Hacker Newsnew | past | comments | ask | show | jobs | submit | gapeslape's commentslogin

I’m a solo entrepreneur - working on a questionnaire solving tool (think security questionnaires, RFPs and similar). Would love to hear any feedback.

https://requestfx.com


This reminds me of an idea I had a few days ago. Imagine a world where speed of light:

- 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?



This is awesome, thanks!

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.


I suppose the problem in multiplayer is that everyone has the same wall clock time, so you couldn't easily have consistent time dilation and related effects such as the twin paradox.


I agree with what you are saying.

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.


Your link is broken?


“30 hours of unattended work” is totally vague and it doesn’t mean anything on its own. It - at the very least - highly depends on the amount of tokens you were able to process.

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.


"Slack clone" is also super vague:

(First of all: Why would anyone in their right mind want a Slack clone? Slack is a cancer. The only people who want it are non-technical people, who inflict it upon their employees.)

Is it just a chat with a group or 1on1 chat? Or does it have threads, emojis, voice chat calls, pinning of messages, all the CSS styling (which probably already is 11k lines or more for the real Slack), web hooks/apps?

Also, of course it is just a BS announcement, without honesty, if they don't publish a reproducible setup, that leads to the same outcome they had. It's the equivalent of "But it worked on my machine!" or "scientific" papers that prove anti gravity with superconductors and perpetuum mobile infinite energy, that only worked in a small shed where some supposed physics professor lives.


Has their comment has been edited? A few words later it says it resulted in 11,000 LoC.

> [..] left it unattended for 30 hours, and it built a Slack clone using 11,000 lines of code [..]


Their point still stands though? They said the 1 tok/hr example was illustrative only. 11,000 LoC could be generated line-by-line in one shot, taking not much more than 11,000 * avg_tokens_per_line tokens. Or the model could be embedded in an agent and spend a million tokens contemplating every line.


If anyone is struggling with keeping up with EU regulations, we built an AI powered platform that helps companies navigate this complex world. You can find it at: https://fx-lex.com


This needing to exist is sad, but keep it up.


Thanks, I really appreciate it.

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.


I don't _necessarily_ have a problem with quantity, it's more about accessibility.

Rules are only fair if the people supposed to follow them can make sense of them.


The standard establishment reply s that "Ignorance of the law is no excuse".

Countered this with "Ignorance of how to write laws in plain language and make them easily accessible is no excuse".


In my mind, Gemini 2.0 changes everything because of the incredibly long context (2M tokens on some models), while having strong reasoning capabilities.

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.


What does "throw everything into the model" entail in your context?

How much data are you able to feed into the model in a single prompt and on what hardware, if I may ask?


Gemini models run in the cloud, so there is no issue with hardware.

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.


Maybe a dumb question, have you tried fine tuning on the corpus, and then adding a reasoning process (like all those R1 distillations)?


We haven't tried that, we might do that in the future.

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.


looks beautiful, great execution! do you mind sharing which fronted tools you used?


Thank you! The main website (https://www.myphotos.site) was built my co-founder Or using Webflow. He's a real pro when it comes to websites - see more of his work here https://gambit.design/

The user galleries and the editor dashboard are built using Next.js, Typescript, Tailwind, and Vercel. For the masonry, we first tried a few libraries (such as https://www.npmjs.com/package/react-masonry-css) but ended up writing our own because all the libraries we tried didn't handle proper column-height distribution.

Anything else you're curious about?


I bet the comment above was produced by generative AI.


Only the dialog about "sky is not blue" - yes, I generated it (formatted manually). Don't blame me, I can't stand that style.


It seems that the only two possible answers are "perhaps" and "no".

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

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


The paper linked explains what the “perhaps” are. The website is seemingly trying to drive a narrative that blockchains are unnecessary.


I kinda see the point though. State management is bundled with frontend development in such a way that even for simple projects it almost seems like necessity for most people.

Don't use things that you are not hundred percent sure you need. Blockchain is a robust solution for high complex state management issues but most people will never end up using it for its full potential. Even if you did there often are alternatives that performs much better for your need.

People will try to bend their projects to meet the blockchain need rather than just use it when you need to use it.


I think it attempts to paint them as overhyped. If the target would be to put down blockchains, the page would simply be a "No". But it's true that we throw blockchains at things that don't need a blockchain.


This seems like a nice example of chaotic system (https://en.wikipedia.org/wiki/Chaos_theory).


Any kind of atmospheric studies (or studies of currents) would indeed be an archetypal example of a chaotic system -- although much simpler dynamical systems would exhibit chaotic behaviors.


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

Search: