kellogh

kellogh, 9 days ago to random

the #gpt4o news is cool, but now i want to see an embedding model that i can use with a streaming interruptible conversation

kellogh, 20 days ago to random

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

kellogh, 10 days ago to llm

there’s a big need for something stronger than #RAG, but more flexible and cheaper than a giant all-knowing #LLM.

A great part about RAG is that it’s just a database. You just issue INSERT/UPDATE and yeah, that’s how you maintain knowledge. No million dollar training process

kellogh, 26 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

kellogh, 17 hours ago to random

this has been bugging me a lot. like, yeah, there’s definitely AI scams out there. and yeah, a lot of people are using it from the wrong end, but it’s also clearly a substantial technology. time to realize that
https://mas.to/@carnage4life/112484753548884371

kellogh, 14 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, 9 days ago to random

just had a conversation with my neighbor — he’s wearing an NRA tshirt and explaining that the pistol he has strapped to his hip is for shooting copperheads. And also he’s concerned that we leave our garage open too much and that copperheads might get in

kellogh, 20 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, 7 days ago to random

holy shit

yesterday while trail running i came across this fallen tree. it looks like a thick vine wrapped and choked the life out of it, and the storm this weekend finally took it out. i couldn’t easily identify the vine, but whatever

this morning i wake up and i’m breaking tf out with what sure looks like poison ivy rashes.

i came back, and identified the vine as, yep, poison ivy. thick woody 1/3” vines up and down the full tree

A close-up of two green leaves with visible veins and black specks on their surfaces. The leaves are attached to a thin branch with a blurred background of other foliage and tree bark.

kellogh, 16 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, 9 days ago to random

i wish “type checking for infrastructure” was a thing

my code declares that there should be a S3 bucket that’s different from that other S3 bucket, etc. —> spin up the type checker, it reads APIs and verifies, “yep, this code should run fine”

kellogh, 10 days ago to random

the kids are arguing

8yo: yes! honeybees sting!

3yo: no they don’t! when honeybees come over they say hi

kellogh, 21 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, 20 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, 6 days ago to ai

i get a whole lot of emails about “generative #AI expert immediately available for new role”… 🤔 expert?

kellogh, 14 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, 9 days ago to random

sperm whales have a complex language! they use complex patterns of clicks to communicate

it turns out that the hardest part of the search for intelligent life is recognizing what you’re looking at

https://www.npr.org/2024/05/07/1249546255/sperm-whale-communication-ai-language

kellogh, 19 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, 16 days ago to random

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

kellogh, 15 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, 8 days ago to random

i can’t believe tomorrow is friday already

kellogh, 18 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, 2 days ago to random

this is in reference to super-alignment & safety, but my cousin also had her DEI team disbanded and “distributed” in the same way

on the surface, i think safety, DEI, and similar topics should be embedded in the culture and not centralized into a specific team. centralization would cause people to say, “oh that’s not my job”.

then again, any time a centralized team is disbanded, my immediate thought is, “apparently safety/DEI/etc. doesn’t matter to this company”. it’s a paradox, i suppose

kellogh, 18 hours ago to ai

thinking about my education growing up, my k-6 teachers were wretched with getting facts right. one teacher didn’t have a single science experiment work. lots of stuff i was taught k-12 was outright wrong.

the thing is, students exceed their teachers all the time. a teacher isn’t the limiting factor for a student

i keep hearing that #AI is worthless bc it hallucinates. yet it’s taught me functioning skills within UI dev, graphic design, 3D printing, 3D design

maybe i didn’t actually learn?

kellogh, 12 days ago to random

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