Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

The R1 GitHub repo is way more exciting than I had thought.

They aren't only open sourcing R1 as an advanced reasoning model. They are also introducing a pipeline to "teach" existing models how to reason and align with human preferences. [2] On top of that, they fine-tuned Llama and Qwen models that use this pipeline; and they are also open sourcing the fine-tuned models. [3]

This is *three separate announcements* bundled as one. There's a lot to digest here. Are there any AI practitioners, who could share more about these announcements?

[2] We introduce our pipeline to develop DeepSeek-R1. The pipeline incorporates two RL stages aimed at discovering improved reasoning patterns and aligning with human preferences, as well as two SFT stages that serve as the seed for the model's reasoning and non-reasoning capabilities. We believe the pipeline will benefit the industry by creating better models.

[3] Using the reasoning data generated by DeepSeek-R1, we fine-tuned several dense models that are widely used in the research community. The evaluation results demonstrate that the distilled smaller dense models perform exceptionally well on benchmarks. We open-source distilled 1.5B, 7B, 8B, 14B, 32B, and 70B checkpoints based on Qwen2.5 and Llama3 series to the community.




Where are you seeing this? On https://github.com/deepseek-ai/DeepSeek-R1/tree/main?tab=rea... I only see the paper and related figures.


I see it in the "2. Model Summary" section (for [2]). In the next section, I see links to Hugging Face to download the DeepSeek-R1 Distill Models (for [3]).

https://github.com/deepseek-ai/DeepSeek-R1?tab=readme-ov-fil...

https://github.com/deepseek-ai/DeepSeek-R1?tab=readme-ov-fil...


The repo contains only the PDF, not actual runnable code for the RL training pipeline.

Publishing a high-level description of the training algorithm is good, but it doesn't count as "open-sourcing", as commonly understood.


was genuinely excited when I read this but the github repo does not have any code.


[flagged]


this means we are going to get o3 level open source models in a few months. So exciting !


Is o3 that much better than o1? It can solve that Arc-AGI benchmark thing at huge compute cost, but even with o1, the main attraction (for me) seems to me that it can spit out giant blocks of code, following huge prompts.

I'm kinda ignorant, but I'm not sure in what way is o3 better.


> It can solve that Arc-AGI benchmark thing at huge compute cost

Considering DeepSeek v3 trained for $5-6M and their R1 API pricing is 30x less than o1, I wouldn’t expect this to hold true for long. Also seems like OpenAI isn’t great at optimization.


OpenAI is great at optimisation - compare the cost of -4o to -4. They just haven't optimised o3 yet.


4o is more expensive than DeepSeek-R1, so…? Even if we took your premise as true and we say they are as good as DeepSeek, this would just mean that OpenAI is wildly overcharging its users.


now openai has no other choice than shipping a cheaper version of o1 and o3. The alternative is everyone using r1 (self hosted or via openrouter, nebius AI, together AI and co)


yes o3 is better, but I would argue it is not yet clear for which cases it is absolutely crucial to use o3 instead of o1.


This is how you do "Open" AI.

I don't see how OpenAI isn't cooked. Every single foundation model they have is under attack by open source.

Dall-E has Stable Diffusion and Flux.

Sora has Tencent's Hunyuan, Nvidia's Cosmos, LTX-1, Mochi, CogVideo.

GPT has Llama.

o1 has R1.

And like with R1, these are all extensible, fine tunable, programmable. They're getting huge ecosystems built up around them.

In the image/video space there are ComfyUI, ControlNets, HuggingFace finetrainers, LoRAs. People share weights and training data.

Open source is so much better to base a company on than a proprietary model and API.

...

It looks there is no moat.


The moat might be tiny at the frontier level. But the mainstream still only knows about ChatGpt. OpenAI won consumer before others even started.


Which is funny because ChatGPT was sort of a random experiment and not like a planned attempt at a huge product launch.


indeed there is no moat. Open source will win !


I think open source AI has a solid chance of winning if the Chinese keep funding it with great abandon as they have been. Not to mention Meta of course, whose enthusiasm for data center construction shows no signs of slowing down.




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: