Private torrent trackers have been doing this for a while. If some number of your downstreams act like shitheads - you get nipped and so do your other downstreams.
This seems like the best way to handle it. Also, smaller communities. It's cool to do the global thing, but once you have 10k active users you can't moderate it with a team of 5 volunteers.
I think the attestation approach works best if there are different reasons for the punishment. Eg someone inviting a turd doesn't ban the person who invited them. Someone going full ai spam should.
This takes it a step further than what you describe. They keep track of who you’ve invited, who they’ve invited and so on and if there’s enough bad leaves on the tree they just cull the entire tree. It’s a somewhat common practice with private trackers
what.cd was better. You either got an invite where if you tanked your reputation you'd get banned and risk the inviter getting banned too; or you had to take an interview where you got quizzed on how to properly rip music in a variety of methods and how to ascertain between different qualities of rips (like mp3 bitrates to flac cue files).
If you weren't a bellend on what.cd you got access to certain forums where there were even more and better private trackers. Once you built that trust there were social privileges, but if you abuse that trust you got rightfully banned.
> You wouldn't trust an engineer a bridge that an engineer vibe-engineered would you?
If it was as easy to stress test/battery test/materials test/etc a bridge as it is to test code - then yes. I'd trust an engineer who vibe-engineered a bridge.
---
The problem with mapping digital problems into meat-space is that there is inherently a few orders of magnitude of cost automatically added to anything that happens in meat-space.
I can spin up an arbitrary number (10, 10k, 500k) docker instances, X with fuzzed inputs, Y with explicit edge cases, Z with tolerance testing, etc etc. And if that doesn't work - I can fix and push a button and it just happens again.
If a bridge engineer could do that with bridges - yes I'd expect them to be vibing just as hard as we are now.
Absolutely. These days engineers use AI and simulation to design new types of engines, jet nozzles, etc. Treating it not like a tool is the mistake, and the assumption many make is that “other people must be making that mistake too”.
... just force the data into a structured format, then use "hard code" on the structure.
"Generate the following JSON formatted object array representing the interruptions in my daily traffic. If no results, emit []. Send this at 8am every morning. {some schema}. Then run jsonreporter.py"
Then just let jsonreporter.py discriminate however it likes. Keep the LLMs doing what they are good at, and keep hard code doing what it's good at.
> to my Boomer uncle it's incoherent, if not an outright attack.
These are separate things. If he's interpreting it as an outright attack, he _is_ hearing it correctly. But incoherence would imply he's _not_ hearing the coded language in it's true meaning.
You know, I wouldn't be surprised if the AI was less than 50% accurate. I'm not claiming that in general, but I'm also certain it would be possible to construct a dataset such that the AI would do far worse than a coin flip.
You know that it's not possible to do worse than a coin flip, right? If you're getting it 100% wrong, I'll just do the opposite of what you say, and have a 100% correct predictor.
The threshold isn't 50% because the distribution of human and AI written cases isn't naturally 50-50. So a coin flip will underperform always guessing the more frequent class. Where it gets interesting is if the base is unknown or variable over time or between application domains. Like, since AI written text is being generated faster than the human kind, soon guessing AI every time will be 99% accurate. That doesn't mean such a detector is useful.
When we say "coin flip" in these situations we mean "chance", ie the prior distribution. Otherwise a predictor of the winning lottery numbers that's "no better than a coin flip" would mean it wins the jackpot half the time.
Yup! My point is that the 'coin flip baseline' model that's as good as chance isn't actually trivial to create, for an unbalanced and time varying underlying distribution.
I hear this all the time, but to what end? If the input costs to produce most things ends up driving towards zero, then why would there be a need for UBI? Wouldn't UBI _be_ the performative economics mentioned?
I think of it like limits in math. The rate at which we'll be out of work is much higher than the rate at which prices will fall towards zero.
A performative/underemployment economy keeps everyone working not out of necessity, but to appease the sentiments of the wealthy. I'd argue that we passed the point at which wages were tied to productivity sometime around 1970, meaning that we're already decades into a second Gilded Age where wealth comes from inheritance, investment and connections (forms of luck) rather than hard work.
And honestly, to call UBI performative when billionaires are trying to become trillionaires as countless people die of starvation every day just doesn't make any sense.
We had a "smart person only internet". Then it became financially prudent to make it an "everyone internet", then we had the dot com boom, Apple, Google, etc bloom from that.
We _still_ have a "smart person only internet" really, it's just now used mostly for drug and weapon sales ( Tor )
I think the comment was showing that the project takes 9 weeks either way, but coming to that determination was much more confident and convincing with a functional demo versus a hand-wavy figma + guesstimate.
> was much more confident and convincing with a functional demo versus a hand-wavy figma + guesstimate.
Except it also blurs the lines and sets incorrect expectations.
Management often see code being developed quickly (without full understanding of the fine line between PoC and production ready) and soon they expect it to be done with CC in 1/2 the time or less.
Figma on the other hand makes it very clear it is not code.
Which is why I like balsamiq. It looks like hand sketches but can be interactive. I can create any UI for brainstorming in a matter of minutes with it. Once the discussion is settled, we can move to figma for actual UI design (colors, spacing,…).
Which will certainly be granted and thus Better Days *WILL* Come, at least in the localized "I'm taking practically no risk" sense.
reply