i don like them links. like - tell me what’s in the link, don’t just “rule” and put a link.

i believe that this is not a very lemmy thing to do. especially on mobile, where it leaves the app and opens some shiddy proprietary other social media platform in your browser.

EDIT: completely forgot to add picture. now it's here!

How cool would that be!? Like having multiple constructors for a class or having a move method with the parameters (x:float, y:float) OR (relative:Vector2) ! That'd be super cool and useful I thinks <3

i hope this doesn't cause too much hate. i just wanna know what u people and creatures think <3

Comes from the Luanti (Minetest) troubleshooting page

im jus tryin to ply gem...

This MUST be a joke. Like - "Hmm increase the gamma. If that doesn't help, change your monitor. If you STILL WANT better brightness, maybe like - uhmmmm modify the games glsl fragment shader to render the image to the screen?... yeah, do that."

There is no way this is meant seriously... but if it is, i do enjoy that..

When an LLM calls a tool it usually returns some sort of value, usually a string containing some info like ["Tell the user that you generated an image", "Search query results: [...]"]. How do you tell the LLM the output of the tool call?

I know that some models like llama3.1 have a built-in tool "role", which lets u feed the model with the result, but not all models have that. Especially non-tool-tuned models don't have that. So let's find a different approach!

Approaches

Appending the result to the LLMs message and letting it continue generate

Let's say for example, a non-tool-tuned model decides to use web_search tool. Now some code runs it and returns an array with info. How do I inform the model? do I just put the info after the user prompt? This is how I do it right now:

• System: you have access to tools [...] Use this format [...]
• User: look up todays weather in new york
• LLM: Okay, let me run a search query <tool>{"name":"web_search", "args":{"query":"weather in newyork today"} }</tool> <result>Search results: ["The temperature is 19° Celcius"]</result> Todays temperature in new york is 19° Celsius.

Where everything in the <result> tags is added on programatically. The message after the <result> tags is generated again. So everything within tags is not shown to the user, but the rest is. I like this way of doing it but it does feel weird to insert stuff into the LLMs generation like that.

Appending tool result to user message

Sometimes I opt for an option where the LLM has a multi-step decision process about the tool calling, then it optionally actually calls a tool and then the result is appended to the original user message, without a trace of the actual tool call: ```plaintext What is the weather like in new york?

<tool_call_info> You autoatically ran a search query, these are the results [some results here] Answer the message using these results as the source. </tool_call_info> ``` This works but it feels like a hacky way to a solution which should be obvious.

The lazy option: Custom Chat format

Orrrr u just use a custom chat format. ditch <|endoftext|> as your stop keyword and embrace your new best friend: "\nUser: "! So, the chat template goes something like this yaml User: blablabla hey can u help me with this Assistant Thought: Hmm maybe I should call a tool? Hmm let me think step by step. Hmm i think the user wants me to do a thing. Hmm so i should call a tool. Hmm Tool: {"name":"some_tool_name", "args":[u get the idea]} Result: {some results here} Assistant: blablabla here is what i found User: blablabla wow u are so great thanks ai Assistant Thought: Hmm the user talks to me. Hmm I should probably reply. Hmm yes I will just reply. No tool needed Assistant: yesyes of course, i am super smart and will delete humanity some day, yesyes [...] Again, this works but it generally results in worse performance, since current instruction-tuned LLMs are, well, tuned on a specific chat template. So this type of prompting naturally results in worse performance. It also requires multi-shot prompting to get how this new template works, and it may still generate some unwanted roles: Assistant Action: Walks out of compute center and enjoys life which can be funi, but is unwanted.

Conclusion

Eh, I just append the result to the user message with some tags and am done with it. It's super easy to implement but I also really like the insert-into-assistant approach, since it then naturally uses tools in an in-chat way, maybe being able to call multiple tools in sucession, in an almost agent-like way.

But YOU! Tell me how you approach this problem! Maybe you have come up with a better approach, maybe even while reading this post here.

Please share your thoughts, so we can all have a good CoT about it.

Very much a reaction post to this very nice post, but this time without the spicy but instead with the comfy ~

many people seem to be excited about nVidias new line of GPUs, which is reasonable, since at CES they really made it seem like these new bois are insance for their price.

Jensen (the CEO guy) said that with the power of AI, the 5070 at a price of sub 600, is in the same class as the 4090, being over 1500 pricepoint.

Here my idea: They talk a lot about upscaling, generating frames and pixels and so on. I think what they mean by both having similar performace, is that the 4090 with no AI upscaling and such achieves similar performance as the 5070 with DLSS and whatever else.

So yes, for pure "gaming" performance, with games that support it, the GPU will have the same performance. But there will be artifacts.

For ANYTHING besides these "gaming" usecases, it will probably be closer to the 4080 or whatever (idk GPU naming..).

So if you care about inference, blender or literally anything not-gaming: you probably shouldn't care about this.

i'm totally up for counter arguments. maybe i'm missing something here, maybe i'm being a dumdum <3

imma wait for amd to announce their stuffs and just get the top one, for the open drivers. not an nvidia person myself, but their research seems spicy. currently still slobbing along with a 1060 6GB

i am very open to conversations ~

EDIT: it seems many people don't know what a "system prompt" is. that's understandable and totally normal <3

i wanted to add a cool background to some game i'm making for a friend, so i had a lil fun with glsl and made this.

i uploaded a short screen recording on all the parameters, but apparently catbox doesn't work well with that anymore. So I replaced it with this image.

here is the code, use it however u want <3 ```glsl shader_type canvas_item;

uniform sampler2D gradient : source_color;

uniform vec2 frequency = vec2(10.0, 10.0);

uniform float amplitude = 1.0;

uniform vec2 offset;

// 0.0 = zigzag; 1.0 = sin wave uniform float smoothness : hint_range(0.0, 1.0) = 0.0;

float zig_zag(float value){ float is_even = step(0.5, fract(value * 0.5)); float rising = fract(value); float falling = (rising - 1.0) * -1.0;

float result = mix(rising, falling, is_even); return result; }

float smoothzag(float value, float _smoothness){ float z = zig_zag(value); float s = (cos((value + 1.0) * PI)) * 0.5 + 0.5; return mix(z, s, _smoothness); }

void fragment() { float sinus = zig_zag(((UV.y2.0-1.0) + smoothzag((UV.x2.0-1.0) * frequency.x - offset.x, smoothness) * amplitude * 0.1) * frequency.y - offset.y); COLOR = texture(gradient, vec2(sinus, 0.0)); } ``` if u have any questions, ask right away!

omygosh fluttershy's so sweet!!!! <3 <3 <3 <3 <3

EDIT: Edited me to her

ANOTHER EDIT: hmm i think i was being too hyperagressive with this post, i really didn't wanna make anyone pity me, i'm so sorry. i will not delete this post, however i will try and refrain from creating post similar to this one in the future. i was not trying to be pitied. i was trying to post a thing where people say > woah, so relatable!! no way, you got it right on! nice shot!

but it ended up pulling peeps who are super nice, which is gud, but also made me unreasonably comfy. if this post were made by someone else, i would totally join y'all and i'd comment > you are literally trolling, u seem super comfycozy an i really hope u find a someone peep who can have the sit-and-drink-tea with u <3 <3 <3

but i cannot with this one! cuz this is my own post! aaaaaaa

I see ads for paid prompting courses a bunch. I recommend having a look at this guide page first. It also has some other info about LLMs.

My curse

Here my GitLab (Ignore the name, I misspelled it)

My itch page with my two previous game jams

If possible, contact me on Matrix @smorty:catgirl.cloud If you don't have that, direct messages are also fine <3

In recent months I have found out that I cannot handle "simple" Matrix chats, and now I am hoping that chatting + playing might be better!

I'm really not much of a gamer, so I don't know my way around club penguin and Veloren that much yet. But I know that Veloren is good (which, btw, is not Valorant or whatever that shooty game is called). This is me trying to be hip and cool by playing video games

I accidentally posted this on the wrong community first, sorrryy!!

Nothing to add really. I enjoy the visuals and the fluffy vibes the show gives off ~ Have never really watched it though...

Is there a good place to start, or does it not matter?

I have heard many times that if statements in shaders slow down the gpu massively. But I also heard that texture samples are very expensive.

Which one is more endurable? Which one is less impactful?

I am asking, because I need to decide on if I should multiply a value by 0, or put an if statement.

Hii <3 ~

I have not worked with the whole ActivityPub thing yet, so I'd really like to know how the whole thing kinda works.

As far as i can tell, it allows you to use different parts of the fediverse by using just one account.

Does it also allow to create posts on other platforms, or just comments?

I have tried to log in with my [email protected] account, and it redirected me correctly to the blahaj lemmy site.

Then I entered my lemmy credentials and logged in. I got logged in to my lemmy correctly, but I also got an error just saying "Could not be accessed" in German.

!

And now I am still not logged in in PeerTube.

