Hacker Newsnew | past | comments | ask | show | jobs | submit | gHA5's commentslogin

You can change the units in the settings, accessible from the start screen

Do you not experience LLM generated code constantly trying to use Pandas' methods/syntax for Polars objects?


Yes, ChatGPT 5.2 Pro absolutely still does this. Just ask it for a pivot table using Polars and it will probably spit out code with Pandas arguments that doesn’t work.


There were some growing pains in gpt-3.5 to gpt-4 era, but not nowadays (shoutout to the now-defunct Phind, which was a game changer back then).


The fact they pivoted away from their very compelling core offering (AI stack overflow) to complete with loveable etc in the "AI generated apps" giant fight continues to baffle me. Though I guess model updates ate their lunch.


My guess is that their pivot came after distress, and was not the cause of it. It'd be great to have @rushingcreek write a post-mortem. I think it'd benefit a lot of people because I honestly don't have a monday morning playbook of what could have saved them.

Like you said, perhaps the demise of phind was inevitable, with large models displacing them kind of like how Spotify displaced music piracy.


Are you using Pydantic AI for structured output? If so, have you also tried instructor?


`outlines` (https://github.com/dottxt-ai/outlines) is very good and supported by vLLM as a backend structured output provider (https://docs.vllm.ai/en/v0.8.2/features/structured_outputs.h...) for both local and remote LLMs. vLLM is probably the best open source tooling for the inference side right now.


I did look at instructor and probably for structured output pydantic-ai and instructor are about the same, but pydantic-ai supports a ton of other stuff that isn't part of instructor's feature set. For me killer apps were the ability to serialize/deserialize conversations as json; frictionless tool-calling; and ability to mock the LLM client for testing.


I personally just switched to https://docs.boundaryml.com/guide/comparisons/baml-vs-pydant...

just feels a bit more polished. especially testing part.


Haven't tried balm, I will give it a shot, I am really curious to see all the features it supports.


Have you considered whether this is because of the local weather tendencies? I visited the Netherlands once in summer near Amsterdam, and there were short bursts of rain frequently throughout the day. I'd imagine weather patterns like that are not well represented in global weather apps lowering the prediction accuracy in such regions.


As far as I can tell, it's largely a data or modeling problem.

Weather radars exist in most of Europe, including all of Western Europe. What's missing is somebody actually getting that data (which is not open in all countries) and feeding it into a short-term precipitation prediction model like Dark Sky (now Apple) does in a few regions.

Currently, in regions where it's not available, I just do that manually: Look the rain radar data for the last hour or so and extrapolate linearly based on wind direction. You'll miss rain that's just starting or stopping or sudden changes in wind direction, but it's much better than what many apps offer.


Remote Desktop Protocol protocol


The underlying text generation should be made aware that it can make sounds. It told me it can't.

Also for proper emotional dialogue it needs to determine the human input emotions. It seems to work with a transcript of the input.


So you got the impression he didn't like the paintings? He seemed to be moved by them to me.


It was pretty obvious he didn’t like them IMO. He didn’t even hang them, he put them away as hidden as he could.


The exchange in looks he had with Natalie character right after the board dropped off the call was clearly also an indication of dissatisfaction from both of them.


MCDONALD'S!


For those unaware, OP is referring to Sony patent US8246454B2 which describes a system in which people can skip ads by e.g. shouting out the brand name of the ad.


https://i.imgur.com/OPbRxhK.png

I love (hate) that the figure in the illustration stands up with his arms raised. I wonder what the artist was thinking...


I have always felt uneasy about that too. I think it’s because the next (and final) panel looks exactly like the first. It’s the implication that you’ll have to do something so over the top as getting up, raising your arms, and shouting a brand name, then resuming what you were doing as it that were completely normal.


You have to show exuberance when demonstrating your brand loyalty, otherwise you’re not loyal enough to pass the ad. You’ll need to watch the entire reeducation, I mean ad, in that case.


I'm glad to see this website working again, years ago it broke because they couldn't afford Google Maps costs.


He's probably talking about split brain patients. Here's a video by CGP Grey about them: https://www.youtube.com/watch?v=wfYbgdo8e-8


Yep.


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

Search: