Hacker Newsnew | past | comments | ask | show | jobs | submit | dyauspitr's commentslogin

Yeah, it’s probably very similar to my experience where I just tried Codex because I had a ChatGPT subscription found it to be quite powerful and then because I was used to it just ended up getting the pro subscription so I am guessing folks like me have never really used Claude.

So what? That might happen one out of 100 times. Even if it’s 1 in 10 who cares? Math is verifiable. You’ve just saved yourself weeks or months of work.

You don't think these errors compound? Generated code has 100's of little decisions. Yes, it "usually" works.

LLM’s: sometimes wrong but never in doubt.

Not in my experience. With a proper TDD framework it does better than most programmers at a company who anecdotally have a bug every 2-3 tasks.

The kind of mistakes it makes are usually strange and inhuman though. Like getting hard parts correct while also getting something fundamental about the same problem wrong. And not in the “easy to miss or type wrong” way.

I wish I had an example for you saved, but happens to me pretty frequently. Not only that but it also usually does testing incorrectly at a fundamental level, or builds tests around incorrect assumptions.


The fact that they might gimp it in the future doesn’t mean it does offer very real world value right now. If you’re not using an LLM to code, you’re basically a dinosaur now. You’re forcing yourself to walk while everyone else is in a vehicle, and a good vehicle at that that gets you to your destination in one piece.

as an overpowered stack overflow machine this is quite good and a huge jump. As a prompt to code generator with yolo mode (the one advertised by those companies) it is alternating between good to trash and every single person that works away from the distribution of the SFT dataset can know this. I understand that this dataset is huge tho and I can see the value in it. I just think in the long term it brings more negatives.

If you vibecode CRUD APIs and react/shadcn UIs then I understand it might look amazing.


Yes, definitely CRUDs but also iPhone applications, highly performant financial software (its kdb queries are better than 95% of humans), database structure and querying and embedded systems are other things it’s surprisingly good at. When you take all of those into account there’s very little else left.

Most of these batteries are on full warranty for 8-10 years. You should definitely make full use of it during that period.

Read the fine print - there is usually a limitation on charging cycles. So battery can be out of warranty even if it's 3 years old but reached limit on charging cycles.

It’s not. For my ford it is 8 years or 100,000 miles whichever comes first. It’s not about cycles.

How are cycles counted if the battery is not drained fully?

Does that warranty still apply if the battery is used for other applications besides it's core function of powering the car?

The car battery warranty is often for X years or Y cycles, whatever comes first.

Yeah, I guessed so. Using it as a home battery with incur a lot more cycles I suppose. Although if the battery is large enough so that a day of powering a home only drains the battery eg. 10%, how does that factor into the cycle count? Is that somewhere in the small print maybe?

I would look at your warranty, mine is 8 years or 100,000 miles. It doesn’t have a cycles stipulation.

The whole phrase is one character?

It's one codepoint, U+FDFD, with the name "Arabic Ligature Bismillah Ar-Rahman Ar-Raheem".

https://www.compart.com/en/unicode/U+FDFD


It’s one code point that’s (in theory) meant to hold the ligature of the whole phrase. As it stands it’s only used as a demonstration of Unicode difficulty.

﷽ translates to "In the name of Allah, the Most Gracious, the Most Merciful."

But it is indeed just the single character (U+FDFD)


> lead to a false positive for 98-99 healthy embryos per 1000 live births.

The number you’re looking for is 9, not 99


Oops... Off by one [order of magnitude]...

In a place like Rome with layers and layers of deep history they should just think of building elevated metro systems.

You are getting downvoted, but Rome is nothing but a museum. It would be empty if not for the tourist attractions.

Of course elevated trains are not good for tourism. Not unless you're Elwood Blues and can get used to the noise.

https://youtu.be/0lL3PODLf_A?feature=shared


The rational thing to do would be to build more data centers. Use that huge influx of money on infrastructure. Make tokens dirt cheap.

You’re going to loose a lot of natural language nuances then. Plus git is essentially your structured, validated state description.

You can do that now. Just ask it to use bad grammar and introduce spelling mistakes and it does.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: