Skip Navigation

ikt

@ Eyekaytee @aussie.zone

Posts
125
Comments
674
Joined
3 yr. ago

  • Qwen-Image is here

    Jump

  • ah awesome, let me check! i used qwen for ages before flicking over to GLM and I've not been impacted but it's not like i ask about chinese government things very often

  • Qwen-Image is here

    Jump

  • You can't run Qwen-image in LM Studio? It doesn't support image generation:

  • Qwen-Image is here

    Jump

  • How are you running this?

  • Qwen-Image is here

    Jump

  • TBH I haven't used any local image generators like Flux etc in a long time so I'm not even sure how to input this in, I think LM Studio is still a way off

    What do you use?

  • Microsoft Has a Surface Laptop 'Smurface Edition' for Smurfs Fans

    Jump

  • cut the shit and try making a laptop that doesn’t suck

  • Proton releases a new app for two-factor authentication

    Jump

  • as above trying to get away from american services, it’s really, youtube, google maps and iphone are only things im stuck with

  • Proton releases a new app for two-factor authentication

    Jump

  • fuck yeah, goodbye authy

  • Proton freezes Swiss investment over surveillance fears

    Jump

  • For those who didn't read the article

    “If the proposals pass, Proton’s services in Switzerland would be less private than Google’s,” Mr Yen told Le Temps. Frustrated by the lack of assurances from Beat Jans, the federal councillor overseeing the matter, Proton has opted to halt Swiss investments and shift its infrastructure plans abroad. Its artificial-intelligence data centres, deemed especially sensitive, will be located in Germany and Norway and involve investing CHF 100 million.

  • Deleted

    Permanently Deleted

    Jump

  • is the joke that bill nye is a science nerd and you're using the language of urban youth?

  • Long Island man wearing 9kg-metal necklace dies after being sucked into MRI machine

    Jump

  • nah just a heart attack, I can't actually picture it outside of the magnet jerking him towards the MRI machine

  • Long Island man wearing 9kg-metal necklace dies after being sucked into MRI machine

    Jump

  • that’s terrible :(

    i assume he must have thought because the machine was off it wasn’t an issue

    and died of a heart attack as well damn

  • Female Peasant

    Jump

  • i don’t get it

  • OpenAI just launched its new ChatGPT Agent that can make as many as 1 complicated cupcake order per hour, but even Sam Altman says you probably shouldn't trust it for 'high-stakes uses'

    Jump

  • yes in the wired article one of them says they would like to find out where it got stuck taking an hour with an agent replay feature

  • OpenAI just launched its new ChatGPT Agent that can make as many as 1 complicated cupcake order per hour, but even Sam Altman says you probably shouldn't trust it for 'high-stakes uses'

    Jump

  • for coding you want to use claude

    if you don’t want to pay for claude after so many messages what you can do is use mistral to code it up then use claude to proof check the code

  • Dentist accused of fatally poisoning his wife asked daughter to create AI deepfake of mom asking for chemicals

    Jump

  • If they divorce, they have to split their possessions

    Better murder another human being then?! That's a foolproof plan

    To me just easier to walk away with half than literally murder someone

    I don't think I'll ever get it

  • OpenAI just launched its new ChatGPT Agent that can make as many as 1 complicated cupcake order per hour, but even Sam Altman says you probably shouldn't trust it for 'high-stakes uses'

    Jump

  • I don’t want to spend an hour on tasks that would normally take 10 minutes.

    I don't get it, do you think she spent an hour talking to ChatGPT to try and get it to order doughnuts?

  • Dentist accused of fatally poisoning his wife asked daughter to create AI deepfake of mom asking for chemicals

    Jump

  • i'll never understand what is going through these guys minds when they can just get up and leave

    it makes no sense to me

  • I totally missed the point when PeerTube got so good

    Jump

  • I saw recently they are preparing for this

    https://lmstudio.ai/blog/free-for-work

    Commercial Plans

    LM Studio is a conduit for open source models and AI software. It's meant to be the first place you go to try new models, and a place where you can do professional grade work over months and years. In addition to the app, we're also shipping the LM Studio SDK and recently the Hub. The LM Studio Hub is where you can share your LM Studio "stuff": things you create within the app or with the SDK.

    Putting all these things together, companies often have a need for fine-grained control over the models (and recently MCPs) their users can run, or require access control capabilities for various artifacts (presets, configurations, etc.) shared within the team.

    Later this week, we will introduce a way to create a public Hub organization for your team, and use it with LM Studio at work (or school, or anywhere) for free. For companies that require more advanced features like SSO, model / MCP gating, and private collaboration: we are offering an Enterprise plan. A growing list of Fortune 500 companies, universities, and global organizations are already using LM Studio for Enterprise. If this sounds like something you need, contact us to get started.

    In line with reducing friction for using LM Studio at work, we will also be introducing a simple self-serve Teams plan later this month that enables sharing various artifacts privately within your team. Sign up to be notified when it becomes available.

  • I totally missed the point when PeerTube got so good

    Jump

  • Then why are you defending it?

    I'm not defending it, you were just way off base about it and then decided to double down, who's the AI now? 😉

    ChatGPT steals many of the features from other LLM's and websites, bit like how Microsoft and Apple and Linux all copy and steal from each other

    Yes, the summary is right

    Great! Turns out AI doesn't hallucinate everything, it might actually be useful! 🤣

    And if that's the case then you need not worry! If you are worried about the accuracy of a statement you can click on the links provided.

    This allows you to do 2 things:

    1. on things you are looking for an approximation of you get immediate results (Benefit of using AI)
    2. if you would like to look further into the results you can click on the links like a regular search engine (benefit of integrated search results)

    Like how many times does it need to repeat the same thing over and over again?

    Because I want it to be and I like it this way :) if you prefer all responses to be more brief you can change it using the system prompt:

    I asked it to say the same thing but to be brief:

    The phrase suggests skepticism about AI's ability to accurately summarize web content without introducing errors or distortions, likening the process to a "game of telephone" where information gets garbled as it passes through multiple layers (e.g., original source → AI interpretation → human sharing). The user is implying that relying on AI for this could lead to misinformation.

    The cool thing is that no search engine can assist in such a personalised way like this

    This is cool as heck:

    Anyway thanks for your time, time to sleep