luckydata

absolute freedom of speech is not a value or constitutional right in most european countries. I don't understand why americans can't get comfortable with the notion that other countries have different laws. There's plenty of things that could be considered bizarre and arbitrary in the US form the perspective of a european, I know full well being one living in California for 20 years.

the downvotes are just further proof of how stupidly this kind of discussion is handled on hacker news. It's demoralizing the lack of quality this community shows lately.

they aren't trying to hide anything, those are accounting rules that are applied to the letter. I'm feeling like I'm taking crazy pills whenever I see this stuff about AI, your hate boner for a specific technology shouldn't trigger you saying things that are provably untrue.

I am based in California unfortunately otherwise I would have gladly accepted.

this project is a monument to the HUGE failure of the Workspace team at Google to enable agent editing in a way that makes sense.

Google is really shitting the bed in all the way that matters on GenAI and being an ex employee of Cloud I am not in the least surprised about it, just really sad.

not in any way that matters, no. this is a strawman and a really bad one too.

you must be very unlucky

given enough time and tokens, it will become that. I really don't understand how that is a problem in any way.

meh, in my experience good quality LLMs are significantly more correct than Stack Overflow ever was and have access to your code and machine to help you diagnose issues.

the message you replied to implied the exact opposite.

the brand the author of the article points at as "good" makes me want to vomit, my wife receives a large quantity of it every year from a service provider she works with as a christmas gift and it's my job do melt it and dump it down the drain since nobody in the family can stand it.

I'm open to suggestions!

that website is doing itself no favor. I could read the whole thing and still didn't fully understand what they are selling.

Everyone makes mistakes. I think OPs problem might be more in how he analyzes, internalizes and reacts to mistakes. I hope he can fix his problems and move on with his life, as a person living with ADHD I can empathize with feeling "broken" and not equipped for corporate life and in a way I am not, but I'll keep going until my energy allows me because... I have no other option. Good luck to everyone out there.

which cheap models have you found work best as agents?

I think the comments on AI related projects are filled with negativity and uninformed opinions and I too find the atmosphere around here pretty off-putting lately.

As an immigrant I thought for a while now that all ice cream in USA taste like shit, despite my wife saying I'm imagining things... Now I know why.

what is the utility of alfaalfa? Because as it stands it's essentially just a way to export enormous amounts of water from a place where there's little (California) to a place where there's none (the Arabian peninsula).

This is bullshit to be charitable.

some might call it "perspective"

oh poor babies they got sad their human sacrifices didn't work, that's surely as much punishment as losing your livelihood because a pack of morons act randomly based on feels.

Just no, this isn't a thing at all.

I really like Anthropic, they have gotten a lot right but I can't shake the feeling that IMHO they have very poor product management.

This stuff is something that as a PM I KNOW is going to happen and I would carefully plan around. Everything I read about the PMs at Anthropic makes me believe they have forgotten what it actually mean to be a good product manager, it's not about throwing shit at the wall as fast as possible because customers have a limited amount of patience before the constant churn becomes a hassle.

Anthropic has some seriously patient customers but it will not last forever.

I'm so tired of this guy

that 28% is what, 3 people?

you just need the right tools https://github.com/CaliLuke/loom

no discussion was needed, it was a statement. the tone is dismissive because the video deserved it.

let's benchmark a truck for doing track days. pointless.

so you're saying Google DOESN'T have wildly successful products? That's definitely a hot take.

you do not. Just build the right tools as you go. A small example of one of the pieces of my toolchain: https://github.com/CaliLuke/lagotto

it's not a solved problem but it's not impossible to keep it at bay either. I created this tool for my own project and it does a pretty darn good job at keeping the AI accountable, I have a harness that runs this in a loop and helps refactor as we go like humans do anyways:

https://github.com/CaliLuke/lagotto

this review was essentially pointless, they reviewed the card for a ton of workloads nobody in their right mind would pick it for, and left out the only use case where it makes sense. great job?