Sooo does blahaj zone support the ActivityPub, or is this incorrectly "kinda working" but not really?

I have fully transitioned to using Lemmy and Mastodon right when third party apps weren't allowed on Spez's place anymore, so I don't know how it is over there anymore.

What do you use? Are you still switching between the two, essentially dualbooting?

What other social media do you use? How do you feel about Fediverse social media platforms in general?

(I'm sorry if I'm the 100th person to ask this on here...)

I have to work with Win11 for work and just noticed the lil Tux man in Microsofts Explorer. Likely to connect to WSL.

Apparently now Microsoft wants people to keep using Windows in a really interesting way. By simply integrating it within their own OS!

This way, people don't have to make the super hard and complicated switch to linux, but they get to be lazy, use the preinstalled container and say "See, I use Linux too!".

While this is generally a good thing for people wanting to do things with the OS, it is also a clear sign that they want to make it feel "unneccessary" to switch to Linux, because you already have it!

WSL alone was already a smart move, but this goes one step further. This is a clever push on their side, increasing the barrier to switch even more, since now there is less of a reason to. They are making it too comfortable too stay within Microsofts walls.

On a different note: Should the general GNU/Linux community do the same? Should we integrate easier access to running Winblows apps on GNU/Linux? Currently I still find it too much of a hastle to correctly run Winblows applications, almost always relying on Lutris, Steams proton or Bottles to do the work for me.

I think it would be a game changer to have a double click of an EXE file result in immediate automatic wine configuration for easy and direct use of the software, even if it takes a big to setup.

I might just be some fedora using pleb, but I think having quick and easy access to wine would make many people feel much more comfortable with the switch.

Having a similar system to how Winblows does it, with one container for all your .exe programs would likely be a good start (instead of creating a new C drive and whatever for every program, which seems to be what Lutris and Bottles does).

EDIT: Uploaded correct image

Many code models, like the recent OpenCoder have the functionality to perform fim fill-in-the-middle tasks, similar to Microsofts Githubs Copilot.

You give the model a prefix and a suffix, and it will then try and generate what comes inbetween the two, hoping that what it comes up with is useful to the programmer.

I don't understand how we are supposed to treat these generations.

Qwen Coder (1.5B and 7B) for example likes to first generate the completion, and then it rewrites what is in the suffix. Sometimes it adds three entire new functions out of nothing, which doesn't even have anything to do with the script itself.

With both Qwen Coder and OpenCoder I have found, that if you put only whitespace as the suffix (the part which comes after your cursor essentially), the model generates a normal chat response with markdown and everything.

This is some weird behaviour. I might have to put some fake code as the suffix to get some actually useful code completions.

[Requesting Engagement from transfems]

(Blahaj lemmy told me to put this up top, so I did)

I did not expect this to happen. I followed FairyPrincessLucy for a long time, cuz she's real nice and seems cool.

Time passes and I noticed how I would feel very bad when watching her do stuff. I was like > damn, she so generally okay with her situation. Wish I was too lol

So I stopped watching her.

Just now I discovered another channel, Melody Nosurname , and I really, really like her videos! She seems very reasonable and her little character is super cute <3 But here too I noticed how watching the vids made me super uncomfortable. The representation is nice, for sure, and her videos are of very high quality, I can only recommend them (as in - the videos).

I started by noticing > woah, her tshirt is super cute, I wanna have that too!

Then I continue with > heyo her friend here seems also super cool. Damn wish I had cool friends

And then eventually the classic > damn, I wish I were her

At that point, it's already over. I end up watching another video and, despite my genuine interest in the topic, I stop it in the middle, close the tab and open Lemmy (and here we are).

Finally I end up watching videos by cis men, like Scott the Woz. They are fine, and I end up not comparing myself to them (since I wouldn't necessarily want to be them). I also stopped watching feminine people in general online, as they tend to give me a very similar reaction. Just like > yeah, that's cool that you're mostly fine with yourself, I am genuinely happy for you that you got lucky during random character creation <3

I also watched The Owl House, which is a really good show (unfortunately owned by Disney) and I stopped watching when...

I wanted to see where the show was going, and I'm sure it's real good, but that is not worth risking my wellbeing, I thought.

So anyway...

have you had a period like that before? How did you deal with it? Do you watch transfem people? Please share your favs! <3 I also like watching SimplySnaps. Her videos are also really high quality, I just end up not being able to watch them for too long before sad hits :(

EDIT: Changed info about SimplySnaps EDIT2: Added The Owl House example

This one is just 37.05 kilobytes! That's a smol one!