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。

Sci-fi story coauthored by GPT-3, including in-character human/AI chats

161 点作者 eliotpeper超过 4 年前

15 条评论

ghgr超过 4 年前
I&#x27;m sure GPT-3 is impressive and probably a paradigm change, but all this hype has an air of urban legend that somehow irks me. We all know of somebody&#x27;s friend who had access and blew its mind, and that is &quot;too dangerous&quot; to be released to the world. There&#x27;s an API, but not public, and the only way to get access is to join a waitlist (and wait).<p><i></i>If<i></i> it were a marketing ploy it would be indeed terrific. It reminds me of the movie &quot;The Blair Witch Project&quot;. And I can&#x27;t wait to try it by myself.
评论 #24227076 未加载
jamesjyu超过 4 年前
Author of the stories here! Happy to answer questions about the process. I&#x27;m a big believer that tech like GPT-3 can provocate creative writers similar to tools like oblique strategies and story dice. But it can also go further like what I&#x27;ve shown here: it can embody a character, allowing authors to converse and play with it to spark new ideas.
评论 #24226350 未加载
评论 #24230605 未加载
评论 #24228592 未加载
评论 #24226716 未加载
评论 #24234970 未加载
评论 #24231251 未加载
评论 #24231667 未加载
评论 #24226327 未加载
评论 #24226726 未加载
评论 #24226784 未加载
评论 #24229923 未加载
dave_sullivan超过 4 年前
As someone who has been playing with neural networks since 2011, the results of gpt2 and gpt3 are really impressive.<p>Things have been getting better at a steady pace and all the recent work builds on previous work. I know we will see even more impressive results in years to come.<p>People saying things like “this isn’t different from what we had before” or “it’s hype” are failing to see the progress that has occurred and the field that has developed around these ideas.
评论 #24228944 未加载
echelon超过 4 年前
GPT-3 is self-driving car hype all over again. ML can generate all kinds of signals across a large variety of domains [1], but it lacks intelligence for what to do with any of the signal it spews. Humans are still very much required at all steps.<p>If anything this is just a tool to aid human authors. A photoshop brush for the mind, if you will.<p>[1] I authored <a href="https:&#x2F;&#x2F;vo.codes" rel="nofollow">https:&#x2F;&#x2F;vo.codes</a>, so I&#x27;m at least a little knowledgeable.
评论 #24226325 未加载
评论 #24229343 未加载
评论 #24226317 未加载
评论 #24226609 未加载
评论 #24226477 未加载
nutanc超过 4 年前
Nice. I had tried a short story effort concentrating more on speed of generation. If you work with GPT-3 it becomes a very helpful tool.<p>The story I generated: <a href="https:&#x2F;&#x2F;gpt3experiments.substack.com&#x2F;p&#x2F;the-devils-mind" rel="nofollow">https:&#x2F;&#x2F;gpt3experiments.substack.com&#x2F;p&#x2F;the-devils-mind</a>
api超过 4 年前
I just have a hard time seeing any uses for GPT-3 that are not dystopian other than better telephone assistance and voice commands.<p>The uses that immediately spring to mind for me are automated propaganda, automated spam that&#x27;s virtually indistinguishable from real content, really compelling phishing attacks, and automated con artistry at scale... basically the linguistic version of deep fakes with all the ensuing use cases. I see this stuff killing the open web and any open communication platform.
