HN user
Sure it does. I still nees to know the correct mathematics to type into the calculator and the calculator is deterministic. If you don't understand it without the llm explaining it, how can you be sure you actually understand it? How can you catch mistakes made due to it being non-deterministic? Ask another llm? Same problem
We have more code than we need. Proof for me is every "smart" device that worked better before we put a computer in it.
Blame goes to everyone involved. From the decision makers to the implementors
What did they actually say about some's kida?
Knocking out someones teeth would necessitate filing charges
I write code by hand every day. I do the main part of the feature implementation myself and leave comments for the code i want the agent to write. I have some skills and a command that sets the stage to get the agent to fill in the rest
Vibes are not evidence, neither is a curated demo. You need actual measured evidence that has an adversarial review to actually prove something without falling to confirmation bias.
Yep to the point where its easier without the gps.
Got any sources for those claims that show how broadly adopted ai is in those countries? I lookes at japan and china and could find a few articles, the anime one cites a single anime made with ai and nothing about its reception and similar results for china
Id say it improved until about 2016, since then the additions have generally made the software worse.
More overlays and popups More needlessly verbose navigation instructions Less predictable routes.
Thats just the start
They aren't blameless, friends and family only should be the default even if you don't engage much. Why would they default it to a bunch of junk.
I'd agree but we're closer to getting forced into the chair than making a decision that's right for us
Yes but able bodied people shouldnt decide to use a wheelchair until their legs attrophy and become useless.
I've been very happy using cdk for interacting with aws. Much better than terraform and the like.
Or how you'll get all your data out and imported into your custom system.
Just give multiple options in the config file. Give us the current default, what you now call verbose mode and the previous verbose mode. If Claude is as effective as marketing claims then maintaining all 3 options should be trivially doable, we've been doing more complex configuration in tons of apps for decades.
Vibe steering and navigating
I assume all ads are scams. That's easier.
We could measure it for cocaine and cigarettes couldn't we.
Worse enough it isn't addictive. The goal is non-addictive, whatever changes to whatever part are necessary to hit that goal.
Is that what I should be doing? I'm just encouraging the devs on my team to read designing data intensive apps and setting up time for group discussions. Aside from coding and meetings that is.
This is the bad side of things like OKRs. They push you away from user satisfaction since that harder to measure, coupled with go consequences for missing them. People just force adoption without taking the product signals that come from users rejecting your changes.
Come on Claude, making it not start isn't the same as fixing the bugs
Do not give a shit about how they excuse doing a bad job. If their tools make them that much more productive, and being the developer of those tools should allow you to make great use of them.
Use native for osx Use .Net framework for windows Use whatever on Linux.
Its just being lazy and ineffective. I also do not care about whatever "business" justification anyone can come up with for half assing it.
Fuck is there a way to have that degree and not be clueless and toxic to your colleagues and users.
Sounds like a decent into madness to me and I'm somewhat pro AI.
There being a few edge cases where it doesn't work in doesn't mean it doesn't work in the majority of cases and that we shouldn't try to fix the edge cases.
Because I've been burned by every big tech company I can think of. As for why it would be soothing, well because it gives me hope that when I read any further legal docs they'll hold to the post.
What does ai have to do with this? The sooner that bubble bursts the better IMO.
I don't know dude. Every time I've assumed good faith on my paying for something means ad free, I've been screwed by some asshole with an MBA getting into a leadership position high enough to push ads through. I'd rather it be explicit
Honestly IMO it's more that I ask for A, but don't strongly enough discourage B then I get both A, B and maybe C, generally implemented poorly. The base systems need to have more focus and doubt built in before they'll be truely useful for things aside from a greenfield apps or generating maintainable code.
Until AI labs have the equivalent of an SLA for giving accurate and helpful responses it don't get better. They've not even able to measure if the agents work correctly and consistently.