jimmaswell

A rewrite is a slam dunk for any decent frontier AI. It has a penchant for maintaining API/etc contracts to a fault in the absence of instructions to the contrary. It can easily validate its work and loves building exhaustive test cases. You can tell it to get 100% code coverage if you want. It will laborously accurate document every accumulated edge case and help you find a better overall cohesive structure.

A rewrite has historically been a huge mistake in many situations, some of which I've personally had the agony of witnessing firsthand, powerless to stop it. But AI completely changes the calculus because it doesn't waste significant developer time or energy crawling back to the previous working state, it just does it while you go get coffee. And this I've found to be a huge benefit, that I can continue making my codebases nicer to work with and better documented/integrated with bugs stamped out for free. There are upsides to a rewrite, and they're now much more likely to be worth it as the downsides are automated away.

This isn't a big problem for roads, sidewalks, or the library.

A job is bullshit if it's wasting resources duplicating the work of a machine without good reason. Replacing excavators with teams of shovelers would be a bullshit job, but the same job wouldn't have been bullshit before excavators.

Demanding the world halt progress and do something inefficiently just to give you a bullshit job is not a position that engenders my empathy

Her "cause" of making everyone's lives worse by delaying food delivery? Why would I ever support this?

In what scenario is Sunoco going to try to steal all my money?

It's obvious pretty quick that you use the prediction line to inform what to do on the next pass, and you have to time it. It would be too easy if it was just "wait for the projection to point at the other player and hit fire".

Being able to shoot the other player is a minor quibble for this kind of web minigame. It's still fun and interesting.

AI is a threat if you're a messy codebase, an unsolved math problem, or cancer. Otherwise you only have an improved quality of living to look forward to IMO.

Somehow this just hasn't happened to me. I use Astra on high all day for fairly intensive game dev tasks, sometimes cranked up depending on the task.

I have heard ultra thinking might delegate to worse agents for some of its sub-tasks, but I don't use that much anymore since Astra came out. Just high seems good enough to throw most laundry lists at.

Why would I ever do that to myself? My experience with Codex/GPT is fantastic, while my impression of Claude/Opus is that it's longwinded, patronizing, token-inefficient, stops to ask stupid questions every other minute, overcomplicates simple tasks, often poor engineering overall. I don't use it but this is what I see my partner run into who has access to both and compares them often. She has the same assessment.

Agreed. I don't believe intuition and creativity would be more than pattern recognition, remixing ideas, and trial and error combined with a kind of "genetic algorithm" approach if you deconstructed them into what the brain is actually doing.

I would find it very interesting to train a model on information only available prior to the discovery of e.g. relativity or calculus and see if it can invent it. My intuition is that modern frontiers absolutely could. Not to take away from their brilliance, but Newton and Einstein were brilliant people who also happened to be in the perfect place at the perfect time - there's not so much "low hanging (i.e. approachable by one brilliant individual) but immensely valuable fruit" anymore.

It feels goalpost-movey to downplay exploring a large search space efficiently in regards to "intelligence". If we dug into a human genius's brain and found it was somehow trying out a million ways to solve a a problem at once, no one would seriously suggest the person isn't actually intelligent.

And our brains must something like that at some physical level. You can't have a "turtles all the way down" of reasoning - the building blocks must be simpler. It must reduce to something like pathfinding and brute force at some point, weighted by factors in the system and maybe some randomness.

You would often not have wifi available, and you wouldn't want to have to type in wifi passwords to your camera all the time. But your phone will almost always be nearby and persistent bluetooth is easy.

I would hope they have some feature for automatic backup to your phone over bluetooth or such today.