> Feedback helps, right. But if you've got a problem where a simple, contained feedback loop isn't that easy to build, the only source of feedback is yourself. And that's when you are exposed to the stupidity of current AI models.
That's exactly the point. Modern coding agents aren't smart software engineers per se; they're very very good goal-seekers whose unit of work is code. They need automatable feedback loops.
Tofu being displeasurable is funny to me because it literally has no taste and texture by default. It becomes whatever you put it in or how you cook it. You want crunchy? You got it. Puree? Sure. Sweet? Fine. Salty? Spicy? Tangy? Easy.
People just don't want to actually put in the effort to prepare it.
My problem is that I just can't get it to take up any of the flavour. I can marinate it for days, and the marinade will still just be a superficial layer on top of a piece of tofu which, itself, always remains completely unfazed and tasteless.
It's not a problem for saucy dishes like a curry, but even experimenting with friends and borderline "molecular cuisine" techniques I have never once managed to flavour tofu itself :(
yeah that can be very difficult. I think you should aim to _season_ the tofu (i.e. salt -- or slight umami with soy sauce), but your primary flavour should still come from a sauce that's on it. I really like sticky sauces that cling to tofu like buffalo sauce or sugary, sticky glazes.
It’s actually extremely motivating to consider what LLM or similar AI agent could do for us if we were to free our minds from 2 decades of SaaS brainrot.
What if we ran AI locally and used it to actually do labor-intensive things with computers that make money rather than assuming everything were web-connected, paywalled, rate-limited, authenticated, tracked, and resold?
Certainly useful for authoring, since that's what I do most now as a founder. Most of my code is pretty fresh. While I can give you some feedback, I probably wouldn't pay more than a couple bucks a month. Meanwhile the larger, older codebases at more mature companies have much greater need and budgets.
Thanks! Getting all the possibly-relevant related code isn't too hard; the hard part is filtering down to what's relevant. So I think specific use cases (e.g. "how do I get from a known entry point to some method/property/etc") is gonna be key.
I read that sentence as saying someone came up with a cost estimate of $142.7b to clean up everything, and then there's a comparison to 3M's $53b market cap for scale/comparison.
I don't think all the money in the world could cleanup "everything" that is contaminated with PFAS - it is effectively pervasive in the ecosystem at this point.
> Apps like Bear, Reeder, Anybox, Things 3, make switching devices seamless
I think Apple's whole point is that they provide the APIs so that apps can do this themselves. Which, yeah, is a bit disappointing; I'd love to have a 100% fidelity, flick-to-another-device type of Continuity built into the OS, but the APIs are at least a starting point.
That's exactly the point. Modern coding agents aren't smart software engineers per se; they're very very good goal-seekers whose unit of work is code. They need automatable feedback loops.
reply