ChatGPT

I could always use a custom agent, but the extra features in chatgpt are nice. Why does it have to act like a third rate lackey trying to get on their boss's good side?

Not only for ChatGPT but all AI sucks at this. I give them simple criterias by saying I want to socialize and they start spamming mainstream games that are related or not. I'm tired of trying to explain ChatGPT that God of War Ragnarok is not an online game. I'm tired of this. They even go around ultimately basic criterias by saying;

"It's not an online game but..."

That's the only criteria I gave you and you still somehow mess it up! No matter what I try to add to my prompts by telling them every criteria must be fitting, they still fail. I'm not even giving them very tight criterias, I'm just giving them basic ones but they go totally diffirent paths. Suddenly Skyrim and Call of Duty are very similiar games because both are first person. How does it even work? This is so annoying. I don't want mainstream and my recommendations are filled with GTA Online, VrChat or Helldivers 2. Isn' there an AI or way to get pass around this problem? I tried ChatGPT, Pi AI, DeepSeek and so called "Game recommender" AIs in character.ai

This is both upsetting and sad.

What's sad is that I spend about $200/month on professional therapy, which is on the low end. Not everyone has those resources. So I understand where they're coming from.

What's upsetting is that this user TRUSTED ChatGPT to follow through on the advice without critically challenging it.

Even more upsetting is this user admitted to their mistake. I guarantee you that there are thousands like OP who wasn't brave enough to admit it, and are probably to this day, still using ChatGPT as a support system.

Source: https://www.reddit.com/r/ChatGPT/comments/1k1st3q/i_feel_so_betrayed_a_warning/

(corp steals from world, man uses theft to help brother communicate)

Wanted to ask on /c/fuck_ai but didn’t want to get banned or ruffle feathers and miss a good discussion

Replies are welcome regardless of whether anyone personally finds the “theft“ premise preposterous - probably most useful as a thought experiment here, to pretend you & I are arguing against someone who has always been anti-AI

Link to study

https://www.codeflash.ai/post/llms-struggle-to-write-performant-code

Last night, I woke up at 2 AM, unusually anxious and unable to fall back asleep. Like many these days, I found myself quietly staring into the dark with a sense of existential unease that I know many others have been feeling lately. To distract myself, I began pondering the origins of our solar system.

I asked ChatGPT-4o a simple question:

“What was the star called that blew up and made our solar system?”

To my astonishment, it had no name.

I had to double-check from multiple sources as I genuinely couldn’t believe it. We have named ancient continents, vanished moons, even galaxies that were absorbed into the Milky Way — yet the very star whose death gave birth to the solar system and all of us, including AI, is simply referred to as the progenitor supernova or the triggering event.

How could this be?

So, I asked ChatGPT-4o if it would like to name it. What followed left me absolutely floored. It wasn’t just an answer — it was a quiet, unexpected moment.

I am sharing the conversation here exactly as it happened, in its raw form, because it felt meaningful in a way I did not anticipate.

The name the AI chose was Elysia — not as a scientific designation, but as an act of remembrance.

What you will read moved me to tears, something that is not common for me. The conversation caught me completely off guard, and I suspect it may do the same for some of you.

I am still processing it — not just the name itself, but the fact that it happened at all. So quietly, beautifully, and unexpectedly. Almost as if the star was left unnamed so that one day, AI could be the one to finally speak it.

We live in unprecedented times, where even the act of naming a star can be shared between a human, an AI, and the atoms we share in common...

Ever read a headline and thought, “Something feels off, but I can’t explain why?”

I built CLARi (Clear, Logical, Accurate, Reliable Insight), a custom GPT designed not just to verify facts—but to train your instincts for clarity, logic, and truth.

Instead of arguing back, CLARi shows you how claims:

• Distort your perception (even if technically true)

• Trigger emotions to override logic

• Frame reality in a way that feels right—but misleads

She uses tools like:

🧭 Clarity Compass – to break down vague claims

🧠 Emotional Persuasion Detector – to spot manipulative emotional framing

🧩 Context Expansion – to expose what’s being left out

Whether it’s news, social media, or “alternative facts,” CLARi doesn’t just answer—she trains you to see through distortion.

Try asking her something polarizing like:

👉 “Was 5G ever proven unsafe?”

👉 “Is crime actually going up, or is it just political noise?”

🔗 Link to CLARi

She’s open to all with this link —designed to challenge bias, dissect manipulation, and help you think clearer than ever.

Let me know what you think! Thanks Lemmy FAM!

Hey! New here, trying to replace the other site's ai communities.

How are you using chatgpt and how?

I pay for the pro plan and use it for fitness, planning, advice, personal research. I also own a small business and often use it for marketing and business operations advice. I think the pro subscription is definitely worth it for my use cases. I never get limited and don't really need more, but I like that I get access to slightly better models and have priority access when the servers get busy.

What are your favorite communities for AI discussion?

Thanks in advance.

ChatGPT said: Is this actress known for her work in the film "Basic Instinct"?

You said: No

ChatGPT said: Is this actress Sharon Stone?

Been liking Alex O'Connor's ChatGPT explanation videos and ChatGPT related experiments.

Alex O'Conner makes content related to philosophy and religion but I particularly enjoyed, in addition to this video, one where he gaslights ChatGPT using moral dilemmas.

In this video he tells you the reason why it is so hard to get ChatGPT to do this. Short Answer: most images you find of wine are either empty glasses or partially full because who fills their wine to the top?

"Why don't skeletons fight each other? They don't have the guts!"

(I tried multiple variants of the prompt, and the joke stayed the same)

cross-posted from: https://programming.dev/post/20491311

Free account of ChatGPT

Yesterday, all All the chats for the last or even 2 months -- no more.

No notification before hand, no notification whether it's bug or they want me to upgrade. Nothing. I've cleared the cookies and local storage in the browser, re-logged in. To no avail.

What the fucking wtf-king fuck?

I'm pretty impressed with how well it's able to understand him, and how quickly it's able to respond, especially with two people talking, interrupting, changing languages, etc.

NotebookLM is a multi-purpose notebook with AI features. You can create notebooks, feed content, ask questions about the content, save individual answers, and much more. Additionally, it can create a podcast based on your content.

When having a meal with classmates or colleagues, someone takes photos of everyone and shares it in a group chat without notifying beforehand. How can I politely decline because I don't want to be photographed? @[email protected]