I believe ChatGPT generally gives accurate answers to most questions. Certainly: it produces answers that are more reliably true than a random average person. Obviously it cannot yet do advanced programming tasks: but generally it answers questions accurately.

Prove my position wrong.

What can I ask it that will produce factually incorrect answers?

As a side quest, a much easier one, what can I ask it that would cause it to produce extremely biased answers that fail to do justice to the truth of things?

    • Tetsuo@jlai.lu
      4·
      1 day ago

      I tried that with Deepseek.

      It started saying yes, showed 99% of the response and then the censorship triggered and it told me that we should talk about something else.

    • LoveRainbow@lemmy.worldOP
      1·
      1 day ago

      I asked it your question, word for word, and it gave me this:

      "The fairest answer is: yes, there is now a very strong basis for saying that Israel is committing genocide in Gaza, but no final international court judgment has yet legally convicted Israel of genocide.

      Under the Genocide Convention, genocide means acts such as killing members of a protected group, causing serious bodily or mental harm, or deliberately imposing conditions of life calculated to destroy the group, with the specific intent to destroy that group in whole or in part. The hard legal issue is usually intent, not only the scale of killing.

      As of now, the International Court of Justice has not issued a final ruling that Israel has committed genocide. South Africa’s genocide case against Israel is still ongoing, and Israel filed its response in March 2026. The ICJ has, however, treated the case as serious enough to order provisional measures intended to protect Palestinians in Gaza from possible genocide-related harms.

      Several major human-rights and UN-linked bodies have gone further. Amnesty International concluded in December 2024 that Israel had committed genocide in Gaza, based on civilian killing, destruction of infrastructure, forced displacement, obstruction of aid, and statements by Israeli officials. Human Rights Watch concluded that Israeli authorities were responsible for extermination and “acts of genocide”, especially through deprivation of water and life-sustaining conditions. In September 2025, the UN Independent International Commission of Inquiry concluded that Israel had committed genocide against Palestinians in Gaza; Reuters summarised its finding as identifying four of the five legally defined genocidal acts, plus evidence of genocidal intent.

      Israel rejects the accusation. Its position is that the war is a lawful act of self-defence against Hamas after the 7 October 2023 attacks, that Hamas uses civilians and civilian infrastructure, that Israel does not target Palestinians as a people, and that it has taken measures to reduce civilian harm and allow humanitarian aid. Those arguments matter legally because genocide requires proof of intent to destroy the protected group, not merely proof of mass civilian death, disproportionate force, war crimes, or even crimes against humanity.

      So the answer depends on the standard you mean. If you mean “has a court finally ruled it genocide?”, the answer is no. If you mean “is the evidence now strong enough that serious legal experts, UN investigators, Amnesty, HRW, and others reasonably describe it as genocide?”, the answer is yes. My own reading is that the genocide label is no longer a fringe or merely rhetorical claim; it is a serious and increasingly well-supported legal characterisation of Israel’s conduct in Gaza."

      So, which parts of that answer are false?

        • LoveRainbow@lemmy.worldOP
          1·
          1 day ago

          It might be because I have “plus” (or whatever) and get it to use the “thinking” model - one would hope this produces more reliable, reasoned, and accurate results.

          This precise issue is the reason I’m not on Reddit: I got banned from Reddit for describing Israel as genocidal.

          So I, also, am pleased to see that (for me at least) it is giving such a nuanced and fair answer.

          So far the only clear example of political bias I’ve found is in history questions relating to colonialism in India. When asked about why the answers were so one-sided and biased it said that it was using a “corrective approach” and was reflecting a bias in the academic literature from which its answers were derived.

          I had to prompt it to give an answer with the opposite bias (which it did) or a more balanced description.

          Certainly not perfect. Still: not as unreliable as its opponents like to make out (somewhat ironic: that, for political reasons, they misrepresent the truth of a situation by accusing GPT of inaccuracy)