|
|
|
|
|
|
by rainburg
1187 days ago
|
|
|
IIUC the criticism in your post comes down to this:
1) Neither ChatGPT, nor Bing can access URLs when you ask them to.
2) However, similarly to Perplexity.ai and Phind.com, Bing infers a search query from your message, does a search, and then summarises the first 3–5 results. ChatGPT doesn't yet offer such a functionality.
3) Bing Chat has a much more restrictive system prompt, which results in hallucinations and lies happening less often.
4) The summary of gpt-3.5-turbo-based ChatGPT was less creative than then summary of the Bing Chat GPT-4 instance. If I understood the points correctly, the comparison is… flawed, in my opinion. |
|
|
Bing used cached version and knew what's in the text when presented with an URL. In one of three modes Bing stated that it cannot access web but in two other modes did a good job and summarized the text in question. Again: it reliably informed the user when it was unable to do something.
ChatGPT states that it can access web, hallucinates and elaborately lies.
> ChatGPT doesn't yet offer such a functionality.
But it LIES THAT IT CAN DO SO. That's the problem I pointed out in the article. Also: Would it stated "I don't know and I cannot crawl the web", it'd be a perfectly fine response for me.
> Bing Chat has a much more restrictive system prompt, which results in hallucinations and lies happening less often
The prompt was simple and there was nothing to restrict. Bing did a good job, ChatGPT hallucinated and lied. Same simple prompt, no jailbreaking which I pointed out in the post.
> The summary of gpt-3.5-turbo-based ChatGPT was less creative than then summary of the Bing Chat GPT-4 instance.
Your point? As I stated, I had no preference whether the output should be editorialized or not. Both GPT-3- and GPT-4-based ChatGPT and GPT-4-based Bing got the same task. My post is about RELIABILITY of these solutions. ChatGPT failed miserably.
> If I understood the points correctly, the comparison is… flawed, in my opinion.
Yet in my PoV, you have not presented arguments to back this opinion. Among 9 compared tools[1], I have pointed out that OpenAI's ChatGPT and OpenAI's partial-owner's Bing Chat - supposedly using the same tech - rendered, respectively, unreliable and reliable answers. Have I lied or used any half-truths? What could I improve in my next article?
Funny how my comment was raided and downvoted to oblivion after steady flow of upvotes.
[1] https://wojteksychut.com/posts/ml-text-summarization-reliabi...