It sends to OpenRouter if you chose to use OpenRouter. Can use Ollama. Idk how to get more local than that? Any tool will be non-local, when you do something explicitly non-local.
Overly, compared to what? Most people I know would be hard pressed to give either accurate information or even honest opinions when specifically asked. People want to be liked and people want to like people for reasons that have little to do with accuracy or honesty.
It's an interesting point but I too find it questionable. Humans operate differently than machines. We don't design CPU benchmarks around how humans would approach a given computation. It's not entirely obvious why we would do it here (but it might still be a good idea, I am curious).
I am worried for people using write ups like this as a huge, much appreciated dose of copium.
Try it out and don't stop trying. If something improves at this rate, even if you think it's not there right now, don't assume it is going to stop. Be honest about the things we were always obviously bad at, that the ai has been getting quickly better at, and assume that it will continue getting better. If this were true, what would that mean for you?
Ah, metaphors. Abstract concepts are not moving objects. You don't actually need to "turn it around" or "sail past it". You can break the laws of physics (because they don't apply). You can teleport around.
Speed actually just wins, because we are usually constrained by time.
1) a lot of shallow, orthogonal directions is better than 1 deep, careful approach
2) There's no social aspect to churning out a bunch of slop that will affect the perception of potential "right things" later. My domain can be particularly grudgeful in this regard.
1) If there is uncertainty, that seems to be correct, yes. (If there is no uncertainty, then the question and the essay become moot: You already know what to do. Things take as long as they must. Worst case, you are wrong.)
2) I read that part twice and could not figure out what it is you are trying to say.
Honest question: What is the hard part? If you took all of that stuff and did it as quickly as you could somewhere else, what's would be the biggest issue? People + resistance to change of any kind?
The outcome seems so obviously good. I have never heard of anyone complaining about a city becoming less car centric, but maybe somehow it's an under-represented story?
Well I sold off my car after realizing I enjoyed the bike ride to work. Then a year later an older family member had a health crisis requiring hospital visits at all possible times of the day and night for many months. Couldnt always rely on cabs and that was the only time I regretted selling the car. But we got through it with friends and fam sharing transport duties. Quite a crazy period so I could imagine it becoming real complicated for certain issues.
There are places where car is simply the mean of transport - to the point where using the car is preferred to literally a five minutes walk.
In contexts like this, using a car is perceived as a right - restricting usage doesn't make people think "I'll take the chance to use the bike", rather "How the f*ck do I get there now?".
You have not heard people complaining about cities impeding traffic, likely, because of the bubble you live in. That is the thing that makes regular people to run for the city offices. A whole lot of recent "urbanization" is not going to survive for long because of this IMHO.
There is a plausible scenario in which software engineering requires a very finite amount of intelligence, in which sota models will be used mainly for other things and where for coding the harness will become increasingly more important than the model.
i've kinda had this thought before but never could express it ("you only need up to a certain level of smartness to express most coding concepts correctly")
but it never occurred to me that, if true, of course the harness becomes increasingly more important. which feels absolutely correct of course.
https://www.iea.org/reports/global-ev-outlook-2025/electric-...
reply