HI Mike, I am really enjoying your ongoing thinking and development of this tool. I can see how it surfaces and makes visible what we try and teach students. One possible enhancement I can see is to have the tool surface the assumptions that underpin the different standpoints within the discourse you are exploring
I appreciate you sharing (and developing) this tool. I was very excited to use it after watching your video, but immediately ran into some issues. I did try to verify that I was using o3, so that hopefully wasn't the issue. Not sure if I just had particularly bad luck, but a) initial response conflated the specific subset I was asking about with tangentially-related groups (leading to statements that are simply not backed up by any research), b) context report included sources invented of whole cloth, and c) source table had author names and publication years not match the actual article linked to.
I really like the idea and how it can model the research process, but it runs into the same issues I've had with my forays into genAI so far: the likelihood of inaccuracies or straight-up hallucinations is so high that I don't see it saving time for experienced researchers and can see it leading novice learners astray.
If you can send me a link to the chat I can check your version. I will say that every time this has happened it has been because the user was either using 4o (not o3) or an unpaid version of Claude with no search. But it might be different this time and I appreciate the feedback, so send a link and I will check your version.
Also I generally end my posts with a warning to not use free versions or 4.x versions and maybe I need to add that here. I feel like I am saying that constantly but I forget people aren't reading my posts in sequence so thank you.
Oh my gosh! That is a wrong response from GPT 4o on what 4o is! No wonder people find it confusing. 4o, quite confusingly, is not part of the o1 family. I have found 4o in my experiments to be quite poor at the complex reasoning needed to explore a complex information space on the fly, and unfortunately its failure mode it to hallucinate.
I was so happy to find that I could run the prompt on o3, but you're not the first person who has noted that OpenAI routes free users to 4o even when the link requests o3, and I think I'm going to have to be more explicit with warnings there. Thank you for bringing this to my attention. And my God, what a fail from OpenAI here with that response.
Thank you for clarifying! I'm glad the prompt works on o3. I did some googling just now, and I *think* o3 is only available to users who have specific tier access via OpenAI, which I think is tied to a track record of being a paid user. My university offers access to things such as BoodleBox and an organizational version of ChatGPT, but I don't pay for those. Anyways, if I'm understanding correctly, I don't have access to o3. I hope in time it'll become available more widely so more of us can engage with your "superprompt."
Awesome. Just watched the video. I need to update my Claude Project with the newer version - I love the shorthand queries for tables, context report, read the room, etc... This is great. I have an advanced Independent Research Class for HS seniors - do you think this is too sophisticated for them?
HI Mike, I am really enjoying your ongoing thinking and development of this tool. I can see how it surfaces and makes visible what we try and teach students. One possible enhancement I can see is to have the tool surface the assumptions that underpin the different standpoints within the discourse you are exploring
I appreciate you sharing (and developing) this tool. I was very excited to use it after watching your video, but immediately ran into some issues. I did try to verify that I was using o3, so that hopefully wasn't the issue. Not sure if I just had particularly bad luck, but a) initial response conflated the specific subset I was asking about with tangentially-related groups (leading to statements that are simply not backed up by any research), b) context report included sources invented of whole cloth, and c) source table had author names and publication years not match the actual article linked to.
I really like the idea and how it can model the research process, but it runs into the same issues I've had with my forays into genAI so far: the likelihood of inaccuracies or straight-up hallucinations is so high that I don't see it saving time for experienced researchers and can see it leading novice learners astray.
If you can send me a link to the chat I can check your version. I will say that every time this has happened it has been because the user was either using 4o (not o3) or an unpaid version of Claude with no search. But it might be different this time and I appreciate the feedback, so send a link and I will check your version.
Also I generally end my posts with a warning to not use free versions or 4.x versions and maybe I need to add that here. I feel like I am saying that constantly but I forget people aren't reading my posts in sequence so thank you.
https://chatgpt.com/share/68655b73-18a4-8001-ace7-8cd3bb32a5ff I did see the note about the version, but I struggled to figure out exactly what version I was using. I did ask ChatGPT itself which version I was using - and the response was confusing - it says both that I'm using 4.x but that this is part of the o3 family: https://chatgpt.com/share/68655be9-f220-8001-9f23-df05daecc0f7
Oh my gosh! That is a wrong response from GPT 4o on what 4o is! No wonder people find it confusing. 4o, quite confusingly, is not part of the o1 family. I have found 4o in my experiments to be quite poor at the complex reasoning needed to explore a complex information space on the fly, and unfortunately its failure mode it to hallucinate.
I was so happy to find that I could run the prompt on o3, but you're not the first person who has noted that OpenAI routes free users to 4o even when the link requests o3, and I think I'm going to have to be more explicit with warnings there. Thank you for bringing this to my attention. And my God, what a fail from OpenAI here with that response.
Thank you for clarifying! I'm glad the prompt works on o3. I did some googling just now, and I *think* o3 is only available to users who have specific tier access via OpenAI, which I think is tied to a track record of being a paid user. My university offers access to things such as BoodleBox and an organizational version of ChatGPT, but I don't pay for those. Anyways, if I'm understanding correctly, I don't have access to o3. I hope in time it'll become available more widely so more of us can engage with your "superprompt."
Awesome, Mike. Is the link to the prompt the same one from the SIFT page?
Yes! I've just retitled the existing checkplease.neocities.org site.
Awesome. Just watched the video. I need to update my Claude Project with the newer version - I love the shorthand queries for tables, context report, read the room, etc... This is great. I have an advanced Independent Research Class for HS seniors - do you think this is too sophisticated for them?