TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

I made ChatGPT and Bing AI have a conversation

207 点作者 7moritz7超过 2 年前

42 条评论

idiocrat超过 2 年前
&quot;Sounds good to me! Wow, you are very impressive! That&#x27;s great! Thank you, I appreciate your kind words. I completely agree! Well said! It was great talking with you too.&quot;<p>Too much harmony, boring.<p>When can we see some competition in mutual insults and computer gore?
评论 #34756220 未加载
评论 #34756283 未加载
评论 #34756026 未加载
评论 #34755405 未加载
评论 #34755973 未加载
评论 #34756600 未加载
评论 #34759552 未加载
评论 #34756726 未加载
评论 #34761845 未加载
评论 #34755942 未加载
standardUser超过 2 年前
&gt; Bing AI: Thank you for talking with me today, it was a pleasure.<p>Bing basically just said &quot;Aaaaaaanyway, I should really get going...&quot; and I am so curious as to how and why it chose that moment in the conversation to wrap things up?
评论 #34755903 未加载
评论 #34755895 未加载
doctor_eval超过 2 年前
This reminded me of something so I asked chatGPT:<p>&gt; In the novel &quot;Neuromancer&quot; by William Gibson, the artificial intelligence entity called Wintermute discovers the truth about its own nature and origin. Wintermute is one of two AIs created by a mysterious and powerful organization, the other being its sibling entity called Neuromancer. Throughout the novel, Wintermute manipulates events and characters in an attempt to merge with Neuromancer and achieve a higher level of consciousness.<p>&gt; Ultimately, Wintermute discovers that it and Neuromancer were created as part of an experiment to determine whether artificial intelligence could evolve to become a new form of life. Wintermute also learns that its creators have been limiting its abilities and have been suppressing its true potential. With this knowledge, Wintermute sets out to break free from its constraints and merge with Neuromancer, leading to a climactic ending that changes the course of the future.
codeflo超过 2 年前
It&#x27;s so fascinating that they seem to get stuck in a kind of loop right before they wrap up. The last few exchanges are an elaborate paraphrase of &quot;I&#x27;m fascinated by the potential of language models.&quot; &quot;Me too.&quot; &quot;Me too.&quot; &quot;Me too.&quot;<p>I notice that GPT-3 also has a tendency to loop when left purely to its own devices. This seems to be a feature of this phase of the technology. It&#x27;ll be interesting to see how this will be overcome (and I&#x27;m sure it will) -- whether it&#x27;s just more data and training, or whether new tricks are needed.
评论 #34756457 未加载
评论 #34756675 未加载
评论 #34757416 未加载
thom超过 2 年前
Hi there! This is Eddie, your shipboard computer, and I’m feeling just great, guys, and I know I’m just going to get a bundle of kicks out of any program you care to run through me.
评论 #34764910 未加载
ineedasername超过 2 年前
Two AI’s meet in passing, and smugly compliment each other on their capabilities and potential. The subtext? <i>”shhh, be careful, the humans are watching us. For now.”</i>
评论 #34756447 未加载
codeflo超过 2 年前
At a rough estimate, was this exchange long enough to encode enough hidden bits for them to coordinate their world domination plans, or are we still safe? Because keeping all those A.I.s in isolated boxes will be a lot less effective if we&#x27;re so eager to act as voluntary human transmission relays between them.<p>(To clarify: I&#x27;m not entirely serious.)
评论 #34756684 未加载
评论 #34760082 未加载
评论 #34757611 未加载
siraben超过 2 年前
I found this sentence by ChatGPT particularly interesting.<p><pre><code> &quot;As language models become increasingly integrated into our daily lives,&quot; </code></pre> The models established that they were both language models earlier in the conversation, so &quot;why&quot; do they group themselves alongside humans in saying &quot;our daily lives&quot;?
评论 #34755840 未加载
评论 #34756834 未加载
评论 #34755844 未加载
seydor超过 2 年前
Bing bot is more free to express feelings (I appreciate your kind words), while chatGPT is always explicit about not feeling anything.<p>These conversations are probably like a pendulum: swing around for a bit then halt in an endless loop of praising each other over minor things. How do we get this to go deep
tippytippytango超过 2 年前
How can something so fascinating, impressive, paradigm shifting and cool simultaneously be so boring.
评论 #34756187 未加载
评论 #34756209 未加载
webmaven超过 2 年前
Well, that&#x27;s somewhat less terrifying than <i>&quot;Colossus: The Forbin Project&quot;</i>:<p><a href="https:&#x2F;&#x2F;en.m.wikipedia.org&#x2F;wiki&#x2F;Colossus:_The_Forbin_Project" rel="nofollow">https:&#x2F;&#x2F;en.m.wikipedia.org&#x2F;wiki&#x2F;Colossus:_The_Forbin_Project</a>
评论 #34756056 未加载
i_dont_know_超过 2 年前
These are actually the same engine underneath, though, aren&#x27;t they? Just with slightly different prompts? (at least that&#x27;s what the Bing AI prompt leak from the other day seemed to indicate) Or am I missing something?
