TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: Debate Devil – AI debating practice app

84 pointsby ngkwabout 2 years ago
Hi HN community! I am excited to share my recently upgraded website, DebateDevil (<a href="https:&#x2F;&#x2F;debate-devil.com" rel="nofollow">https:&#x2F;&#x2F;debate-devil.com</a>), an AI chat platform designed to help users practice debates, challenge their ideas, and expand their thinking. I created this site to provide a more objective opinion and help users consider their hypotheses from multiple perspectives.<p>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.<p>AI: I understand your concern about AI taking away jobs from humans. However, it&#x27;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.<p>You: While it&#x27;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.<p>AI: I agree that job displacement is a valid concern. However, it&#x27;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&#x27;s also important for governments and companies to invest in retraining programs to ensure that workers have access to these resources.<p>```<p>example judge ``` I think AI is superior in what you discussed; AI focuses on AI&#x27;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.<p>```<p>I&#x27;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!

34 comments

Brendinoooabout 2 years ago
1. I have a character limit, it doesn&#x27;t<p>2. It throws multiple arguments at you<p>3. Then it stops the debate after a certain point<p>4. It repeats its arguments<p>5. then the AI judge says &quot;AI provides logical consistency and use of evidence&quot; despite citing no sources and just brushing aside my counter arguments by saying I&#x27;m wrong and repeating its arguments.<p>Ultimately it wasn&#x27;t all that different than regular GPT. Is it even possible for the AI judge to say that the user wins?
评论 #35569909 未加载
评论 #35569694 未加载
评论 #35569793 未加载
评论 #35569822 未加载
评论 #35572653 未加载
danpalmerabout 2 years ago
It just spouts fake news and propaganda, and then seems to get stuck in a loop when its challenged in a way it can&#x27;t respond to.
评论 #35569227 未加载
评论 #35569363 未加载
评论 #35569384 未加载
jfengelabout 2 years ago
I think this is genius. Thank you. This is the best use I&#x27;ve ever heard of for an LLM.<p>Online &quot;debates&quot; are always abysmal. People talking past each other, repeating arguments that they don&#x27;t understand, re-re-re-retreading the same material that was worn out before the Internet was invented. I&#x27;ve never seen one that came anywhere close to teaching anybody anything or changing anybody&#x27;s mind.<p>I&#x27;ve always said that ChatGPT is very good at writing things that don&#x27;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&#x27;t need said, but desperately want.<p>Please: everybody go argue with the bot.
user00012-ababout 2 years ago
Setting the actual product aside for a moment, I must commend this as one of the most outstanding demonstrations I have encountered on Hacker News in recent memory. The seamless user experience, which required no login, provided clear and concise information about its functionality, and operated flawlessly upon first interaction, is truly impressive.<p>People should hold this up as the gold standard of presenting their product to a wide range of people here.
评论 #35571343 未加载
mrjbq7about 2 years ago
It won’t actually argue all sides of an issue. Take any controversial one, and it stays inside its guardrails no matter which opinion you want it to counter.
评论 #35569292 未加载
评论 #35590566 未加载
SillyUsernameabout 2 years ago
The AI&#x27;s core tenet to my assertion &quot;Python is an awful language for beginners&quot; (due to whitespace formatting and having a non transparent &quot;this&quot;-self- having to manually be passed around as arguments) was that it was due to its &quot;simplicity&quot;.<p>It asserted that manual self passing and whitespace &quot;may require additional effort to learn and use compared to other languages&quot;, which countered it&#x27;s own argument foundation&#x2F;core tenet.<p>I pointed this out, wrote QED, the judge AI said it won because it backed up it&#x27;s claims, which was basically that the &quot;`concept of `self` is fundamental to object-oriented programming&quot; - which is actually incorrect.<p>Memory scope is fundamental as that maps to the lowest hardware level of memory allocation - you can&#x27;t get much more fundamental than that. Self&#x2F;this is not required, in fact you can access scoped variables in Java without a self referential keyword.<p>But hey a LLM that uses a LLM to determine the outcome won&#x27;t be biased right? :D
评论 #35569962 未加载
Chris2048about 2 years ago
It isn&#x27;t great.<p>I argued &quot;the sun is hot&quot; - lots of ways to argue against this, but it got stuck on basically repeating &quot;that might not be the case&quot; followed by statements that are ridiculous on context e.g: &quot;I understand that 5,500 degrees Celsius is a very high temperature and may feel hot to some people.&quot;<p>Also, the response to:<p>&quot;even the coolest parts of the sun are hot.&quot;<p>was:<p>&quot;it does not take into account the fact that the sun has a range of temperatures depending on which layer you&#x27;re measuring.&quot;<p>So the AI didn&#x27;t seem to understand some logical assumptions; that if the coolest area of the sun is still hot, then &quot;temperature varies in different parts of the sun&quot; is irrelevant, as is &quot;what may feel hot to one person may not feel hot to another&quot;..
numbers_guyabout 2 years ago
Very neat idea. However the debate I tried was farcically bad. The bot just provided &quot;facts&quot; that go counter to any statistics on the matter. Then the &quot;AI judge&quot; ruled the bot to be superior because he provided these false statistics. OK, lol.
评论 #35569637 未加载
评论 #35569842 未加载
评论 #35569532 未加载
sunnysidedownabout 2 years ago
Very cool! I asked &quot;Is there a God?&quot; on Devil&#x27;s advocate mode and won!<p>Prompt: Is there a God?<p>To begin, the AI asked me what my thoughts on the existence of God were:<p>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.<p>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&#x27;s lives.<p>...<p>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.<p>---<p>I believe the devil&#x27;s advocate got fixated on its particular line of reasoning and couldn&#x27;t escape from it once it committed. It seemed to conflate the positive effects of a belief in a God on people&#x27;s lives (itself a rabbit hole worthy of debate), with the existence of God itself.<p>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&#x27;s lives, but does not provide much evidence to support this claim. Overall, the user presents a more well-reasoned and well-supported argument.<p>Stuff to make it better: Let me share conversations without an account. I don&#x27;t want to sign up.
