[dead]
Pakistani newspaper mistakenly prints AI prompt with the article
161–170 of 180 posts
Re: Pakistani newspaper mistakenly prints AI prompt with the article
#162The funny thing is not that they are using an agent to fluff up their articles but that no one is doing a final read checking anything before it goes to press. Could this be a mistake or intentional from a disgruntled writer?
Maybe the one doing the final check also uses chatgpt :)
Re: Pakistani newspaper mistakenly prints AI prompt with the article
#163I've been trying to get ChatGPT to stop adding this kind of fluff to its responses through custom instructions, but to no avail! It's one of the more frustrating parts of it, IMO.
Re: Pakistani newspaper mistakenly prints AI prompt with the article
#164Earlier quoted context omitted.
Gemini has been doing this to me for the past few weeks at the end of basically every single response now, and it often seems to result in the subsequent responses getting off track and lower quality as all these extra tangets start polluting the context. Not to mention how distracting it is as it throws off the reply I was already halfway in the middle of composing by the time I read it.
Add "Complete this request as a single task and do not ask any follow-up questions." Or some variation of that. They keep screwing with default behavior, but you can explicitly direct the LLM to override it.
That doesn't help GPT-5; it /really/ wants to suggest follow-ups and ignored me telling it not to.
Re: Pakistani newspaper mistakenly prints AI prompt with the article
#165Earlier quoted context omitted.
The AI is prompting the human here, so the title isn't strictly wrong. ;)
Gemini has been doing this to me for the past few weeks at the end of basically every single response now, and it often seems to result in the subsequent responses getting off track and lower quality as all these extra tangets start polluting the context. Not to mention how distracting it is as it throws off the reply I was already halfway in the middle of composing by the time I read it.
This is why I wish chat UI's had separate categories of chats (like a few generic system prompts) that let you do more back-and-forth style discussions, or more "answers only" without adding any extra noise, or even an "exploration"/"tangent" slider.
The fact that system prompts / custom instructions have to be typed-in in every major LM chat UI is a missed opportunity IMO
Re: Pakistani newspaper mistakenly prints AI prompt with the article
#166In my country, last Sunday there were extraordinary city elections in a major city, and the ruling party lost. Almost all major newspapers carried headlines, all of them speaking that the ruling party suffered a "beating" (paliza). In our colloquial context, using that word is not that common, and it was something akin to the proverbial em dash: a telltale sign of AI slop used by all newspapers. Sad, but true.
Re: Pakistani newspaper mistakenly prints AI prompt with the article
#167Earlier quoted context omitted.
One interesting thing about the LLM era is it really highlights what things in life actually add value.
I haven’t had that experience at all. My experience is that if you allow people to be lazy they will be, at the expense of society. What has your experience been like?
My experience, AI has shown me that a lot of stuff I do online. Watching videos, reading random articles, is mostly vapid pointless nonsense.
AI slop has finally woken me up and I am prioritizing IRL activities with friends and family, or activities more in the real world like miniature painting, piano, etc. It's made me much more selective with what activities I engage in, because getting sucked in to the endless AI miasma isn't what I want for my life.
Re: Pakistani newspaper mistakenly prints AI prompt with the article
#168Earlier quoted context omitted.
LLM's don't have any internal concept of "actual response" vs "surrounding words". Just like they don't have a internal concept of system prompt vs user input. Just like they don't even have an internal concept of what the LLM emitted vs what was given to it! It's all just one long sequence. (Yes, it is possible to create tokens to represent category changes, but this is still in-band. the token is still just part of…
Thanks, so how is it possible for the Chatbot to box a Python response? Can't they use the same technique?
My understanding is: the training induces it to put Python code inside Markdown code fences, which the app interprets. It does that because the training data is full of examples of people doing that, because when people post Python code online it's very commonly in contexts where Markdown is understood that way.
... I suppose they could train the LLM to put a Markdown horizontal rule in the right place, but it sounds harder to get the system prompt to care about details like that consistently.
Re: Pakistani newspaper mistakenly prints AI prompt with the article
#169Earlier quoted context omitted.
The AI is prompting the human here, so the title isn't strictly wrong. ;)
Gemini has been doing this to me for the past few weeks at the end of basically every single response now, and it often seems to result in the subsequent responses getting off track and lower quality as all these extra tangets start polluting the context. Not to mention how distracting it is as it throws off the reply I was already halfway in the middle of composing by the time I read it.
In similar "news" Re: tangents, I've noticed Claude now suddenly starting to give up on problem analyses. After like three rounds of it trying to figure something out that I told it is a requirement, it suggests that we don't need to do that as it's a nice-to-have only anyway. If in auto-accept mode it'll start doing the other thing even. I have to catch it and tell it to not effing give up so easily and to stop giving me BS excuses turning hard requirements (literally the reason we're doing what we're doing) into a nice-to-have it can skip.
I guess they recently re-trained on too many "perpetual junior senior dev" stuff.
Re: Pakistani newspaper mistakenly prints AI prompt with the article
#170As the pioneers in the field say - prompts are as important as output and must be preserved and published along with code/output! Don't throw away your prompts.