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 used ChatGPT as a reporting assistant. It didn't go well

25 点作者 giuliomagnifico大约 1 年前

6 条评论

Benjammer大约 1 年前
The problem is that people like this author are trying to literally treat it like a person instead of an LLM. Like honestly if you look at the linked chat convo early in the article, this person kind of just sucks at prompt engineering, imo.<p>&quot;At times I was able to get the chat agent to give me what I wanted, but I had to be very specific and I often had to scold it.&quot;<p>You can&#x27;t just half-ass a paragraph of disjointed system instructions into the user input and expect clean results, in my experience. You need to leverage the custom system instructions, give example responses if possible, and be very, very specific and direct with instructions. You need to explain the type of response you want, and you also need to describe any applicable constraints (or lack thereof) on the response content.<p>&quot;When you are asked something, it is crucial that you cite your sources, and always use the most authoritative sources (government agencies for example) rather that sites like Wikipedia&quot;<p>This is not sufficient to achieve what the author intends. It&#x27;s written in a speech-like roundabout style (e.g. &quot;it is crucial that&quot;), and there&#x27;s a typo right in the middle on an important word (than --&gt; that). LLM can work around typos in most cases, but here it is vaguely possibly imo that this is what is causing it to continue citing wikipedia in responses.<p>&quot;At times, the tool was too eager to please, so I asked it to tone it down a little: “You can skip the chit chat and pleasantries.”&quot;<p>I have found in my experience playing with ChatGPT that this is just the completely wrong mental model to have of the tool in order to get what you want out of it. You have to treat it more like a prose-language programming tool, not like a person with emotions that you are conversing with...
评论 #39768295 未加载
评论 #39770400 未加载
评论 #39769170 未加载
Havoc大约 1 年前
That’s consistent with my experience too.<p>Huge help for hobby programming but struggling to use it for day job (finance). Even for basic memos the reasoning just isn’t coherent enough and not nuanced enough.<p>I think it’s because programming is quite modular. You can ask it a fragment of a problem easily. Eg how do I send a message on GCP pubsub. That same modular and self contained aspect just doesn’t exist in my day job
评论 #39773482 未加载
smileysteve大约 1 年前
The article lost me at<p>&gt; The confidence that ChatGPT exudes when providing poorly sourced information (like Wikipedia)<p>Isn&#x27;t the data that Wikipedia is more peer reviewed and up to date than most other aggregated sources (such as encyclopedias); Sure it can be co-opted, but we&#x27;ve also seen publishing houses co-opted.
评论 #39768948 未加载
评论 #39771419 未加载
JohnMakin大约 1 年前
At that point in 2023 didn&#x27;t chatGPT have a hard knowledge cutoff? If so asking it to cite relevant sources to a major news event that just happened seems kind of ridiculous. I think it was much later in 2023 that that was removed.
评论 #39772266 未加载
nine_zeros大约 1 年前
ChatGPT cannot be used for anything that requires precision. It is just confidently wrong too many times.<p>Use it for what it is good for, easy fuzzy activities.
VincentEvans大约 1 年前
If you have to «always double-check» - it means that you have to do the most important portion of the work yourself, which significantly narrows potential uses to those where you already possess competence of the task and command of the data to judge the results and the use of gpt just saves you some typing. And saving on typing is great, but a significant step down from our collective expectations.<p>It’s like having a personal assistant that is most helpful but has a penchant for blatantly sociopathic lying. Not great.<p>Not arguing, just restating the obvious in my own words.
评论 #39767908 未加载