cause I just had fun.

Right! I forgot Sweden is basically people who speak better English than native speakers, apologizing for their subpar English.

I'm curious as to what prevented you from learning it to a level that doesn't embarass you?

Time goes by quickly and suddenly it's been 10 years is a perfectly fine answer.

This is really nice. I'm able to read Hiragana and Katakana fully after about 4-6 weeks now but then I'm hit with the reality of how many Kanji I have to learn still everytime I want to read something in real life lol

I simply don't want to review AI code in depth.

I used to do it but now I only review code organization and structure.

Mostly I define the product behavior I want and discuss the technical implementation beforehand.

Once that's in a spec I let it build in my durable implementation engine. Automated verification, review rounds from different agent types across different models, issues triaged into meaningful clusters and flagged for false positives before finally being fixed.

That loops until the code is up to spec.

There is no special secret, LLMs need repetition and multiple passes.

They'll one shot bigger and bigger things in their default harnesses but they'll be filled with issues no matter what.

Same, used them exclusively last time I was in SF and it was absolutely perfect.

"be able" implying capability rather than time constraints and opportunity cost which is what most people on here refer to when they mention something cool they're doing with LLMs that they weren't doing before.

Right! I just remembered why I was still on my Nvidia Shield Pro, Apple TV 4K doesn't have the lossless pass through.

That's crazy

What's crazy is that it's still close to the best device you can get.

I'd upgrade my Shield Pro to something else but there's nothing to upgrade to that doesn't have some compromise on formats or capabilities.

I presume MITMdling Apple is not even close to as easy (or profitable) as Ledger.

Funny I just asked that too but in my quick check boat was slightly more expensive albeit with more storage space.