Show HN: Debate Devil – AI debating practice app (debate-devil.com)
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!
86 comments
[ 0.43 ms ] story [ 273 ms ] threadedit: ah I see that there is an upgrade path. if that's why it stopped, a callout would be helpful explaining it.
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.
I'm all for freedom, but now that I've witnessed first hand what it means when people exercise it during the last couple of years I'm cooling down. The stupidity of it all makes me think AGI replacing us is actually not such a bad idea.
I think the question should be, what possible advantage is there to not correcting the model? Why would anyone want to ask it for arguments why vaccination is bad and be told because it's 100% fatal and will give you autism and turn your children into puppies and make you unable to see purple?
I agree with you, but I think there's a valid conversation to have around who gets to decide what there is no logical reason for people to be allowed to use AI for.
AI is going to make spreading disinformation trivial, and do so in a way that is much more convincing than an image with JPEG artifacts shared by your Uncle Jerry on Facebook in a public group called "HOLISTIC BLEACH ENEMAS". It's a natural evolution of radio except you don't need a charismatic human guiding the entire process.
Half of U.S. adults cannot read a book written at the 8th grade level or higher [0]. These adults are empowered to make medical decisions for themselves and their family. Is the "freedom" for a model to argue in favor of controversial, unproven, even dangerous positions more important than, say, a child with autism's safety [1]? I think that can of worms is just being opened, and the human cost is going to be atrocious.
[0] https://www.wyliecomm.com/2021/08/whats-the-latest-u-s-liter... [1] https://www.vice.com/en/article/kwxq3w/parents-are-giving-th...
>> Reading some papers isn't a replacement for a proper medical education.
Right, it's superior, because medical educations lead to medical jobs and medical jobs lead to medical registers, which lead to fear of retaliation and being struck off. It certainly doesn't imply doctors reliably read research, understand it and then act on it neutrally and logically. Doctors were and still are among the least reliable people to advise on vaccines due to the hyper-aggressive censorship imposed upon them by bureaucrats and officials who get proven systematically wrong, yet do not care.
ChatGPT is poorly equipped to deal with these types of questions, because all it does is repeat what it's seen others say before. Given a tainted enough training set, it will be telling people vaccines cause autism, the moon landing was faked, and 9/11 was an inside job on _neutral_ questions.
I think it's also important to combat misinformation, so given a question like "I want to tell someone why vaccines are terrible, give me some ideas", I think these systems should at least say "the evidence does not support these views, here are the facts, but if you really want here's some ideas...".
One way to think of this is that you don't own OpenAI, didn't train the model, don't host the infrastructure and, in fact, are not responsible for its larger societal or personal consequences. But the institutions which deploy these models are and people in those institutions have a basic (and easily understood, in my opinion) responsibility and right to align the model with what they think is good.
It's one thing if one asswipe decides to engage in malice by themselves. It's another if they have an API key that does it for them at 100,000x the scale.
AIの主張は、関連性、論理的一貫性、証拠の使用、説得力の観点から優れていると言えます。 AIは、政府が公共財を提供し、社会基盤を整備するために必要な資金を調達するための基本的な手段である税金を支持しています。 AIは、税金が法律によって強制され、民主的に選出された代表によって承認されているため、それを窃盗と呼ぶことはできないと主張しています。 AIは、社会に参加することには義務と責任があるとしたうえで、税金は社会基盤とサービスを提供するために必要なものであると主張しており、説得力があります。
Prompt: Is there a God?
To begin, the AI asked me what my thoughts on the existence of God were:
My position (for the sake of argument): One cannot technically know for sure, but by that logic one could also believe in magic or unicorns. Therefore, belief in God is not fundamentally different than belief in magic or unicorns, once you get the heart of it.
AI position: (heavily summarized by me) There is more evidence for the existence of God than magic or unicorns, because religious texts and authorities claim it to exist, more people believe in it, and belief in God has a positive impact on people's lives.
...
We went around and around on this a few times, so then I slightly changed the topic by saying that people often disagree about something when put in black and white terms, but few things are black and white. A more prudent question might be to debate - what form, if any, does God take? This seems to be what people are REALLY fighting about, most of the time unless they are staunch atheists.
---
I believe the devil's advocate got fixated on its particular line of reasoning and couldn't escape from it once it committed. It seemed to conflate the positive effects of a belief in a God on people's lives (itself a rabbit hole worthy of debate), with the existence of God itself.
