HackerTrans
TopNewTrendsCommentsPastAskShowJobs

kshitij_libra

no profile record

Submissions

Ask HN: Independent Research, Review and Publication

4 points·by kshitij_libra·2 jaar geleden·4 comments

Can LLM benchmarks evaluate React coding skills?

kshitij-banerjee.github.io
1 points·by kshitij_libra·2 jaar geleden·0 comments

Ask HN: Can LLM's produce useful code?

4 points·by kshitij_libra·2 jaar geleden·11 comments

Can LLM's produce useful code?

kshitij-banerjee.github.io
2 points·by kshitij_libra·2 jaar geleden·1 comments

Can LocalLLMs write React Code?

kshitij-banerjee.github.io
1 points·by kshitij_libra·2 jaar geleden·0 comments

Ask HN: Prediction game - stock lock-in for 10years.

1 points·by kshitij_libra·2 jaar geleden·2 comments

How to build – Tony Fadell [Book summary]

kshitij-banerjee.github.io
2 points·by kshitij_libra·2 jaar geleden·0 comments

Show HN: Logseq and GTD (getting things done)

kshitij-banerjee.github.io
2 points·by kshitij_libra·2 jaar geleden·0 comments

Ask HN: How would you build OSS Figma?

7 points·by kshitij_libra·2 jaar geleden·8 comments

comments

kshitij_libra
·vorig jaar·discuss
This seems very useful. Why not make it paid ? Do you think your customers won’t buy ? Have you tried ?

What would your customers need to make them want to pay for it ?
kshitij_libra
·vorig jaar·discuss
Do you plan to write the book ? I’d like to read it
kshitij_libra
·2 jaar geleden·discuss
IMG_0163 - Gold
kshitij_libra
·2 jaar geleden·discuss
nopes.. beyond starter projects, raw usage of chatgpt hardly leads to any gains in productivity in the enterprise setting .

So far no, but in the future with more specific and enterprise suitable tooling - likely
kshitij_libra
·2 jaar geleden·discuss
Yes, but then a PhD is a chicken and egg problem. You can't get into the top PhD programs under a respectable professor - unless you have some publications under your name.

So how does one get published, enough to get into a good PhD program?
kshitij_libra
·2 jaar geleden·discuss
Right. I think the ability to run tests/compilation as a feedback mechanism is definitely interesting .

I wonder whether the problem is that its landed on an incorrect output sample (i.e re-sampling another code output would fix it ) .. vs … a feedback loop on the compiler output is what it really needs ..
kshitij_libra
·2 jaar geleden·discuss
No, I meant to ask HN, but didn’t realise that if I put a URL it doesn’t start a discussion.. and now there is no delete button
kshitij_libra
·2 jaar geleden·discuss
> Other tasks have an element of looping which is really fundamental in computer science

Have you tried any of these agent based workflows that claim to be able to loop with some amount of reasoning ?
kshitij_libra
·2 jaar geleden·discuss
100% I’d rather have specialised LLMs that can solve some hairy problems like CSS , than what we have now
kshitij_libra
·2 jaar geleden·discuss
Precisely. I think it helps with smaller/mundane tasks (that it has seen in its training), but the tasks that actually require a higher level reasoning and understanding of the bigger picture - are not something we can expect the current LLM's to do.

However as I was researching, there are a few interesting ideas in this space that might help these LLM's solve more complex problems in the future. Post here if interested: https://kshitij-banerjee.github.io/2024/04/30/can-llms-produ...
kshitij_libra
·2 jaar geleden·discuss
After using code LLMs' for a bit, I wonder whether there is significant productivity gain in using them. I found that its limited for me.

Main reason: a) to find the right code, I have to keep sampling it, and b) it doesn't seem to be able to solve larger / more complex problems that I actually find more need for.

I found some interesting research on combining planning-algorithms for complex problems, and some ideas on guiding the LLM's decoding process towards correctness by optimizing it via reward functions and reducing the search space. I've detailed and summarised the main points in the post above.

Questions:

1) Do you find code LLM's really useful? Please share some stories / examples where they help vs they didn't. I'm trying to form a better understanding they are just fancy, vs actually productive and useful to most

2) Any other research ideas being pursued in this field ? / what are you trying ?
kshitij_libra
·2 jaar geleden·discuss
Hi - ( some questions as i’m curious about your entrepreneurship journey )

Does anyone pay for this ? how does this compare to other products ? what made you build this ?
kshitij_libra
·2 jaar geleden·discuss
This trend really needs to die. If you can’t come up with an original paper name , maybe the contents aren’t that original either
kshitij_libra
·2 jaar geleden·discuss
Is this how you kill superman?
kshitij_libra
·2 jaar geleden·discuss
Meta, Shopify - both companies reject the Agile + Microservice cult
kshitij_libra
·2 jaar geleden·discuss
yeah, I think I like your approach, but the multiplayer aspect seems to be a great add-on, as opposed to a must-have feature to get the product started.

Both Go and Rust, and wasm are new to me - so i'm wondering about whether one is superior to the other.

I think figma has a lot of feature, and penpot seems a great replica of it, but I'm not too sure if the SVG + Clojurescript is a great way to build it..

I'm really looking for the core figma feature set to build. 1. Ability to have a canvas with zooms / freedom to create elemnets 2. Components and instances, and tree structured layers 3. Autolayout + CSS options. Frames and Pages

I think with the above 3, there's a viable basic feature set that would get one off the ground.

I did try the figma plugin apis, to extend native figma capabilities - but there's a limit to things you can do with it and it's getting to a point where more investment in the figma plugin seems a bit wasteful
kshitij_libra
·2 jaar geleden·discuss
Yeah, PenPot (mentioned in the comments below), seems to have chosen SVG as their choice of rendering. But, looking at a few customer reviews - the performance issue seems to be noticable with the SVG approach (zooms are not clean, and more than 20 screens it starts feeling slow).

Wasm seems appropriate. Why Go, instead of Rust ?
kshitij_libra
·2 jaar geleden·discuss
nice! Are you affiliated/ working at penpot?
kshitij_libra
·3 jaar geleden·discuss
The Great Mental Models - Shane Parrish