🧑‍💻 Open Model Hackathon

Hugging Face, NVIDIA, Ollama, vLLM, and OpenAI challenge you to build something weird, useful, or groundbreaking (or all three!) with gpt-oss.

Virtual for the next six weeks, starting today.

Categories: Best Overall, Robotics, Weirdest Hardware, Local Agent, Useful Fine-tune, Wildcard, and For Humanity.

Winners will receive cash or NVIDIA GPUs.

Join: https://openai.devpost.com/

If you’re participating in the hackathon, feel free to use this thread for discussion!

@edwinarbus Thanks for sharing! I’ve never known about this sort of thing from day 1 before! Squeeeeeeee. :heart_eyes:

Please let us know if you’re tinkering on anything!

There’s no tinker: there’s only picking a specific category - and destroying it.

Plus, don’t get “special consideration” from OpenAI, or be DQ’d.

At least this time they went through a contest administrator. Who got those Christmas radios for tweeting from the last one, with 24 hours to make something?

Whatcha’ destrying @_j ?

Mine might fit in Useful Fine-tuning, Local Agent, or For Humanity. I’ll have to see what I can do.

Probably the wrong model for my prompt -> SPICE -> autorouted Gerber wishes…You aren’t going to smash any benchmarks.

I’d give advice “think locally” in general. The local category is a subset of that, the VC buzzword “agent” without using internet (aka no API services). And the model is knowledge-bound, so it’s not going to be filling in the lyrics fields of your MP3s.

Certainly. It sounds like the new oss models are operating at o4-mini-ish levels for most tasks, with fine tuning and training making it more and more appropriate for a specialized task over time.

Though I don’t envision an internet-agnostic scenario, personally; not that I don’t think it’s useful. Guess I’ll have to look into the definitions… because wouldn’t you want to fine tune a local agent?

Wow super awesome.

I guess I dropped my project too soon :smiley:

But totally happy with that!

Looking forward to seeing what everyone comes up with.

For Humanity!

The image is completely blank with a white background. (Captioned by AI)

For humanity! =)

What did you build? Think you could throw together something new in time?

Just my thread here from the last forum hackathon thread, a simple local Agentic system a bit like ‘Operator’ with the ability to share self-describing agents packed in GIFs.

It’s not very professional like you guys would do though, it’s a hobby project.

Feel free to use it / repurpose it for your project if it’s in any way useful though.

I don’t use things like Github, more interested in hacks around the edges that a smart AI might take. The value for me is in sharing these concepts though rather than any prize.

Make something beautiful :slight_smile: !

Passed along to a talented robotics student I know.

Hi everyone!
I’m not a developer, but I enjoy working out ideas and system structures. I’d like to share a concept — maybe someone here will find it worth building.

Idea #1 – “Health AI”
An application that:

  • Accepts lab results in PDF/JPEG, converts them to text, and translates into any needed language.

  • Stores them in a database and analyzes via an LLM (ChatGPT, Ollama, vLLM).

  • Compares results with both current and historical reference ranges.

  • Suggests additional tests or procedures to get a complete health picture.

  • Uses a node-based visual interface for easy navigation and linking.

Idea #2 – “Real-time ECG Analysis”
API stream from ECG → AI analyzes waveform patterns → provides recommendations or alerts in real time.

Idea #3 – “Profile Memory”
A feature for ChatGPT (or any OSS LLM) to store a small “profile window” with user info, which can be enabled/disabled for new sessions.

Idea #4 – “Node Share”
A visual node system where each block can be code, a function, or a prompt. Users can share ready-made node chains with each other.

:speech_balloon: If anyone here would like to expand on these ideas — I’d be happy if they help someone’s project!

@edwinarbus Do you know if Ollama will be releasing a version that works natively with the Responses API anytime soon?

I had a question regarding model providers - do I have to use the model locally on my machine or can I call an API to a provider serving it like Groq?

Feel free to use any model provider like Groq.

No news yet, but you can use Hugging Face’s proxy. How to run gpt-oss locally with Ollama

Hi Edwin, thanks for creating this thread. I look forward to posting here as the hackathon progress takes place.

I am looking for team members, if anyone here looking for a team, please do reply to this :slight_smile:

Hi GoldenJoe, if they are looking for a team, let me know.

I am finding team members. I am a Data Scientist, interested in LLM, RL and Causal Inference. Let me know if you have similar interests. We can brainstorm ideas together.