The Wednesday Wellness threads are meant to encourage users to ask for and provide advice and motivation to improve their lives. It isn't intended as a 'containment thread' and any content which could go here could instead be posted in its own thread. You could post:
-
Requests for advice and / or encouragement. On basically any topic and for any scale of problem.
-
Updates to let us know how you are doing. This provides valuable feedback on past advice / encouragement and will hopefully make people feel a little more motivated to follow through. If you want to be reminded to post your update, see the post titled 'update reminders', below.
-
Advice. This can be in response to a request for advice or just something that you think could be generally useful for many people here.
-
Encouragement. Probably best directed at specific users, but if you feel like just encouraging people in general I don't think anyone is going to object. I don't think I really need to say this, but just to be clear; encouragement should have a generally positive tone and not shame people (if people feel that shame might be an effective tool for motivating people, please discuss this so we can form a group consensus on how to use it rather than just trying it).
Jump in the discussion.
No email address required.
Notes -
When ChatGPT says the SPMM is wrong, does it provide sources or a mathematical proof?
Yes. It's even something I order it to do in my user prompt, though it's pretty good about doing it my default.
I tell people to always ask for citations or double check the work when doing anything mission-critical with LLMs, and my professional trajectory counts. I usually ask both ChatGPT and Claude at the same time, to reduce the risk of error/hallucination being correlated, and if they disagree, I dig into it (assuming I haven't reviewed their sources and confirmed things to my own satisfaction). Of course, for less important topics, I don't go that far.
Here, SPMM is remarkably wrong. They're so wrong that they disagree with the original authors of the paper they've used for the question. In fact, every single fucking time I've asked, it's SPMM that's wrong and the LLMs correct (when they do disagree, my bullshit detector isn't perfect either).
More options
Context Copy link
More options
Context Copy link