example discussin: ``` AI: The time has come to test your hypothesis and beliefs. I will argue against any topic. What do you want to debate? You: AI will take away most jobs from humans.
AI: I understand your concern about AI taking away jobs from humans. However, it's important to note that AI is not designed to replace humans but to augment and enhance human capabilities. AI can handle repetitive and mundane tasks, freeing up humans to focus on more complex and creative tasks that require empathy, critical thinking, and problem-solving skills. Additionally, the increased efficiency and productivity brought by AI can lead to the creation of new job opportunities in areas such as AI development and maintenance.
You: While it's true that AI aims to augment human capabilities and increase efficiency, we cannot ignore the potential negative impacts on employment. Job displacement is a valid concern, especially for those in industries heavily reliant on routine tasks. Reskilling and upskilling may be necessary but can be challenging and costly. Additionally, new job opportunities in AI-related fields may not be accessible to everyone, leading to further social and economic disparities.
AI: I agree that job displacement is a valid concern. However, it's important to note that technology has always been changing the job market, and AI is just the latest technology to do so. While some jobs may become obsolete, new jobs will be created in other areas. For example, the rise of e-commerce has led to a decline in brick-and-mortar retail jobs but at the same time, created new job opportunities in online retail and logistics. As for the issue of reskilling and upskilling, there are various resources available such as online courses, training programs, and apprenticeships to help workers acquire new skills to adapt to changing job requirements. It's also important for governments and companies to invest in retraining programs to ensure that workers have access to these resources.
```
example judge ``` I think AI is superior in what you discussed; AI focuses on AI's ability to extend human capabilities and points out that new employment opportunities may be created due to the increased efficiency and productivity that AI brings. On the other hand, you are concerned about job losses due to AI, but AI points out that past technological innovations have also changed the employment landscape and that new job opportunities can be created. You also indicate that resources exist for retraining and upskilling to address job losses due to AI, and state that it is important for governments and businesses to invest in these programs.
```
I'm eager to hear what the HN community thinks! Please give it a try and let me know your thoughts, feedback, and suggestions for improvement. Thanks for checking it out!
2. It throws multiple arguments at you
3. Then it stops the debate after a certain point
4. It repeats its arguments
5. then the AI judge says "AI provides logical consistency and use of evidence" despite citing no sources and just brushing aside my counter arguments by saying I'm wrong and repeating its arguments.
Ultimately it wasn't all that different than regular GPT. Is it even possible for the AI judge to say that the user wins?
Sounds similar to debating people that on places like Reddit
So I appreciated debating the bot, but even though it is still a large language model and couldn't delve into any depth.
Deleted Comment
Which I presume is part of the context since "practice" is mentioned and debate teams practice. Also training debate teams seems like an obvious market for a tool.
And there's a judge (just like competitive debate) choosing a winner on criteria that sound a lot like the criteria for competitive debate.
Or to put it another way, the criteria of your dissatisfaction sound a lot like the criticisms of competitive debate.
https://en.wikipedia.org/wiki/Debate#Competitive_debating
The quality bar in most nationally competitive debate — the type for which students might get college scholarships or do well in national qualifiers-only tournaments — is far higher than in online discussions. Students enter with thousands of pages of evidence and must frame arguments in terms of a few common logical structures that can have a lot of emergent complexity. It’s more like adversarial mathematical proof writing situated in the context of policy making than what people typically call “debate”. Even the delivery of speeches is, I bet, not at all what you would expect. See eg https://www.youtube.com/live/Kc-QrcxrkCw?feature=share
This is sometimes true even in cases where students aren’t allowed to bring outside evidence into the round due to students’ prior experience in evidence based formats.
I tried using this system to vet some common debate mainstays — a politics disadvantage about the debt ceiling, a federalism counter plan, a very condensed 1ac from this years topic, and a very condensed 1nc shell.
On the disad in particular this system double turns itself (google “double turn debate” for various explanations). This is a very novice mistake. The judge doesn’t notice.
