Copilot is notoriously bad. Have you tried (paid plans) codex, Claude or even Gemini on your legacy project? That's the bare minimum before debating the usefulness of AI tools.
"notoriously bad" is news to me. I find no indication from online sources that would warrant the label "notoriously bad".
https://arxiv.org/html/2409.19922v1#S6 from 2024 concludes it has the highest success rate in easy and medium coding problems (with no clear winner for hard) and that it produces "slightly better runtime performance overall".
> Have you tried (paid plans) codex, Claude or even Gemini on your legacy project?
This is usually the part of the pitch where you tell me why I should even bother especially as one would require me to fork up cash upfront. Why will they succeed where Copilot has failed? I'm not asking anyone to do my homework for me on a legacy codebase that, in this conversation, only I can access---that's outright unfair. I'm just asking for a heuristic, a sign, that the grass might indeed be greener on that side. How could they (probably) improve my life? And no, "so that you pass the bare minimum to debate the usefulness of AI tools" is not the reason because, frankly, the less of these discussions I have, the better.
I'm saying this to help you. Whether you give it a shot makes no difference to me. This topic is being discussed endlessly everyday on all major platforms and for the past year or so the consensus is strongly against using copilot.
If you want to see if your project and your work can benefit from AI you must use codex, Claude code or Gemini (which wasn't a contender until recently).
> This topic is being discussed endlessly everyday on all major platforms and for the past year or so the consensus is strongly against using copilot.
So it would be easy to link me to something that shows this consensus, right? It would help me see what the "consensus" has to say about the known limitations of Copilot too. It would help me see the "why" that you seem allergic to even hint at.
Look, I'm trying to not be close-minded about LLMs hence why I'm taking time out of my Sunday to see what I might be missing. Hence my comment that I don't want to invest time/money in yet-another-LLM just for the "privilege" of debating the merits of LLMs in software engineering. If I'm to invest time/money in another coding LLM, I need a signal, a reason, to why it might be better than Copilot for helping me do my job. Either tell me where Copilot is lacking or where your "contenders" have the upper-hand. Why is it a "must" to use Codex/Claude/Gemini other than trustmebro?
Allowing politics on HN doesn't mean discussing politics in every thread. If it's a story about someone who improved performance of their system by using Rust then sure there's no need to bring anything political. But threads about Nvidia, Tesla, encryption, internet blackouts, social media, startups investments, etc, all warrants political discourse.
I wish that were true, but in my experience so far, it isn’t.
Not only does politics and general stories crowd out everything else over time on other sites, there are HN submitters who seem to be trying to accelerate this.
During the war, when HN was getting Israel-Palestine stories constantly, I started looking at the submission history of some of the submitters, and some of them were just pushing these types of stories every day for months and months.
So yes, I think allowing politics will eventually mean being dominated by politics and general interest.
Globalizing the intifada means pushing an agenda everywhere, including on HN, on posts where it is relevant and on posts where some obscure or conspiratorial connection can be made.
If HN is going to allow accusations to be slung against groups of people it has to allow others to respond, and that sets off endless debate amongst people who will not be changing their minds on the matter but will repeat the same argument on the next post.
Every Israel Palestine story was like that. Just hundreds of back & forth exchanges of fire that could be copy pasted from the last story, along with copious complaints that HN was censoring them even though the story was on the front page. Just a complete waste of time, and very dishonest & unserious people.
Conversely it's true for the parent comment. Being able to eat food from any country is a plus only to those who are into that hobby. Personally it ranks pretty low in my list of things that make a city a great city. And if we're talking about food, access to fresh, high quality and affordable produce is way more important than being able to eat Afghan food at 3am. These criteria are arbitrary and don't make a city better than another imho.
Completely agree. "All food of the world at 3am" wears out pretty quickly. Much higher priority for me is access to fresh fruit, vegetables, fish, and meat at a good price.
And we've seen what allowing people to promote hate speech with no restraint does to a nation.
When it's over, and it will be, Americans need to start from scratch, iterate and write a new constitution, create new institutions and build a new system.
We've also seen what very rigid hate speech policing does to a nation in Germany... and AfD seems to be doing pretty well.
It's almost as if those laws are mostly just performative bullshit that doesn't actually prevent the spread of violent ideologies when the environment is conductive to them.
Fair, but we need to account for the influence of the 1st-amendment-propelled far right discourse in the US on German politics to know how (in)effective German speech laws are.
And some HN users are being paid a lot of money to write software that facilitates the actions of this administration and/or further destabilizes democracy.
One problem is the billionaires themselves. It's too much power and influence in the hand of a single person. They can fun newspapers at loss and have them spread any kind of lies or narrowly biased news for decades.
Billionaires would be less of a problem in a world where we'd all be multi millionaires.
reply