purplerabbit
purplerabbit on Hacker News
People are gonna hate this but: we’ll need agents ready and waiting to autonomously patch and deploy instantly
Also a recurring motif with Nick Cammarata from even before the LLM wave.
Love him and hope he's right! But still.
I always find it weird when people declare things “are” rights, as rights are things societies create. “Should be a right” seems like a more appropriate framing
Doesn’t scratch the itch, but I will concede that this is a fair point
I crave an industrial megaproject to solve this. Specifically: A pipeline from the ocean. But alas, only China has a social structure capable of getting projects of this scale done anymore. So I guess I'll keep tracking the AQI and keeping my kids indoors when it's bad.
I'd love to see statistics as well.
My wife self-reports as very happy and talks a lot about how proud she is of the decision. I'll acknowledge that we are privileged in terms of support -- 3 relative families within 30 minutes and most people in a 100 meter radius attend the same church. Even in our setup, however, we really wish we could swing a multi-generational setup and have grandparents around all the time.
Maybe the Amish are on to something!
So confidently stated! My wife had ludicrous options and chose it — what draws you to this conclusion?
And guess why trad household structures are (still) popular in some circles
Something freeing to me that my wife said:
"If you get rid of clutter, there will be cases where you'll have gotten rid of something useful at that moment. It's not about avoiding that -- it's about accepting the right tradeoff between cleanliness and functionality."
Anyone know any interesting OSS Slack alternatives with a decent API?
Posted by
purplerabbit on Saturday February 14, 2026 @10:23AM
from the solveeverything.org dept.
Posted by
purplerabbit on Wednesday February 11, 2026 @01:18PM
from the o16g.com dept.
I know plenty of nondeterministic accountants
The lack of broad benchmark reports in this makes me curious: Has OpenAI reverted to benchmaxxing? Looking forward to hearing opinions once we all try both of these out
You could have to your chat give them direction
Have you checked out t3 stack? Curious which pieces are missing from that that you'd deem critical
Most of us probably do the same thing when we read a HN comment about something specific: "This rando seems to know what they're talking about. I'll assume it as fact until I encounter otherwise."
Not doing this might actually cause bigger problems... Getting first-hand experience or even reputable knowledge about something is extremely expensive compared to gut-checking random info you come across. So the "cheap knowledge" may be worth it on balance.
Just to throw into the mix: apparently sitting in a hyperbaric oxygen chamber does. Who would've thought.
In case you find it interesting: I deployed an early version of a "lesson administering" bot deployed on a college campus that guides students through tutored activities of content curated by a professor in the "study mode" style -- that is, forcing them to think for themselves. We saw an immediate student performance gain on exams of about 1 stdev in the course. So with the right material and right prompting, things are looking promising.
Everyone ITT will hate me for saying this, but: T3 stack.
What model are you personally using in your aider coding? :)
Maybe they just mean for the type of projects they care about
Have you tried drizzle? If so, what's your beef? (The only one I've had is lack of down-migrations)
Sounds like your market is a few years behind the US :)
Seriously, I hope you get honey/cosmic crisps -- they converted me to buying apples regularly.
The tokens could describe a sequence of actions and their consequences vs. blog / forum type content
Posted by
purplerabbit on Tuesday October 01, 2024 @01:12PM
from the self-post dept.
Stupid question, but if we want models that are capable of doing things (agents) vs just spitting out interesting content, why isn't anyone training them on data that represents actions?Models are incredible at generating analytical / blog-ish / stack overflowish content, but suck at doing things that are complex enough that they require iteration.For instance: If we want models that can handle...
"Who could it be... Hmm... Such a tough nut to crack..."
(Even without a report on this it would be obvious)
Sponge bath lying down in insulated closet is safest option
Your comment is written as though the universe is something outside of ourselves.
Our perception of the universe is part of the universe.
We exist in the world and are a part of the world.
Learning to think in new ways can be a powerful force.
Self-taught sweng here. (And late self-taught -- didn't really start learning programming until age 21.) Early in my first job, I was asked to design a simple query language and create an interpreter for it. I had absolutely no idea what was involved in interpreters.
I found your book online (it was less complete back then -- this was 2017), and in 3 or 4 days I had a working prototype. In another week or two, I had a working product. Thank you so much for creating this resource -- learning from it and leveraging it gave me a huge confidence boost, and was super interesting and fun. One of the very best resources I've come across. I still reference that project as one of my very favorite I've ever worked on. Best wishes