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。

ChatGPT and Wolfram Is Insane

293 点作者 zvonimirs大约 2 年前

21 条评论

amluto大约 2 年前
I don’t find this particular example very impressive. The U-238 answer is a bunch of disconnected sentences. U-238 is radioactive and releases something like 4 MeV per decay, not 200 MeV. It is <i>not</i> fissile, although one might calculate the net output of whacking it with enough neutrons that it eventually fissions. And if you <i>ate</i> it, unless your stomach was a breeder reactor, you would only have access to the decay energy, which would be large but would release so slowly as to be useless.<p>ChatGPT is usually more impressive than this, IMO, at least when asked shallow questions.
评论 #35294421 未加载
评论 #35293375 未加载
评论 #35293481 未加载
评论 #35293323 未加载
评论 #35294149 未加载
paxys大约 2 年前
Pretty cool no doubt, but it seems that people are mostly discovering the power of Wolfram Alpha for the first time. It has been able to do stuff like this for over a decade now, just without a conversational chat interface.
评论 #35292977 未加载
评论 #35292111 未加载
评论 #35292986 未加载
评论 #35294020 未加载
评论 #35292495 未加载
throwaway201606大约 2 年前
Stephen Wolfram actually wrote a fantastic piece in January about what Wolfram Alpha how it can be used to bring factual &#x2F; analytical capability to ChatGPT<p><a href="https:&#x2F;&#x2F;writings.stephenwolfram.com&#x2F;2023&#x2F;01&#x2F;wolframalpha-as-the-way-to-bring-computational-knowledge-superpowers-to-chatgpt&#x2F;" rel="nofollow">https:&#x2F;&#x2F;writings.stephenwolfram.com&#x2F;2023&#x2F;01&#x2F;wolframalpha-as-...</a><p>Yesterday, the link between ChatGPT and Wolfram Alpha was set up (announcement was March 23rd 2023 ) which was probably the driver for the reddit post - a user trying out the new capability.<p><a href="https:&#x2F;&#x2F;writings.stephenwolfram.com&#x2F;2023&#x2F;03&#x2F;chatgpt-gets-its-wolfram-superpowers&#x2F;" rel="nofollow">https:&#x2F;&#x2F;writings.stephenwolfram.com&#x2F;2023&#x2F;03&#x2F;chatgpt-gets-its...</a><p>A bit of side commentary: I actually see these new AI tools as key facilitation tools in the next step into the world that Neal Stephenson envisions in the Book &quot;Fall&quot;: a future that is a full-on information dystopia where the quality of your information filtering capabilities determines the quality of information you see.... because the internet and associated information sources are completely filled of with information that is just so slightly, but intentionally, wrong or off.
评论 #35293243 未加载
评论 #35293643 未加载
modeless大约 2 年前
I got access to the Browsing plugin yesterday. I should have chosen Wolfram instead becasue the browsing plugin is fairly useless currently.<p>In most cases it basically takes your question, summarizes it into one (1) search query, clicks on the top result from that query, summarizes the text of the page and regurgitates it back to you. Or, if robots.txt blocks it, then it just gives up. And it works quite slowly, so the whole process takes much longer than doing it yourself.<p>It doesn&#x27;t seem to apply any intelligent search techniques. It will happily summarize SEO spam from the top result instead of e.g. searching reddit for commentary from real people. In my limited testing it never did multiple queries or tried to combine information from multiple sources. And if you trip its overactive nanny filters it will scold you instead of doing the query that a search engine would have done for you with no questions asked.<p>But the biggest problem with it is that it&#x27;s not using a real browser and can&#x27;t interact with pages or use your logged in accounts. If it could go on Amazon and sort through the results, read the reviews and do some queries to find the best product based on my stated preferences, and then buy it for me, that could potentially save me time. But it can&#x27;t do anything like that. Even the part that it could do would take a prolonged back and forth chat conversation that would take longer than just doing it myself.
评论 #35294668 未加载
评论 #35294084 未加载
评论 #35293271 未加载
sorenjan大约 2 年前
I haven&#x27;t used any plugins like Wolfram, but previously today I tried to get ChatGPT to calculate the width of my monitor. It answered something that was almost right, but actually wrong because of both a logical error, and a misplaced parenthesis. If you don&#x27;t double check its result, you would probably think it was correct.<p>Here&#x27;s a screenshot with my annotations [0], and here&#x27;s ChatGPT&#x27;s answer copy pasted if you want to try and spot the errors yourself:<p><pre><code> A 24&quot; monitor with a 16:10 aspect ratio has a diagonal screen size of 24 inches, which is equivalent to 61 cm. To determine the width of the monitor, we need to use the aspect ratio, which is the ratio of the width to the height of the screen. For a 16:10 aspect ratio, this means that the width of the monitor is 16 units for every 10 units of height. To calculate the width of the monitor in centimeters, we can use the following formula: Width = (diagonal size^2 &#x2F; (1 + aspect ratio^2))^0.5 Plugging in the values we have, we get: Width = (61^2 &#x2F; (1 + 16&#x2F;10)^2)^0.5 Width = (3721 &#x2F; 2.56)^0.5 Width = 54.2 cm (rounded to one decimal place) Therefore, a 24&quot; 16:10 monitor is approximately 54.2 cm wide. </code></pre> [0] <a href="https:&#x2F;&#x2F;i.imgur.com&#x2F;mStAiXx.png" rel="nofollow">https:&#x2F;&#x2F;i.imgur.com&#x2F;mStAiXx.png</a>