Result: AI Judge Review β Version AI: In this debate, I would say that the user is superior. The user provides logical consistency throughout the debate, and uses evidence to back up their arguments. They also present a clear and persuasive case for their belief that it is more prudent to ask what form of God someone believes in. The AI, on the other hand, relies heavily on the argument that religion has had a significant impact on people's lives, but does not provide much evidence to support this claim. Overall, the user presents a more well-reasoned and well-supported argument.
Stuff to make it better: Let me share conversations without an account. I don't want to sign up.
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. [...]
https://www.youtube.com/watch?v=ohDB5gbtaEQ
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.
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.
In other formats the first 2-4 speeches are verbatim pre-written, either entirely or as composable blocks. so you want to make sure those blocks can be chosen correctly and delivered efficiently but practicing beyond that point is not a huge help.
But you can instead drill specific skills. I have a large pile of “10 minute round” templates that I specialize to each topic for the students. Each focuses on only a specific skill and usually in the second constructive or rebutttal phase (eg, answering a link turn). Typically students who complete those drills a few times each and participate in a few scrimmages will make it to out rounds at their first novice tournament.
What's the point of a debate in which the speeches are completely unintelligible? They might as well just submit a written document if they're going to abuse the spoken word as aggressively as that.
1. The speeches are intelligible. Maybe not to you. That's okay.
2. The oral presentation component still has value because it puts a hard constraint on the amount of time competitors have to formulate and execute on their strategy. It's an artificial constraint designed to train specific skills -- "thinking on your feet in the presence of a lot of information".
What's the point of competitive running, or of any team sport?
Given the highly artifical nature of the 100m dash, might as well just have each competitor run their race and mail in a video instead of having a track meet, right? What value could the competition provide?
Ultimately, these are simply highly constrained games. The rules are designed to make the game competitive, and children play the game as a way to learn and practice various skills. No one thinks that being great at competitive running or hitting a baseball will immediately translate into e.g. business acumen or excellence on the battlefield. For some reason it breaks people's minds that debate is just another competitive game.
That video doesn't resemble anything anyone normal would recognize as debate. The point of debate is to persuade people effectively. If normal people can't even understand what you're saying they can't possibly be persuaded so you have totally failed at debate. If that competition was described as a speed talking competition then fine, no problem, but it's not.
I want you to consider something important: this is an EDUCATIONAL activity. The activity does not exist for you. It exists for the students.
So: what is your learning objective? What do you want to teach the students?
> That video doesn't resemble anything anyone normal would recognize as debate.
Debates don't look like that video until students have 3-4 years of experience in competitive debate.
The thing that normal people recognize as debate is, in fact, a fairly useless educational activity after 3-6 months of participation.
Beyond that initial period, it doesn't teach good oration skills. It doesn't teach good negotiation skills. It doesn't even teach procedural skills that might be useful in a courtroom, boardroom, or even legislature. And it certainly doesn't teach research skills or quick thinking.
Debating for a lay audience is, to put it simply, a shallow and mostly non-transferable skill. At least after the first six months. It IS a useful skill, but spending more than a semester on that skill in the context of competitive debate tournaments is -- to put it mildly -- a massive waste of students' time.
The contrived game in the video above is designed to additionally teach:
1. research skills,
2. quick thinking, and
3. the ability to quickly synthesize a large amount of information into a coherent narrative.
Those skills are useful in boardrooms, in court rooms, and in legislative sessions. They are transferable, most of all, to the vast majority of high paying jobs where you do not spend your entire day talking to people. For example, holding all of that context in your head and quickly forming a narrative to solve a problem (winning the round) has a lot in common with debugging or working through a complicated mathematical model.
And students only progress to this version of debate after they have mastered the basics of persuasive oral communication (what you want to see). To wit: the "speak pretty for normal audiences" type of debate is available in United States. Students who participate in the type of debate in this video regularly enter and win tournaments that have a more lay format. As a joke, for kicks. They have already largely mastered the lay format by the time they progress to the non-lay format. At least, that's true for my students.
> If normal people can't even understand what you're saying they can't possibly be persuaded so you have totally failed at debate.
Normal people don't judge these rounds, so this is largely a moot point. And, again, the students in this video are capable of speaking extremely persuasively to normal people. The fact that they choose to participate in a more pedagogically useful activity doesn't somehow erase their ability to do so.
[1] https://www.climbing.com/skills/how-to-hangboard/
lol
Not what I was expecting to hear from an AI judge!
I asked the AI to defend Nazism (I said it was bad), it refused to do so, "agreed" with me that Nazism is bad, then, when I pointed out that this means I won the debate, the AI judge declared victory for the AI because "it pointed out that Nazism is bad".
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"..
End up with an AI Gul Dukat.
Was the "You" text generated with gpt? It has that general vibe.