https://requestfx.com

I wonder if you could make it multiplayer and then get the effects of time dilation?

In my imagined world I also wanted to explore speeds above the speed of light. You could just stick to galilean transformation, take a very low speed of light and go from there. The world you get should be pretty bizarre.

- is small compared to human level speeds (say 2km/h / 1.25mph)

- things could move faster than the speed of light.

I really wonder how it would feel to explore this world visually. For example:

- an object in front of me accelerates from 0 to above the speed of light

- I'm in a car, looking backwards, going from 0 to above the speed of light

I guess one could easily simulate that in a virtual world, no?

I’m building a tool that helps you solve any type of questionnaire (https://requestf.com) and I just can’t imagine how I could leverage Apps.

It would be awesome to get the distribution, but it has to also make sense from the UX perspective.

Just to illustrate, say you are running on a slow machine that outputs 1 token per hour. At that speed you would produce approximately one sentence.

I do think that the amount of regulation is proportional to the complexity of the society. While you can over or under regulate, the general future trend will be more regulations.

My intuition - not based on any research - is that recall should be a lot better from in context data vs. weights in the model. For our use case, precise recall is paramount.

The EU regulations typically include delegated acts, technical standards, implementation standards and guidelines. With Gemini 2.0 we are able to just throw all of this into the model and have it figure out.

This approach gives way better results than anything we are able to achieve with RAG.

My personal bet is that this is how the future will look like. RAG will remain relevant, but only for extremely large document corpuses.

We are working on compliance solution (https://fx-lex.com) and RAG just doesn’t cut it for our use case. Legislation cannot be chunked if you want the model to reason well about it.

It’s magical to be able to just throw everything into the model. And the best thing is that we automatically benefit from future model improvements along all performance axes.

I’m a solo founder, and I’ve been working on an AI tool that helps companies and organizations navigate and comply with EU regulations. The platform leverages AI to provide insights, research capabilities, and compliance assistance, aiming to reduce the complexity and time spent dealing with regulatory requirements.

Compliance with EU regulations (like GDPR, labor laws, and industry-specific rules) can be overwhelming, especially for SMEs and startups. As someone passionate about tech and legal simplification, I saw an opportunity to create a tool that streamlines this process, providing actionable guidance while cutting down costs.

What the tool does:

- Uses AI to answer EU regulatory questions.

- Provides links to legislation articles, so that users can dig deeper when needed.

- The tool condenses complex legislation into clear summaries, drastically reducing the time needed to understand key topics.

As the only person behind this project, I wear multiple hats—coding, marketing, business development, and more. I’ve learned a lot, but I know there’s so much more to improve, particularly in product-market fit, user onboarding, and getting the word out.

I'd love to hear from the HN community on a few topics in particular:

- Product feedback: Does this solve a real problem for you or someone you know?

- Marketing advice: What are the best ways to promote a niche AI tool like this?

- Solo founder tips: For those who’ve been here, what’s your advice on staying productive and scaling effectively?

I’d love to hear your thoughts, suggestions, or even criticisms. Also, if you’ve had experience dealing with EU regulations, does this tool sound useful? What features would you want to see?

Here’s the link to the tool: https://eur-lex.ai/

Thank you, and I’m looking forward to hearing your feedback!

Comments URL: https://news.ycombinator.com/item?id=42472053

Points: 11

# Comments: 2

If the answer is "perhaps", why don't the authors list viable alternatives?

Perhaps this is how we could all actually learn something new.

Comments URL: https://news.ycombinator.com/item?id=15636413

Points: 1

# Comments: 0