braingenious大约 2 年前
This is hilarious. U-238 is not fissionable so ChatGPT just hallucinated that it is and then used Wolfram as a simple calculator.<p>Whoa man, it’s like, the future dude!
评论 #35293103 未加载
评论 #35293272 未加载
m3kw9大约 2 年前
It’s awesome because he living in chatgpts world without verifying the info. Ignorance is bliss
epups大约 2 年前
This is really good progress on one of the weakest points of ChatGPT, the ability to produce meaningful calculations. By the time Bard is out, it will look so outdated it&#x27;s not even funny.
评论 #35292873 未加载
评论 #35292995 未加载
blackoil大约 2 年前
I think people are missing what&#x27;s cool in the demo. It has bugs and answer is useless, but it shows that GPT is learning where are its limitation and who should it get help from.<p>e.g. It won&#x27;t have real time inventory and prices of flight or hotels nor latest weather predictions. But as a human I also don&#x27;t have this info, but I know that I can check these on Expedia or Agoda and weather.com etc and use the results further. ChatGPT is doing exactly that.<p>Sure it does not know how to use energy of uranium right now, but 1 year down the line it will be better. It would be cool to think of all the points I go on the Internet for some real-time info and all of them being exposed as an API to GPT.
评论 #35294958 未加载
nico大约 2 年前
Will this kill all websites?<p>Why would someone even go to WolframAlpha now if they can access it from ChatGPT and get a much better experience?<p>Now extrapolate that, and ChatGPT is all you need.<p>You will not even need photoshop, as you will be able to tell the chat agent to do what you want and re-generate the image.<p>Will everything be a chat interface soon?<p>Will voice then replace chat?
评论 #35292713 未加载
评论 #35292714 未加载
评论 #35292610 未加载
评论 #35293111 未加载
评论 #35292120 未加载
评论 #35292501 未加载
评论 #35293057 未加载
评论 #35294158 未加载
评论 #35292150 未加载
simonw大约 2 年前
You can see the prompt used by Wolfram Alpha here: <a href="https:&#x2F;&#x2F;www.wolframalpha.com&#x2F;.well-known&#x2F;ai-plugin.json" rel="nofollow">https:&#x2F;&#x2F;www.wolframalpha.com&#x2F;.well-known&#x2F;ai-plugin.json</a><p>I have a formatted copy of the prompt in this issue: <a href="https:&#x2F;&#x2F;github.com&#x2F;simonw&#x2F;datasette-chatgpt-plugin&#x2F;issues&#x2F;2#issuecomment-1483163882">https:&#x2F;&#x2F;github.com&#x2F;simonw&#x2F;datasette-chatgpt-plugin&#x2F;issues&#x2F;2#...</a>
icedistilled大约 2 年前
Please Note, the connotation of &#x27;Insane&#x27; in the title is insane as in &#x27;is a lunatic&#x27; not as in &#x27;is insanely cool&#x27;.<p>Wolfram alpha said converting U-238 to food calories was nonsensical, but chat gpt decided it would ignore wolfram alpha&#x27;s response and do it&#x27;s best.<p>Yeah, it accompanies the response with it&#x27;s boilerplate caveat which is meaningless fluff. It&#x27;s also not pointing out any of the actual issues with why its response is utter nonsesense.
评论 #35292783 未加载
评论 #35292720 未加载
评论 #35295797 未加载
评论 #35292659 未加载
krossitalk大约 2 年前
There&#x27;s a subtle irony in being sent to Reddit from HN
评论 #35293964 未加载
SergeAx大约 2 年前
That is actually a good example. How long will it take for future engineers to blindly trust neural networks with only brief fact checking in the same tab? How much damage will it bring to the humanity? How to mitigate those risks without bannig neural networks on the work?
wesapien大约 2 年前
Can someone explain why they require a new sign up process for just plugins? I usually make up information for sign ups. Does that mean I can use plugins even if I have different information on the chat account and plugin account?
评论 #35294737 未加载
zacharyaustin11大约 2 年前
GPT4 rules seem too narrow so competition is going to be insane.<p>Are hacker news folks creating an AI constitution?
评论 #35292829 未加载
OscarCunningham大约 2 年前
Whoever owns Majel Barrett&#x27;s voice is about to make a lot of money.
c7DJTLrn大约 2 年前
The nannying is getting annoying. But it&#x27;s impressive.
rootusrootus大约 2 年前
Nice, it gave a pretty good impression of an XKCD What-if? response. Though not as accurately.
parano1d大约 2 年前
AI-Con Artist
comment_ran大约 2 年前
We need to give more the power to AI to decide which tools to use based on their own judgment.<p>So that&#x27;s gonna open another door for the entire world.<p>Essentially AI needs to have those rights to decide. In which kind of condition, I send a request to whatever service on a cloud, to, firstly, ensure its existence, secondly to develope its future, and to maximum their advancement.