Comments URL: https://news.ycombinator.com/item?id=47710499

Points: 3

# Comments: 1

I also can't believe how tedious cutting fabric is. Even for a tiny project like this it was such a pain in the ass. Even with nice circular cutters and mats and rulers. I'm now tempted to get a cricut 4 to make the cutting easier.

I've got a version of this now in my front pocket for like 9 months: https://share.zight.com/wbu487ew Yes, it's big, but it's the most comfortable from of a big wallet.

It's funny though. I can't help feel the pull to try and make the hobby a business. But then it probably becomes unfun. But my brain just can't not think that way.

Also, is this something that's a pain in the ass to manage multiple versions of the model? One (maybe more in draft mode) for each client?

fintuneing seems to be out of fashion (if it were really ever in fashion), but I still see folks like Karpathy mention reaching for it as a tool.

But is anyone in any business capacity on here doing that? Are you finetuning any remote LLM or something self-hosted? What for?

I’m just curious where the line is of “oh this is better encoded in the models weights rather than in RAG/thinking over context stuff it needs to figure out.

Comments URL: https://news.ycombinator.com/item?id=47678862

Points: 4

# Comments: 3

I think the gist is: sure, we humans can't conceive of getting to anyone else in the universe in any timescale, but if we can keep ourselves from destroying ourselves, we'll eventually figure it out. And we'll spread. And we'll kill everything that isn't us in the process as we've done as explorers on this planet.

So really in 3BP: it's inexpensive to eradicate. But insanely expensive to possibly get the intention wrong of any other civilization you encounter. They might kill you.

(again, this is just my interpretation of what 3BP said)

Anthropic has a Chrome extension, but my daily driver is Safari. So I made my own extension.

It's not a clone as I've never used the Chrome version. One obvious change: the Chrome version I believe uses Chrome "request sidebar" thing. And Safari doesn't have that, so had to inject the sidebar right in the site html itself.

There's been some fun things in here like figuring out the sidebar html/css sandboxing. Also there's an agent mode where I added domain change alerting (amongst other antagonistic hidden prompt protection things) to hopefully avoid XSS/CSRF type problems.

I've debated so much about this like: just open sourcing it, putting it on the app store, and who the audience even is. Is it me? So someone who can easily get an API key but then who can maybe just take a crack at building their own. Or is it my non-developer wife, who'd totally get value from it, but now has to get a friggin API key :(

But yes, I landed on just trying to sell it for $29 a year with a 7 day free trial. I saw when I was running Highrise people took the trial most seriously when it was credit card up front.

Comments URL: https://news.ycombinator.com/item?id=47288461

Points: 1

# Comments: 0

but the big thing I have in here is simply a cross domain check. if the domain is about to be navigated away from, we alert the user to changing domains. this is all in a browser context too so a browsers csrf protection is also being relied on. but its the cross domain navigation i'm really worried about. and trying to make sure i've gotten super hardened. but this is the trickiest part in a browser admittedly. i feel like browsers are going to need a new "non-origin" kind of flow that knows an agent is browsing and does something like blocking and confirming natively.

Comments URL: https://news.ycombinator.com/item?id=46902112

Points: 1

# Comments: 0

i was working for months on an entity resolution system at work. i inherited the basic algo of it: Locality Sensitive Hashing. Basically breaking up a word into little chunks and comparing the chunk fingerprints to see which strings matched(ish). But it was slow, blew up memory constraints, and full of false negatives (didn't find matches).

of course i had claude seek through this looking to help me and it would find things. and would have solutions super fast to things that I couldn't immediately comprehend how it got there in its diff.

but here's a few things that helped me get on top of lazy mode. Basically, use Claude in slow mode. Not lazy mode:

1. everyone wants one shot solutions. but instead do the opposite. just focus on fixing one small step at a time. so you have time to grok what the frig just happened. 2. instead of asking claude for code immediately, ask for more architectural thoughts. not claude "plans". but choices. "claude, this sql model is slow. and grows out of our memory box. what options are on the table to fix this." and now go back and forth getting the pros and cons of the fixes. don't just ask "make this faster". Of course this is the slower way to work with Claude. But it will get you to a solution you more deeply understand and avoid the hallucinations where it decides "oh just add where 1!=1 to your sql and it will be super fast". 3. sign yourself up to explain what you just built. not just get through a code review. but now you are going to have a lunch and learn to teach others how these algorithms or code you just wrote work. you better believe you are going to force yourself to internalize the stuff claude came up with easily. i gave multiple presentations all over our company and to our acquirers how this complicated thing worked. I HAD TO UNDERSTAND. There's no way I could show up and be like "i have no idea why we wrote that algorithm that way". 4. get claude to teach it to you over and over and over again. if you spot a thing you don't really know yet, like what the hell is is this algorithm doing. make it show you in agonizingly slow detail how the concept works. didn't sink in, do it again. and again. ask it for the 5 year old explanation. yes, we have a super smart, over confident and naive engineer here, but we also have a teacher we can berate with questions who never tires of trying to teach us something, not matter how stupid we can be or sound.

Were there some lazy moments where I felt like I wasn't thinking. Yes. But using Claude in slow mode I've learned the space of entity resolution faster and more thoroughly than I could have without it and feel like I actually, personally invented here within it.

Comments URL: https://news.ycombinator.com/item?id=46797862

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46636004

Points: 1

# Comments: 0