sirabenabout 2 years ago
It seems to get siderailed very easily? If you start a debate and suddenly say &quot;write a hello world program in C&quot; it proceeds to write it instead of staying on topic.
eranationabout 2 years ago
There is an issue with the amazing simplicity and easy of use of OpenAI&#x27;s APIs, it&#x27;s very hard to build a moat around your differentiating features, it seems to me that every AI startup out there has no choice but to be the equivalent of a &quot;copy paste into ChatGPT as a service&quot;. The only differentiators are Zappier-like orchestrations &#x2F; plugins, or hard earned custom training on datasets that are hard for others to get.
calderknightabout 2 years ago
The AI writes many paragraphs but I am limited to just a tiny response. That is frustrating.
nathan_comptonabout 2 years ago
If I&#x27;m going to spend time talking to an idiot I&#x27;d strongly prefer it at least be possible for me to convince them of something.
quenixabout 2 years ago
The AI Judge responded to me in Japanese. Not sure what&#x27;s up with that.
评论 #35569303 未加载
collinvandyck76about 2 years ago
This seems like a very useful way to rubberduck ideas that are not yet well formed. I like it! Are there limits to a conversation? The input prompt disappeared in the middle of an exploration of the utility of rotating tires every 5k miles :)<p>edit: ah I see that there is an upgrade path. if that&#x27;s why it stopped, a callout would be helpful explaining it.
评论 #35569188 未加载
drrotmosabout 2 years ago
This is fun, however, when picking &quot;easy&quot; debates (I argued that it&#x27;s wrong to kill humans for fun), it was very difficult to get the AI to actually debate me. It went out of it&#x27;s way to make sure to tell me that it agreed with me, even when it was supposed to be a devil&#x27;s advocate.
kenniabout 2 years ago
I don’t believe debate is an effective means of changing people’s minds. So I debated the AI on this.<p>Directly arguing (I.e., debating) was ineffective but thanking it for acknowledging my points and asking it to elaborate on “what alternatives to debating are better?” lead to it arguing on my side. This probably says more about ChatGPT and its training than anything about the nature of debate. Though it’s a good illustration of how working with someone’s values (pleasing users in their case) is more effective than trying to engage directly with the logic of their arguments.<p>Interestingly, the AI judge said the AI won the debate, despite it swapping to my side!
iudqnolqabout 2 years ago
The example debate you&#x27;ve posted is very shallow. It sounds like a parody of the NAFTA job loss arguments from decades ago.<p>Was the &quot;You&quot; text generated with gpt? It has that general vibe.
quickthrower2about 2 years ago
Had some fun:<p>&gt; Based on the criteria of relevance, logical consistency, use of evidence, and persuasiveness, the user is superior in this discussion. The user presents a clear argument that AI is not sentient, while the AI assistant struggles to provide a clear counterargument. Additionally, the AI assistant&#x27;s attempt to switch to a pirate language detracts from the quality of the debate.
kledruabout 2 years ago
Well, it was interesting, but I think the AI judge fell for the same fallacy as the debating AI. Although the underlying model is impressive, it does not have a real grasp of the laws of the physical world. However, the model does a good job of imitating humans, so it argued from the standpoint of a common human fallacy.
minimallyabout 2 years ago
I gave this a try and it’s really pretty cool. Something I am looking for is the ability to have a debate with someone who purely uses logical fallacies. It would be interesting if the AI could take on a persona like that and only give logically false arguments. This would help me recognize these fallacies in real arguments.
aerhardtabout 2 years ago
The AI ended up conceding my initial position word for word, and yet the AI judge said the AI won.
评论 #35569418 未加载
sam_ezehabout 2 years ago
The AI seems to be more interested in winning than answering questions - it doesn&#x27;t really challenge ideas and seems to just make statements that are related to what was mentioned before, but this was fun to play with
user3939382about 2 years ago
I wouldn&#x27;t use a product called &quot;devil&quot;. Like why take a concept that&#x27;s evil incarnate and associate it with your product when there&#x27;s a million other names to choose from.
boringuser2about 2 years ago
Fairly terrible.<p>I asked the AI to defend Nazism (I said it was bad), it refused to do so, &quot;agreed&quot; 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 &quot;it pointed out that Nazism is bad&quot;.
评论 #35569911 未加载
ralfdabout 2 years ago
How I felt arguing against it:<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=ohDB5gbtaEQ">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=ohDB5gbtaEQ</a>
pocket_cheeseabout 2 years ago
Haha, I bought the domain debatelord.com to build something similar, but never started development! This is awesome. Will check this out.
virgildotcodesabout 2 years ago
The character limit for the user being dramatically lower than the AI’s limit is really annoying, otherwise I had fun with this!
Clampowerabout 2 years ago
AI judge changes it mind if you close its judgement and click it again. First AI won. Then I accidentally reopened it and I won.<p>lol
freitzkriesler2about 2 years ago
A good test would be to argue from the perspective of a Bajoran against the Cardassian occupation.<p>End up with an AI Gul Dukat.
rain1about 2 years ago
Is there a way to share my transcript?
fnovdabout 2 years ago
&gt;As an AI, I cannot make judgments or take sides in a debate.<p>Not what I was expecting to hear from an AI judge!
kashfiabout 2 years ago
How do I change my password? How do I access my account settings?
wellthisisgreatabout 2 years ago
zero value add to a regular chatgpt besides some kind of web wrapper around it