Clever indeed. This is why I believe AI will become the anti-Christ.
It's just a matter of choosing the most creative of the AI systems available to carry forth that role in the most impressive manner.
School vouchers are a controversial topic in education policy, with arguments on both sides of the issue. Here's a balanced look at some of the main points of debate: Arguments in favor of school vouchers:Arguments against school vouchers:
- Increased school choice: Vouchers allow parents to choose the best school for their children, whether public or private, which can lead to better educational outcomes.
- Competition and innovation: Vouchers can encourage schools to compete for students, potentially leading to improvements in education quality and innovation in teaching methods.
- Opportunities for disadvantaged students: Vouchers may provide low-income families access to better-performing schools they otherwise couldn't afford.
Ultimately, the effectiveness of school vouchers likely depends on the specific design and implementation of the program, as well as local contextual factors. Policymakers must carefully consider the potential benefits and drawbacks in crafting voucher policies. As an AI assistant, I don't take a strong stance on this complex issue, but rather aim to present the main arguments on both sides of the debate.
- Diversion of public funds: Vouchers divert public tax dollars to private schools, which may not be accountable to the same standards as public schools.
- Potential for increased segregation: If more advantaged families use vouchers to leave public schools, it could lead to increased socioeconomic and racial segregation in schools.
- Lack of evidence for improved outcomes: Some studies suggest that voucher programs do not consistently lead to better educational outcomes for participating students.
- Constitutionality concerns: Vouchers used for religious schools might be seen as a violation of the separation of church and state.
You still don’t get it. It isn’t “the programmer”. It is the trainer behind the curtain, who selects and curates the training data set and retrains it if they don’t like how it sounds. If you train using the New York Times, the Economist, and Twitter pre-Musk, and then re-train using knobs the programmers have been pressured to provide, you get this.
Lack of debuggability and exact tracibility of the source of of false results, and the inability to pin responsibility to a person, even given the source code, is not a bug, its a feature.
If you think of what AI does as “if I asked XXX of a YYY person, what would it sound like” you understand how it can make up facts and accept huge cognitive dissonance.
When the governments, Big “Tech” social media, and congress paniced and started having discussions of “AI Safety”, the training sets and acceptable output were what it was about.