> "The government has the right and responsibility to shut down sources of misinformation in the news and online."
Funny that I read this as AuthLeft coded (specific to Youtube suppression of Covid truthing). But obviously the alignment is just a function of whatever specific information is labelled "mis".
Long ago a friend of a friend described a job interview at an ice cream / chocolate shop in a local mall.
The interviewer asked something like "who is our competition here?", and the friend of friend listed off other places in the mall to get ice cream, candy, deserts, etc.
Wrong answer. The ice cream and chocolate store was in competition with every other store in the mall. Time or money spent at the GAP can't be time or money spent here.
---
Whether or not people are using LLMs for news specifically, any new, large eater of eyeball-time is going to hurt the business landscape for all other eyeball harvesters.
> If package X is of sufficient public interest (user count, nature/sensitivity of user data, downstream distribution, etc), then the public interest + cryptographic credentials should permit access to best-available security auditing.
Your private fork doesn't meet the conditions described.
This is a credentials and access list oAuth style problem, and not really intractable.
For package X, I should be able to present my npm (homebrew, apt, nuget, etc) credentials with publishing rights for the package.
If package X is of sufficient public interest (user count, nature/sensitivity of user data, downstream distribution, etc), then the public interest + cryptographic credentials should permit access to best-available security auditing.
Yes, we still are trusting trust, that the owner of the package itself is not malicious, but that's not a sharp degradation from status quo.
I think that as simple as is doing a lot of work when the problem domain is all natural language (or more - all strings?) rather than some well specified DSA problem.
With this framework, I'm making (among other things) an early literacy app at https://letterspractice.com. My aim here is to hit >= 75% efficacy of Mentava at <= 1% of the price.
The app is near to production readiness, and I'd be happy to share access now with anyone who has verbal but non-literate kids. Be in touch if interested at colin at letterspractice.com
People may perceive you to be cheaply mischaracterizing the argument.
Nobody believed or suggested that GPT2 could do longform or produce novel text that stood up against careful scrutiny as insightful or well informed. But because the capabilities were novel, people would have no strong alternative than to believe some person wrote it.
You current tripping over LLMisms is irrelevant. You have years of antibodies, both personal and herd-immunity (eg, the many, many articles and comments that describe LLMisms).
At that time, nobody believed a dead internet was technically feasible. Maybe this is hard to remember now.
The "danger" was in terms of spam / misinformation proliferation, not the same category of capabilities adjacent risks current discussed.
You can hold your own opinions on spam/misinformation as a problem, but to say there was no credibly anticipated outsized downside to a sudden jump in human-passing text generation feels pretty off to me.
> Automation doesn't make operators more careful. It makes them forget how to be. The more reliable the system, the less ready the human.
The entire premise of a system is that it removes the need for careful attention.
system: signal lights tell me whether or not I can pass through an intersection, so that I do not have to attend to potentially high speed traffic from a variety of directions.
system: the side my knife blade sits on my arched guide fingers, so that I do not have to attend to the edge of the blade or the location of my fingers.
I'm no decision theorist but I think they should wait for the rewards outweigh the expected harms in expectation rather than being statistically equal.
Working on FOSS and user-friendly alternatives to things like khanacademy, anki, MathAcademy, Alpha School, etc.
Modern, open edtech tooling.
Also http://paritybits.me