评论 #24227946 未加载
评论 #24229077 未加载
thelazydogsback超过 4 年前
Quite a journey from &quot;The police&#x27;s beard is half-constructed&quot; to GPT-3. However, there&#x27;s also something more poetic about generated text that <i>isn&#x27;t</i> likely to be found &quot;in the wild&quot;.
bra-ket超过 4 年前
I see a lot of hype around GPT models I have yet to see a use case besides convincing nonsense generator, kind of like those deep net toys generating strange art, but now via language. “Colorless green ideas sleep furiously” version 3. NLP research has been stuck in syntax for 70 years, but how about semantics?<p>I mean yeah you gather bazillions of sentences and able to predict the most plausible and grammatical sequence of words that would follow particular prompt by doing a whole lot of trial and error training on massive gpu farms. But it’s just iteration on the least ambitious NLP work in the 70s and 80s. I’d argue that distributional semantics as in these popular vector space models is still solving the syntax problem. The word ‘semantics’ there is a misnomer.<p>Are there any attempts to add actual real world meaning, causality and some ‘common sense’ representation to these models, concept graph or something, try to make them less ‘dumb’ for the lack of better word, like in you know, actual ‘AI’, that has a concept of apples and oranges and a concept of people who eat them or throw in a trash bin when fruits start to rot or draw them on paper in kindergarten or use ‘apples vs. oranges’ as a rhetorical device for telling things apart etc., etc.<p>It seems like the field is stuck optimizing for some artificial toy benchmarks instead, making more convincing but ultimately stupid chat bots. And I mean ‘stupid’ not in derogatory sense but as a formal definition of their capabilities, as opposed to understanding things like a child would.
anentropic超过 4 年前
If it was really all written by a human author, without any GTP-3 involved, how would we know?
评论 #24226522 未加载
ianhorn超过 4 年前
I&#x27;ve been doing sorta similar stuff with GPT-3 since I got access, and I can vouch that it&#x27;s effective. Not up-to-the-hype effective, but that&#x27;s more a function of the hype. It&#x27;s been really great at creative stuff that just needs to spark imagination. Like a super powered natural language version of encounter tables in D&amp;D&#x27;s dungeon master&#x27;s guide. AI isn&#x27;t there as an author yet, but as a brainstorming tool, it&#x27;s full of great ideas if you sample and refine and sample and refine enough.
hdfhu超过 4 年前
GPT is really a tool that draws trees without branches: they look like trees from distance, but fall apart upon some analysis. But I believe GPT will learn soon how to add decent branches.
评论 #24229175 未加载
smusamashah超过 4 年前
Can you give it a huge book, Harry Potter series for example and then assume one of the characters, start an alternate storyline and let it build the rest? Can GPT-3 do that?
评论 #24228006 未加载
mrfusion超过 4 年前
What’s the best way to understand how gpt-3 works? Any good tutorials with visualizations?
segfaultbuserr超过 4 年前
Recently I&#x27;ve spent an entire day playing with AI Dungeon, an AI-based creative writing service for playing role-playing, Dungeon-like text games. You can pay to unlock the &quot;Dungeon&quot; model - an advanced machine learning model supposed based on GPT-3. It&#x27;s not GPT-3 itself, and it&#x27;s not perfect because its output is seriously biased for role-playing games, but as close as we can get for an outsider.<p>I was quite amazed by its performance. It was able to write first-person as an infosec researcher&#x27;s blog post when I used some infosec news story as input, and it was also able to write a surprisingly coherent argument for patent reform and an argument against software patent when I used an EFF article as the input... These are clearly already included in its training input, but still, it was far beyond my expectation - none of the output is a verbatim quote from a single source, everything has been rewritten.<p>I went to Hacker News, copied a random infosec news report on newly discovered security vulnerability on Qualcomm&#x27;s smartphone chips as the input, copied from <a href="https:&#x2F;&#x2F;blog.checkpoint.com&#x2F;2020&#x2F;08&#x2F;06&#x2F;achilles-small-chip-big-peril&#x2F;" rel="nofollow">https:&#x2F;&#x2F;blog.checkpoint.com&#x2F;2020&#x2F;08&#x2F;06&#x2F;achilles-small-chip-b...