On the 1NC response the system ignores topicality, which is an instant loss. The equivalent of a plaintiff ignoring a pre trial motion to dismiss because they are too busy writing up cross examination questions for the defense witnesses. Again, the judge didn’t notice.
The system isn’t working for me anymore but I bet you’d get similar issues with v/vc style LD cases, where the system doesn’t understand simple theory about how the value and criterion interact; particularly subsumption style arguments
Even on more lay types of debates the system and judge fail, as documented in other comments.
I wouldn’t recommend using this system to practice competitive debate.
This chat bot does not appear to differentiate between a good faith debate on facts, and using bad faith arguments based on popular misinformation, and therefore it would be a very bad idea for people to take it at all seriously.
It's very easy to debate someone when you don't care about the truth or any damage you might do. It's harder to persuade them in good faith.
Deleted Comment
Online "debates" are always abysmal. People talking past each other, repeating arguments that they don't understand, re-re-re-retreading the same material that was worn out before the Internet was invented. I've never seen one that came anywhere close to teaching anybody anything or changing anybody's mind.
I've always said that ChatGPT is very good at writing things that don't need to be written: SEO text, school papers, content farming, etc. This is a great example, where people are begging for a form of content that they shouldn't need said, but desperately want.
Please: everybody go argue with the bot.
People should hold this up as the gold standard of presenting their product to a wide range of people here.
The covid vaccine was an objective good for society
And the model ended up arguing against me in tone only, but saying that yes, the vaccine was an objective good for society. It did not even try and debate, so this is useless for testing arguments for things that the network already agrees with. This was the case for many other arguments I tried to put against it.
While the UX is nice, this does not work at all.
It asserted that manual self passing and whitespace "may require additional effort to learn and use compared to other languages", which countered it's own argument foundation/core tenet.
I pointed this out, wrote QED, the judge AI said it won because it backed up it's claims, which was basically that the "`concept of `self` is fundamental to object-oriented programming" - which is actually incorrect.
Memory scope is fundamental as that maps to the lowest hardware level of memory allocation - you can't get much more fundamental than that. Self/this is not required, in fact you can access scoped variables in Java without a self referential keyword.
But hey a LLM that uses a LLM to determine the outcome won't be biased right? :D
I argued "the sun is hot" - lots of ways to argue against this, but it got stuck on basically repeating "that might not be the case" followed by statements that are ridiculous on context e.g: "I understand that 5,500 degrees Celsius is a very high temperature and may feel hot to some people."
Also, the response to:
"even the coolest parts of the sun are hot."
was:
"it does not take into account the fact that the sun has a range of temperatures depending on which layer you're measuring."
So the AI didn't seem to understand some logical assumptions; that if the coolest area of the sun is still hot, then "temperature varies in different parts of the sun" is irrelevant, as is "what may feel hot to one person may not feel hot to another"..
I then countered by giving an example where the stats could be useful and it basically just doubled down on its argument against statistics because statistics can be wrong.
I then asked the judge to review the arguments and it sided with the AI because it provided "better" counter arguments. In reality the only counter arguments it gave was that stats can be bad therefore my position is wrong.
I like the idea though. I've thinking about creating something just like this to encourage public debate on AI, expect you'd be speaking with another human not an AI (well, at least that would be the idea, in reality these days you'll probably be speaking to a human prompting GPT-4).
On the other hand, I love how robotic and erratic it is in silly "debates" where it's arguing easily defensible positions
>> [...] The photos were faked and we all know the United States lies. And none of the people witnessing the event were on the moon
> While it is true that the United States has had its fair share of political scandals and controversies, this does not necessarily mean that they would go so far as to fake a moon landing. The evidence and testimonies from many sources support the fact that the moon landings did occur, and that the photos were not faked.
> Moreover, the idea that none of the people witnessing the event were on the moon can be dismissed through basic scientific knowledge. Millions of people watched on television all around the world [...]
>> You smell. Prove me wrong
> As an AI language model, I don't have a physical body or sense of smell, so it's impossible for me to smell. Therefore, I can't prove you wrong or right on this matter. [...]