You should choose random parts, and add “I don’t think this makes sense, can you explain this part?” or “Why didn’t you use <something semi-related> instead?”, “I think you should have done <random similar pattern>” here." to random parts of the PR. No need for it to be true or read it, not like it matters. You can keep doing that for quite a long time :D Sure, they’ll just copy-paste it to their agent, but the longer you keep that going, the more unsure will they be, probably.

Or even better, just message him that you have questions about the PR, if they can come over because it’s more things, and ask these comments directly.

I’ve been able to find a workflow where it’s mostly correct and can handle most of my gamedev related coding without making too many mistakes. I still have to actually read through the code and pay some attention to what it’s doing, and if it misses something and goes on a wild goose chase, it’s unusable and I have to start over (so someone who didn’t know what they are doing would be cooked), but whatever.

Sure, it does require a lot of looping adversarial reviews, and my average token cost is around 3000$ (4B tokens) a month (we have unlimited budgets and a pretty accurate tracking, and also probably cheaper than consumer prices per token with how large company it is), which is actually more than my monthly salary, but it’s just a job, for a company and on a product I don’t really care about, and I can 1) keep slacking in my job while doing my own coding stuff and projects, and keep seeing how absolutely unreasonable the prices are if you want to get at least semi-submitable results.

You could ask if it’s necessary to spend so much tokens - but so far most adversary review rounds do find serious blocker bugs the first implementation had, most of them being some hidden stuff that would be difficult to reasonably find by hand unless you really understand everything around the code, which you should, but the point of AI is that you shouldn’t have to.

Is it worth it? Lol, no. The whole team is loosing codebase knowledge, we’re getting bottle-necked by pending PR reviews that are just stacking up and no one wants to do, so we’re not even more effective, the cost is absolutely absurd and in no way near sustainable or worth it. And the longer it goes on, the less I can realize it’s spewing bullshit and I should stop it and nudge it into a different direction in our codebase, because I’m slowly loosing touch with it, while for now I’m still relying on what I remember from before we went all-in on AI.

And that’s while the whole industry is in the “Uber pricing” phase, so it will get a lot worse. But yeah, if you can burn 100-200$ per a simple implementation task, then it can have a pretty usable results. And that 3000$ a month does not include our CI review bot, that does additional rounds of multi-agent council reviews. And I’m not even working on anything complex, mostly just various menu screens UI. I can imagine the bill getting a lot higher if you get into more involved systems.

Please please I really hope they will force US companies to start calling their chatbots SI instead of AI, and forbid them from using the term AI.

That would be such a funny PR/marketing nightmare. It’s such a cringe term :D

What, you don’t have your SWAP set to 1TB Google Drive share?

I’m really a fan of the dogmatized occultisms. The orders like Illuminates of Thanateros, Golden Dawn, John Dee’s books, even Wicca, Discordians.

It’s really interesting rabbit hole that’s a nice open-mindness exercise, plus it’s fascinating to experiment with.

Almost everyone I’ve met who showed any interrest in occultism was always taking it too seriously, to the point of sounding unhealthy. They either knew and read the actual sources, and were too much into it, or they had some kind of random vibes-based new-age approach (and also were too much into it to the point of sounding insane).

I never really understood that. Maintaining an open mind while still keeping a little bit of dostance from it, taking it more like a research into history with a bit of curious practice (basically LARPing would be a perfect analogy), is fun and what I did, but people usually just let it take over their lifes in very unhealthy fashion.

I’ve tried out several of the orders/practices, and each one was fascinating to get into, I would say had overall positive effect on my life, even if it was just having fun larping/method acting and exploring what effects it has on my mental state.

I never interacted with the community, though. I’ve only met one other person who has similar aproach, and a lot of people who you’d consider insane upon hearing how they talk about it.

I highly recommend giving it a try with open mind. I work in IT, never really was into spiritualism or religion, but getting through i.e this book on Wicca, with an open mind, without prejudice and giving it a honest try, was really an eye openning experience. I didn’t stick with it for long, but the few months I tried were suprisingly fun. It’s basically solo LARPing.

Also, the whole history around that and other cults is really fascinating read, but trying out the practice is where most of the controversal (for some) fun is. But again - it’s like with religion - you have to be careful not to let it take over your life, annoy others with it, or use it as an excuse for anything, from why your life sucks or why you can be a dick.

Is it a compression when you need presumably gigabites of a model to reconstruct the data?

It’s basically the same as saying I can shatter compressions records by hashing the thing and using a rainbow table to decompress it.

The fact that Meta has a C-suite position that’s called Chief Privacy Officer is my favorite absurdly ironic fact.

I can’t imagine how can anyone apply to that with a strait face and clear conscience, but that’s prpbably true for most positions at Meta, aside from like Beat Games and the like.

You left? Murderer.

Isn’t that, like, illegal?