TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Ask HN: Text-DaVinci-003/ChatGPT made up research sources?

1 pointsby legnaflowover 2 years ago
I&#x27;m using text-davinci-003 to find some research backed findings to build up my startup pitch. However, when I ask for the research source (title and url) for AI&#x27;s answer, the report title and urls given by AI are usually not accessible or searchable online. https:&#x2F;&#x2F;beta.openai.com&#x2F;playground&#x2F;p&#x2F;default-chat<p>Overtime, I started suspecting, are those reports and url fake&#x2F;generated by AI?<p>Examples of the reports referred by AI: 4. Mental Health Foundation (2015). Why do some people not get the help they need? [https:&#x2F;&#x2F;www.mentalhealth.org.uk&#x2F;publications&#x2F;why-do-some-people-not-get-help-they-need](https:&#x2F;&#x2F;www.mentalhealth.org.uk&#x2F;publications&#x2F;why-do-some-people-not-get-help-they-need) 5. National Alliance on Mental Illness (2020). Mental health conditions &amp; stigmas. [https:&#x2F;&#x2F;www.nami.org&#x2F;About-Mental-Illness&#x2F;Mental-Health-Conditions](https:&#x2F;&#x2F;www.nami.org&#x2F;About-Mental-Illness&#x2F;Mental-Health-Conditions) 6. Substance Abuse and Mental Health Services Administration (2019). Mental health services in the United States. [https:&#x2F;&#x2F;www.samhsa.gov&#x2F;find-help&#x2F;national-helpline](https:&#x2F;&#x2F;www.samhsa.gov&#x2F;find-help&#x2F;national-helpline) - National Institutes of Health (NIH):&quot;The Huppert&#x27;s Mental Health Spectrum: Population Distributions and Associated Factors&quot;. https:&#x2F;&#x2F;pubmed.ncbi.nlm.nih.gov&#x2F;31407549&#x2F;.

2 comments

NtochkaNzvanovaover 2 years ago
Yes. This has been well-documented -- in the days since ChatGPT was released, there have been multiple posts with it making up references, book titles and authors, etc. Galactica did the same, and probably every other LLM.<p>An LLM is not a search engine, a database, or a knowledge base. An LLM generates plausible-sounding text based on the distribution of its inputs. There is no constraint that anything it spits out is factually accurate. Why is this so hard to understand?
评论 #33929641 未加载
32gbsdover 2 years ago
Basically all the output can be generated even the specifics. It is its own source of truth.
评论 #33929642 未加载