![](https://lemmy.blahaj.zone/pictrs/image/1AxRiGwL8E.png)
And / or, a bad person!
And / or, a bad person!
Yeah, I agree. I do sort of understand op’s consternation. I don’t browse Lemmy on my work PC, but sometimes on lunch or in public I pull it up on my phone on All communities and I’m suddenly conscious that everyone beside me can see the “sfw” furry and anime art that I scroll past.
However, that’s kinda my fault. I don’t want to ban those communities because I like that stuff. It’s just a little odd that we call it sfw when, to be honest, I have a hard time picturing most work places where I live happy to see that on my desktop.
Yeah, that would be great. Many instance admins already use CSAM classifier models on all incoming images. It’d be great if they could add additional models that could put meta tags on images automatically like “suggestive” and “gore” with the option for the poster to modify the tags just in case it was a false negative or positive. Like a lasagna getting gore, for example.
I feel like the Internet needs more tags:
Something like that.
I believe Librechat would achieve your goals, but you’d need a PC or server to host it in. It supports all major API.
Kobold light might with as well, and doesn’t need to be hosted locally, but I don’t think it supports Claude haiku specifically, for unknown reasons.
Additionally, the official Claude api workshop is pretty good on desktop, but it only supports Claude.
I mean, be careful. These llms can be honeypots for data. Like, if you’re using it for cover letters, or work, you’re sending tons of personal info to random websites.
I would recommend sticking to actual, reputable vendors for llms, or running your own. I have a GTX 1070 and can run some pretty decent models these days locally using koboldai.
Bing is probably the only way to use gpt 4 without paying for it, and Microsoft probably won’t steal your bank account info.
There is almost no chance that it is truthfully based on gpt 4. If you want a free, open source llm with 32k context and generous limits, I recommend using huggingface.co/chat/
The nous-hermes model (you can select different models) is uncensored, and performs really well for a open source model. Plus, they have data controls so you can turn off data gathering per model. Huggingface is a reputable vendor, and doesn’t claim to be something it isn’t.
This feels… Scammy? Not to be accusatory, but gpt 4 is expensive to run. It is impossible for people to use it for free.
What llm is actually providing the response here? Either someone is footing the bill for an API and acting as a proxy, a situation which raises many red flags, or the model you’re talking to is something far cheaper to run, like a mistral model.
Even the second case is sketchy. 😅
In some respects, I can see this. Games such as unscrupulous MMOs are often carefully engineered to distort your ability to manage time and money. However, many games are still produced as entertainment products meant to compete on a basis of artistic or entertainment value. The addictive aspect doesn’t come from a manipulative design, but Rather just plain old fun, and in those cases similar arguments could be made about strawberries or books.
I would like to reiterate that there are addictive video games which really do try to manipulate you. Just like how a breakfast cereal might market itself as healthy and balanced while loaded with sugar and deceptive portion sizes, leading to unhealthy habits, a money first video game will contain elements carefully crafted to distort player’s perception and reasoning.
It’s just… All mixed together.
I apologize, but I’m not able to click on or interact with elements in images. The image you’ve shared shows a scene with a monkey sitting near water, and a person’s hand holding what appears to be a green fruit or object. The text at the top of the image says “HOW TO TRICK A MONKEY”. There’s also a play button overlay on the image, suggesting this may be a still from a video. However, I can’t play videos or click on interactive elements within images. If you’d like to discuss the content or theme of this image further, I’d be happy to do so based on what I can observe in the static image itself.