kellogh

kellogh, 17 hours ago to random

actually yeah, now that all the white moms and dads are smoking pot, might as well make it more legal

kellogh, 1 day ago to fediverse

so is #ActivityPub basically just bidirectional #RSS?

kellogh, 1 day ago to random

the power of wanting to gtfo https://noc.social/@todayilearned/112414756941559961

kellogh, 3 days ago to python

what's the word when, in #python, the declared types are wrong, so you have to butcher the code with assert statements? dark types?

kellogh, 3 days ago to random

are there mastodon clients that are scriptable?

i keep wishing for something good, like @ivory, but extremely customizable that lets me display toots differently, or filter in non-standard ways, or include links to resources that others might not find useful

kellogh, 3 days ago to LLMs

i used an analogy yesterday, that #LLMs are basically system 1 (from Thinking Fast and Slow), and system 2 doesn’t exist but we can kinda fake it by forcing the LLM to have an internal dialog.

my understanding is that system 1 was more tuned to pattern matching and “gut reactions”, while system 2 is more analytical

i think it probably works pretty well, but curious what others think

kellogh, 3 days ago to ai

Experiments and discussion of various UX approaches to displaying #AI code generation suggestions

Personally, the big problems I have with #copilot are

• “this change is crap, except this line here, give me just that”
• changes that are poorly integrated into the file
• the chat never has the right context, so conversations tend to be circular or unhelpful

https://austinhenley.com/blog/intellicode.html

kellogh, 3 days ago to random

Left: what Trump thinks the Bible says
Right: what the Bible actually says

quote: 38 “You have heard that it was said, ‘Eye for eye, and tooth for tooth.’[a] 39 But I tell you, do not resist an evil person. If anyone slaps you on the right cheek, turn to them the other cheek also. 40 And if anyone wants to sue you and take your shirt, hand over your coat as well. 41 If anyone forces you to go one mile, go with them two miles. 42 Give to the one who asks you, and do not turn away from the one who wants to borrow from you.

kellogh, 4 days ago to stackoverflow

i wonder what the thinking is, for #stackoverflow to sell their data to #openai

on the one hand, it feels a lot like the company is being stripped for parts. on the other, openai was probably doing it anyway, so now at least they get paid for it

either way, this seems like a new era

kellogh, 5 days ago to random

y'all are debating println debugging and i'm over here like

kellogh, 5 days ago to LLMs

has anyone made a successor to fuckit.js that uses #LLMs?

(fuckit.js ran the script in a loop, randomly deleting lines until it runs successfully)

kellogh, 6 days ago to random

with our kids, we have this thing where you can do anything as long as you’re prepared

play in the rain? sure, just wear rain jacket/pants/boots

there’s poison ivy in the woods? that’s fine, you know how to identify it, and we have PI soap to wash it off if you miss some

the philosophy is to redirect them into the right way, rather than banning the wrong way. it gives us a lot of freedom in how we travel and experience new things

kellogh, 6 days ago to random

most people don’t know this but there’s a type of antelope in Wyoming that can jump higher than a house! it sounds crazy, but it’s mostly because of it’s powerful hind quarters but also because houses don’t jump

kellogh, 7 days ago to random

this morning i had to exfiltrate a small animal demon from my house

it was hot, so i opened all the doors, to let cool air in. my wife suggested turning the fans on

later, after shutting the doors, i was working on a parser bug, deep in concentration, when i thought i heard someone

i walked around, nobody on the first floor, but i heard an eerie noise on the second floor. at the top of the stairs, i discovered it! flailing in all directions

kellogh, 8 days ago to LLMs

this is such a puzzling perspective

1. #LLMs will be useful
2. i will judge you for trying to use them

i generally regard, “i will think less of you” type comments as a joke, because of how ridiculous the sentiment is, but this sort of stuff is perverse on the fedi

kellogh, 8 days ago to random

with this new definition of “anti-semitic”, is it possible to discuss israeli politics without being anti-semitic?

kellogh, 9 days ago to random

This is cool. A lot of people misunderstand what “real time” means — generally, “late is an error”. For example, he wants to use it in games, where at 60 fps, you have 16.6ms to do all computations and render the screen. Lateness causes lag. Or worse, in a fly-by-wire steering system, late means difficulty steering a multi-ton vehicle.

in a RT system, you need to be able to statically calculate how long all compute will take. Most memory allocators don’t work like that

https://github.com/pcwalton/offset-allocator?tab=readme-ov-file

kellogh, 9 days ago to random

a cool aspect of using LLMs as a tutor is you can test your understanding of a topic, and in the process of validating your understanding, the LLM will also trigger aspects you haven’t thought of yet. So it ends up acting kind of like a rabbit hole, except you end up a lot closer to where you started, just with a much deeper understanding

kellogh, 9 days ago to LLMs

alright, i have to declare this as a strong opinion — #LLMs are better at alt-text than people are

the goal of alt text is to let a person “without eyes” see the picture, to get the same experience as someone who can see fine

but often, almost always, human-written alt text is either too succinct to be helpful, or just an extension of the post itself, and so doesn’t help an impaired person understand what’s in it

kellogh, 9 days ago to random

we all knew is was going to happen eventually https://www.theonion.com/tesla-lays-off-entire-team-behind-brakes-1851449223

kellogh, 9 days ago to random

wife: …and you can add some chicken to it to…ya know

me: you were going to say, “beef it up”, weren’t you

wife: yeah, kinda

kellogh, 10 days ago to LLMs

i've been getting into the things #LLMs can't do well, because i think it says a lot about what they're useful for, and it helps build a mental model around how they work

kellogh, 10 days ago to random

this is a terrible idea show me more https://borgo-lang.github.io/

kellogh, 11 days ago to random

one of my biggest weaknesses is not realizing quickly enough that i’m talking to a boomer that’s not going to give me an adequate response in text, and that it’s gonna take a meeting to resolve this one

kellogh, 14 days ago to llm

i low key don't want to see a big jump in #LLM or #AI capabilities anytime soon. rn they're capable enough that my mom wants to use them, but bad enough that even she has an intuitive sense for when they're wrong

that's how you build "AIQ", the skill of using it. Lots of people toying with them, to feel out their capabilities and limitations