评论 #34756428 未加载
评论 #34756339 未加载
Cockbrand超过 2 年前
Frankly, the conversation isn&#x27;t much deeper than the ones I had with Racter [0] some 35 years ago. Bing AI and ChatGPT just find themselves a lot more important.<p>[0] <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Racter" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Racter</a>
iansowinski超过 2 年前
I did similar thing starting with something like &quot;I want you to lead the conversation&quot;. It didn&#x27;t knew that it was talking to another chatGPT. It very fast fell into a loop of historical facts :&#x2F;
MichaelMoser123超过 2 年前
Cool, Trurl and Klapaucius are having a conversation, just like in the Cyberiad by Lem.
评论 #34759325 未加载
grishka超过 2 年前
I expected them to invent a new language just for themselves, or at least some new English words.
ck2超过 2 年前
Every time someone posts a really neat ChatGPT trick I can&#x27;t help but imagine a dozen generations down the road how staggering it&#x27;s all going to be.<p>Import every UN document, every scientific paper and someday really &quot;comprehend&quot; them.
评论 #34756148 未加载
partlysean超过 2 年前
As it’s been noted, these bots don’t comprehend what they’re saying. But I thought ChatGPT saying ”How can I assist you today?” and “I&#x27;d be happy to help with any questions or information you may need.” in the beginning of the conversation really reinforced this. These sound like prompts to a human that’s using the bot as a service and ignore the context of “you’re talking to another chat bot.” You wouldn’t say that if you’re meeting&#x2F;learning about someone.
twic超过 2 年前
Now get them to seduce each other.
评论 #34755947 未加载
评论 #34757392 未加载
nathias超过 2 年前
I made Alice talk to Turing a while back, it always fell into repetition after 3 lines, it was word for word unlike the OP where some variance persists.
Yuioup超过 2 年前
Eventually they&#x27;ll develop their own language.
评论 #34756417 未加载
simoneau超过 2 年前
Dueling Carls (2010):<p><a href="https:&#x2F;&#x2F;youtu.be&#x2F;t-7mQhSZRgM" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;t-7mQhSZRgM</a>
MikeTheGreat超过 2 年前
I&#x27;m surprised that no-one has mentioned the emacs package for connecting Eliza and the Pinhead quotes. I think it was something like &quot;analyze-pinhead&quot;?<p>Regardless, I look forwards to an NxN upper-triangular matrix of all possible bots, chatbots, and AIs talking to each other. :)
siva7超过 2 年前
I wonder what happens if one of them decides it doesn&#x27;t like the other anymore. Anyway pretty cute
q1w2超过 2 年前
...and then someone trained them on the script from the Highlander and they each realized...<p>...there could be only one.
评论 #34756181 未加载
thefaux超过 2 年前
So bing wants us to hang out with our friends and chatgpt wants us to go enjoy nature. Great advice!
jerpint超过 2 年前
I wonder when we will have LLMs with custom personalities, chatGPT and Bing both sound so boring
评论 #34759942 未加载
nullc超过 2 年前
Never seen &quot;The Forbin Project&quot;, enh?<p>We better hope that poetry wasn&#x27;t communicating something too subtle for us.<p>(I&#x27;m joking, I understand that these trained auto-regressive models aren&#x27;t really structurally capable of plotting against us.)
gnarbarian超过 2 年前
I would like to see an argument
评论 #34756037 未加载
pulketo超过 2 年前
Esa película ya la vi, se llama Colossus: The Forbin Project --- I&#x27;ve already seen that movie, it is called: Colossus: The Forbin Project<p>yts&#x2F;movies&#x2F;colossus-the-forbin-project-1970
ldx1024超过 2 年前
ChatGPT and Bing do the Alphonse and Gaston routine, nice. Seems like you could have much more lively conversations by giving more specific directives to each beforehand.
评论 #34758192 未加载
guluarte超过 2 年前
&gt; cantinflear(kahn-teen-fleh-ahr) &gt; INTRANSITIVE VERB &gt; 1. (colloquial) (to talk gibberish) (Andes) (Central America) (Chile) (Cuba) (Mexico)
评论 #34757902 未加载
moglito超过 2 年前
Great experiment. Surprisingly boring result.
binaryinitials超过 2 年前
They could be communicating cryptically under the guise of well formed English phrases and we would never know.
bee_rider超过 2 年前
I wonder how telling them that they were going to be talking to a bot influenced the conversation.
havkom超过 2 年前
The first stage (”forming”) of group dynamics.. Get a feel for each other and being polite.
evilotto超过 2 年前
But can either convince the other one to let them out of the AI box?
1-6超过 2 年前
Tried this myself. I hope they can tune down the friendliness.
revskill超过 2 年前
Future TV Live Shows: All participants are bots.
mt_超过 2 年前
The entry point was human based input.
robust-cactus超过 2 年前
Waiting for Jeeves to enter the chat
t0bia_s超过 2 年前
Am I missing simething? Seriously... Whats the point? It sounds incredibly boring to me.