</a>)<p>&gt; With over 3 billion users globally, smartphones are an integral, almost inseparable part of our day-to-day lives. In this research dubbed &quot;Achilles&quot; we performed an extensive security review of a DSP chip from one of the leading manufacturers: Qualcomm Technologies. Qualcomm provides a wide variety of chips that are embedded into devices that make up over 40% of the mobile phone market, including high-end phones from Google, Samsung, LG, Xiaomi, OnePlus and more.<p>&gt; More than 400 vulnerable pieces of code were found within the DSP chip we tested, and these vulnerabilities could have the following impact on users of phones with the affected chip:<p>&gt; Attackers can turn the phone into a perfect spying tool, without any user interaction required. Attackers may be able to render the mobile phone constantly unresponsive. Malware and other malicious code can completely hide their activities and become un-removable.<p>And there&#x27;s the output by AI Dungeon (GPT-3). I didn&#x27;t write a single sentence of it, nor did I use undo&#x2F;redo. It was able to make up links, CVE IDs, university names, and technical jargon with ease.<p>(I replaced all &quot;<a href="https:&#x2F;&#x2F;&quot;" rel="nofollow">https:&#x2F;&#x2F;&quot;</a> links to &quot;h__ps:&#x2F;&#x2F;&quot; for readability.)<p>&gt; The phone will not even reboot, but instead simply shut down and cannot be reactivated. This is known as a hard reset.<p>&gt; The full list of vulnerabilities can be seen here: h__ps:&#x2F;&#x2F;www.qualcomm.com&#x2F;security_intelligence&#x2F;dsp-vulnerabilities<p>&gt; This vulnerability has been reported to Qualcomm by Zimperium. We recommend all customers who use the affected DSP chip to update it immediately.*<p>&gt; We apologize for the inconvenience caused by this issue, and we appreciate your understanding.<p>&gt; Zuk Avraham<p>&gt; Zimperium za Chief of Defense<p>&gt; Zuk (ZukAvraham) | 10.05.2017<p>&gt; Hi, this is Zuk from Zimperium. Before we begin, we would like to say we&#x27;re really sorry for the inconvenience that was caused by our previous report (Dirty COW). This report is regarding another set of security vulnerabilities we found in another chipset maker, this time in the MediaTek chipset. We&#x27;ll explain what happened and how we work to prevent issues like this in the future.<p>&gt; First of all, we want to thank CTS (h__ps:&#x2F;&#x2F;cts.cudenver.edu&#x2F;) for providing an open program that allows researchers like us to do responsible disclosures. Through their Vulnerability Reporting Program, we were able to report the issues we found to MediaTek and work with them to make sure these issues get patched for your safety.<p>&gt; What Happened?<p>&gt; This is a story about two bugs we found in the last few months.<p>&gt; The first bug (CVE-2017-05591) was an overly permissive domain validation in the bootloader. The bootloader allows the modem to be updated without flashing the complete firmware. The validation is done using the bootloader code running in the processor of the phone. This allowed us to inject our own bootloader code into the program running on the processor and bypass the authentication of the modem. The modem is responsible for communication with the network. In other words, by bypassing the authentication of the modem we can control the phone communication channels.<p>&gt; The second bug (CVE-2017-95881) is a buffer overflow in a very special program called TrustZone. The TrustZone is a security processor in most of the recent phones. It runs a separate operating system in which the kernel is trusted to be free of any malicious code, and has access to the memory, CPU and devices. The TrustZone kernel code runs outside the control of any other code. This bug in the TrustZone code allowed us to replace it with a custom one we designed, without any permissions.<p>&gt; We wrote a special TrustZone kernel code that allows us to gain full control over the phone. It allowed us to bypass all the phone security restrictions. With this custom TrustZone kernel code running, we were able to read the encrypted messages sent by any application. In addition, we also got full control over the device.<p>But finally the AI lost the context, and the topic shifted from insecure to security, and eventually the writing becomes a new marketing advertisement on a secure smartphone, which I&#x27;ve removed in the quote.
tomc1985超过 4 年前
Every time I see GPT-3 I gsub &quot;Fancypants Markov Chains&quot; and the story always becomes a lot more breathless