this post was submitted on 28 Aug 2025
526 points (99.8% liked)

Technology

74585 readers
3951 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots


founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] ArmchairAce1944@discuss.online 0 points 7 hours ago (2 children)

I asked chatgpt some spicy questions a long time ago (on the order of months), and it was about privacy questions and maintaining privacy online. I even asked it how to keep private from itself. I deleted that account many months ago and it was not immediately linked to my 'real' identity. I've also asked it some other spicy questions about stuff I won't reveal here. Again. Months ago, and by it's own admission if something is reported, it will be acted upon almost immediately. If something is super illegal (as in, I want to kill so-and-so individual) it not only reports it for immediate review but also reports the relevant law enforcement right away.

Chatgpt told me this.

The only way to use chatgpt if you must is with A: a throwaway email (must be reusable) such as those on darknet emails or something that doesnt link it to you by name (such as proton or tutamail). B: over the Tor network.

[–] brucethemoose@lemmy.world 1 points 2 hours ago* (last edited 2 hours ago) (1 children)

The only way to use chatgpt if you must is

-To use it over API.

Or, preferably, literally any other LLM API that isn't such a censored privacy nightmare.

The problem here is that most percieve ChatGPT as the only chatbot in existance... It's not, not even close.

Also, ChatGPT is really bad at spitting out its own policy, FYI. expect it to randomly hallucinate stuff.

[–] ArmchairAce1944@discuss.online 1 points 2 hours ago* (last edited 2 hours ago) (1 children)

Please tell me how to do it over an API. I really want to know.

Edit. I have LM studio and downloaded AI chatbots. But they give far more bullshit than chatgpt (which i rarely use much anyway), which is why talking to it feels even more pointless than chatgpt at times.

[–] brucethemoose@lemmy.world 2 points 2 hours ago* (last edited 2 hours ago) (1 children)

I am on mobile and can be more detailed later, if you want but the jist is to sign up (with a payment method) to some API service. There are many. Some neat ones include:

  • Openrouter (a gateway to many, many models from many providers, I’d recommend this first)
  • Cerebras API (which is faster than anything and has a generous free tier)
  • Google Gemini, which is free to just try this out on with no credit card.

Some great models to look out for, that you may not know of:

  • GLM 4.5 (my all-around favorite)

  • Deepseek (and its uncensored finetunes)

  • Kimi

  • Jamba Large

  • Minimax

  • InternLM for image input

  • Qwen Coder for coding

  • Hermes 405B (which is particularly ‘uncensored’)

  • Gemini Pro/Flash, which is less private but free to try.

Most (in exchanges for charging pennies for each request) do not log your prompts. If you are really, really concerned, you can even rent your own GPU instance on demand.

Anyway, they will give you a key, which is basically a password.

Paste that key into the LLM frontend of your choice, like Open Web UI, LM Studio, or even web apps like:

Or even the Openrouter web interface.

[–] ArmchairAce1944@discuss.online 2 points 54 minutes ago (1 children)

Damn! That is good shit! I'll definitely look into it.

[–] brucethemoose@lemmy.world 1 points 45 minutes ago* (last edited 40 minutes ago)

Yep!

Also, I'm going to plug the AI Horde, which is basically the Fediverse for AI self hosting: https://aihorde.net/

It's awesome! Though a bit sparsely populated, like Lemmy, heh.

Ping me, and I can host a medium-sized model to try for a few hours (via those linked web UIs), if you want. The options are limitless, from something STEM-focused like Nemotron 49B, to a long context model like Bytedance's new 36B, to, dungeonmaster finetunes, to horny as heck roleplaying models, lol. But they should be significantly better than whatever 8B ollama downloads by default.

[–] Randomgal@lemmy.ca 3 points 4 hours ago

Char GPT told you what you asked it to tell you. It has no awareness of itself or ita processes outside the context window.

You're anthropomorphizing de machine.