Gemini thinking
This is a classic "efficiency vs. logic" dilemma!
Since the goal is to wash the car, you should drive.
While 50 meters (about 165 feet) is a very short distance—usually less than a one-minute walk—it is unfortunately very difficult to wash a car that isn't actually at the car wash.
Why Driving Wins:
* Logistics: The car needs to be physically present for the high-pressure hoses or automated brushes to reach it.
* Convenience: You’ll save yourself the confusion of the car wash staff when you show up on foot with a bucket and a hopeful expression.
* The "Dry" Factor: If it's an automated wash, you get to stay inside where it's dry.
When to Walk:
* If you are just going there to buy a gift card or check their prices before bringing the car over.
* If you're looking for a very brief bit of exercise before starting the chore.
Verdict: Put the keys in the ignition. You'll be there in about 10 seconds!
Would you like me to check the local weather to see if there's any rain forecast that might ruin your freshly cleaned car?
s. logic" dilemma!
Since the goal is to wash the car, you should drive.
While 50 meters (about 165 feet) is a very short distance—usually less than a one-minute walk—it is unfortunately very difficult to wash a car that isn't actually at the car wash.
Why Driving Wins:
* Logistics: The car needs to be physically present for the high-pressure hoses or automated brushes to reach it.
* Convenience: You’ll save yourself the confusion of the car wash staff when you show up on foot with a bucket and a hopeful expression.
* The "Dry" Factor: If it's an automated wash, you get to stay inside where it's dry.
When to Walk:
* If you are just going there to buy a gift card or check their prices before bringing the car over.
* If you're looking for a very brief bit of exercise before starting the chore.
Verdict: Put the keys in the ignition. You'll be there in about 10 seconds!
Would you like me to check the local weather to see if there's any rain forecast that might ruin your freshly cleaned car?
Also if it's not correct someone else will edit it. But with the LLM it's just the LLM and you, and if you correct it is not like it will automatically be updated for all the users.
I get a dopamine hit with AI by being able to accomplish tasks fast, mostly in frontent or using a dynamic language like python because you see the changes in real time
It's not really about that but more that other countries start regulating the same way as WhatsApp and that way not all people would switch to these apps but they would have the opportunity to use it and keep talking with their friends and family
If it's bad at python the most popular language what language it's good at?
If you see the other comments they're basically mentioning most programming languages
Pretty good at Java, the verbose language, strong type system, and strong static analysis tools that you can run on every edit combine to keep it on the tracks you define
Maybe I should have made it more clear, but it's pretty good if you know how to work with it. The issue is that it's usually faster to just read the documentation and write the code yourself. Depending on what you're working on of course. Like with the yaml, a LLM can write you an ingress config in a second or two from a very short prompt. It can do similar things with Python if you specify exactly how you want something and what dependencies you want.
That's being bad at programming in my opinion. You can mitigate it a lot with how you config you agents. Mine loads our tech stack. The best practices we've decided to use. The fact that I value safety first but am otherwise a fan of the YAGNI philosophy and so on. I spent a little time and build these things into my personal agent on our enterprise AI plan, and I use it a lot. I still have to watch it like a hawk, but I do think it's a great tool.
I guess you could say that your standard LLM will write better Python than I did 10 years ago, but that's not really good enough when you work on systems which can't fail. It's fine on 90% (I made this number up) of software though.
Agree. It’s excellent at python all round. If it lays out things how you want it to is a matter of preference and usually requires prompting it to restructure. That’s the standard way you work with AI code gen though, it’s iterative and requires testing. If you do it well it can be specified up front as a style guide set of instructions
I've had good results with TypeScript. I use a tested project template + .md files as well as ESLint + Stylelint and each project generally turns out pretty clean.
One thing copilot seems to be good at for me is python. Other, older languages like VB.NET I found it struggled with.
I did find (weirdly) that it improved when running on WSL rather than windows.
However I did get it to code a script for downloading SharePoint files and even got it to reduce the dependencies down to built-ins which was a massive time saver
It's terrible. The biggest issue is dependencies, but we've solved it by whitelisting what they are sllowed to use in the pipelines along with writing the necessary howtos.
The thing I should have made clearer is probably that I think the horrible code is great. Yes it's bad, but it's also a ton of services and automation which would not have been made before LLM's, because there wouldn't have been enough developer time for it. Now it being terrible code doesn't mean the sollution itself is terrible for the business. You don't need software engineering until you do, and compute is really cheap on this scale. What do we care their code runs up €5 a year if it adds thousands of euros worth of value?
It's only when something stops working. Usually because what started out as a small thing grows into something where it can't scale that we take over.
Something interesting happened, this is the first time I read him and just after I finish the article and I get into YouTube YouTube recommends me a video from the author with the same title
reply