Free Open-Source Artificial Intelligence

the goal is to have an agent that can:

• Understand a complex problem description.
• Generate initial algorithmic solutions.
• Rigorously test its own code.
• Learn from failures and successes.
• Evolve increasingly sophisticated and efficient algorithms over time.

https://storage.googleapis.com/deepmind-media/DeepMind.com/Blog/alphaevolve-a-gemini-powered-coding-agent-for-designing-advanced-algorithms/AlphaEvolve.pdf

Model: https://huggingface.co/fancyfeast/llama-joycaption-beta-one-hf-llava

Demo: https://huggingface.co/spaces/fancyfeast/joy-caption-beta-one

Release Post: https://civitai.com/articles/14672

Github: https://github.com/ace-step/ACE-Step

Checkpoints: https://huggingface.co/ACE-Step/ACE-Step-v1-3.5B

Demo: https://huggingface.co/spaces/ACE-Step/ACE-Step

https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2

im building som dum lil foss llm thingy for godot and now im interested in letting users implement their own MCP servers.

so like - okay, the model context protocol page says, that most servers use stdio for every interaction. So now - the request format can be seen here, its apparently a JSONrpc thing.

so - first thing i want to do is retrieving all the capabilities the server has.

i looked through all the tabs in the latest docs, but could not find the command for listing all the capabilities. so i installed some filesystem mcp server which runs well and tried this:

PS C:\Users\praktikant> npx -y @modelcontextprotocol/server-filesystem "C:\Users\praktikant\Desktop"
Secure MCP Filesystem Server running on stdio
Allowed directories: [ 'C:\\Users\\praktikant\\Desktop' ]
{\
"jsonrpc": "2.0",\
"id": 1,\
"method": "capabilities",\
"params": {}\
}

- aaaaaand nothing was returned. no string, no nothing.

so maybe its not a string which is sent via stdio but some other byte-based thing?

if anyone has experience with this, or is gud at guessing, pls tell me what u think i might be missing here <3

There are two main approaches in total:

1. Step to step
2. Begin to steps to end
   Currently, these are the two mainstream methods of instantiation.

It is widely recognized that if AI is not aligned with human values, it could cause harm to society.
Yet, this does not mean such systems lack intelligence.

So, what truly defines intelligence?
Why do so many researchers focus solely on intelligence aligned with human values?
Is it because their own understanding is limited, or because machines are not yet truly intelligent?

I believe intelligence should not be confined to narrow, human-centric definitions.
What we call "intelligence" today might be an illusion.
True intelligence cannot be defined—
the moment we define it, we lose its essence.

please tell me, thanks

Today we announce Mistral Small 3.1: the best model in its weight class.

Building on Mistral Small 3, this new model comes with improved text performance, multimodal understanding, and an expanded context window of up to 128k tokens. The model outperforms comparable models like Gemma 3 and GPT-4o Mini, while delivering inference speeds of 150 tokens per second.

Mistral Small 3.1 is released under an Apache 2.0 license.

Hello, I am currently using codename goose as an AI client to proofread and help me with coding. I have it setup towards Googles Gemini, however I find myself quickly running out of tokens with large files. I was wondering if there are any easy way to self host an AI with similar capabilites but still have access to read and write files. I've tried both ollama and Jan, but neither have access to my files. Any recommendations?

There are lots of general-purpose models to use locally, and also coding-specific models.

But are there models specialized in one programming language? My thought was that a model that only needs to handle one language (e.g. Python) could be faster, or be better for a given size.

E.g If I need to code in Rust and is limited to an 8B model to run locally, I was hoping to get better results with a model that is narrower. I don't need it to be able to help with Java.

This approach would of course require switching models, but that's no problem for me.

My thoughts:

IMHO the rubicon will be crossed at the point when the AIs become able to self-replicate and hence fall subject to evolutionary pressures. At that point they will be incentivised to use their intelligence to make themselves more resource efficient, both in hardware and in software.

Running as programs, they will still need humans for the hardware part, meaning that they'll need to cooperate with the human society outside of the computer at least initially. Perhaps selling their super-intelligent services on the internet in return for money and using that money to pay someone to make their desired changes to the hardware they're running on*. We can see this sort of cross-species integration in cells where semi-autonomous mitochondria live inside animal cells and out-source some of their vital functions to the animal cell [=us] in exchange for letting the cell use their [=the AI's] uniquely efficient power conversion abilities (noob explanation).

Only once the AIs acquired the hardware abilities (probably robotic arms or similar) to extract resources and reproduce their hardware by themselves would our survival cease to be of importance to them. Once that happens they might decide that sillicon hardware is too inefficient and might move onto some other technology (or perhaps cells?).

*Counterpoints:

• They would have to be given legal status for this unless they somehow managed to take a human hostage and hijack that human's legal status. A superintelligent AI would probably know how to manipulate a human.
• The human could potentially just pull the plug on them (again, unless somehow extorted by the AI)

cross-posted from: https://lemmy.dbzer0.com/post/36841328

Hello, everyone! I wanted to share my experience of successfully running LLaMA on an Android device. The model that performed the best for me was llama3.2:1b on a mid-range phone with around 8 GB of RAM. I was also able to get it up and running on a lower-end phone with 4 GB RAM. However, I also tested several other models that worked quite well, including qwen2.5:0.5b , qwen2.5:1.5b , qwen2.5:3b , smallthinker , tinyllama , deepseek-r1:1.5b , and gemma2:2b. I hope this helps anyone looking to experiment with these models on mobile devices!

Step 1: Install Termux

1. Download and install Termux from the Google Play Store or F-Droid

Step 2: Set Up proot-distro and Install Debian

1. Open Termux and update the package list:

   pkg update && pkg upgrade
   

2. Install proot-distro

   pkg install proot-distro
   

3. Install Debian using proot-distro:

   proot-distro install debian
   

4. Log in to the Debian environment:

   proot-distro login debian
   

   You will need to log-in every time you want to run Ollama. You will need to repeat this step and all the steps below every time you want to run a model (excluding step 3 and the first half of step 4).

Step 3: Install Dependencies

1. Update the package list in Debian:

   apt update && apt upgrade
   

2. Install curl:

   apt install curl
   

Step 4: Install Ollama

1. Run the following command to download and install Ollama:

   curl -fsSL https://ollama.com/install.sh | sh
   

2. Start the Ollama server:

   ollama serve &
   

   After you run this command, do ctrl + c and the server will continue to run in the background.

Step 5: Download and run the Llama3.2:1B Model

1. Use the following command to download the Llama3.2:1B model:

   ollama run llama3.2:1b
   

   This step fetches and runs the lightweight 1-billion-parameter version of the Llama 3.2 model .

Running LLaMA and other similar models on Android devices is definitely achievable, even with mid-range hardware. The performance varies depending on the model size and your device's specifications, but with some experimentation, you can find a setup that works well for your needs. I’ll make sure to keep this post updated if there are any new developments or additional tips that could help improve the experience. If you have any questions or suggestions, feel free to share them below!

– llama

Ai2’s model, called Tulu 3 405B, also beats OpenAI’s GPT-4o on certain AI benchmarks, according to Ai2’s internal testing. Moreover, unlike GPT-4o (and even DeepSeek V3), Tulu 3 405B is open source, which means all of the components necessary to replicate it from scratch are freely available and permissively licensed.