Hacker News: kshitij_libra

New comment by kshitij_libra in "Ask HN: What are you working on? (March 2025)"

kshitij_libra — Mon, 31 Mar 2025 01:20:42 +0000

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 ?

New comment by kshitij_libra in "You might not need Redis"

kshitij_libra — Sun, 09 Mar 2025 01:15:24 +0000

Do you plan to write the book ? I’d like to read it

New comment by kshitij_libra in "IMG_0001"

kshitij_libra — Wed, 04 Dec 2024 09:34:08 +0000

IMG_0163 - Gold

New comment by kshitij_libra in "Ask HN: Do you already see the impact of LLMs on the job prospects for dev's?"

kshitij_libra — Wed, 17 Jul 2024 11:24:29 +0000

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

New comment by kshitij_libra in "Ask HN: Independent Research, Review and Publication"

kshitij_libra — Sun, 12 May 2024 14:16:42 +0000

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?

Ask HN: Independent Research, Review and Publication

kshitij_libra — Tue, 07 May 2024 10:00:32 +0000

I am building a set of benchmarks and I’d like to publish results.

How can i get peer-reviews, and how does one publish such research independently ? Anyone has experience, willing to guide me on this ?

Comments URL: https://news.ycombinator.com/item?id=40283899

Points: 4

# Comments: 4

Can LLM benchmarks evaluate React coding skills?

kshitij_libra — Sun, 05 May 2024 10:08:42 +0000

Article URL: https://Kshitij-Banerjee.github.io/2024/05/04/evaluating-llm-benchmarks-for-react/

Comments URL: https://news.ycombinator.com/item?id=40263607

Points: 1

# Comments: 0

New comment by kshitij_libra in "Ask HN: Can LLM's produce useful code?"

kshitij_libra — Tue, 30 Apr 2024 17:08:38 +0000

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 ..

New comment by kshitij_libra in "Ask HN: Can LLM's produce useful code?"

kshitij_libra — Tue, 30 Apr 2024 16:33:51 +0000

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

New comment by kshitij_libra in "Ask HN: Can LLM's produce useful code?"

kshitij_libra — Tue, 30 Apr 2024 15:59:33 +0000

> 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 ?

New comment by kshitij_libra in "Ask HN: Can LLM's produce useful code?"

kshitij_libra — Tue, 30 Apr 2024 15:55:31 +0000

100% I’d rather have specialised LLMs that can solve some hairy problems like CSS , than what we have now

Ask HN: Can LLM's produce useful code?

kshitij_libra — Tue, 30 Apr 2024 15:16:05 +0000

After using code LLMs' for a bit, I wonder whether there is significant productivity gain in using them. I found that it's 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 below.

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 of their usage

2) Any other research ideas being pursued in this field ? / what are you trying ?

Full post with details here: https://kshitij-banerjee.github.io/2024/04/30/can-llms-produce-better-code/

Comments URL: https://news.ycombinator.com/item?id=40211926

Points: 4

# Comments: 11

New comment by kshitij_libra in "Ask HN: Can Devin genuinely replace the roles of developers?"

kshitij_libra — Tue, 30 Apr 2024 15:08:10 +0000

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...

New comment by kshitij_libra in "Can LLM's produce useful code?"

kshitij_libra — Tue, 30 Apr 2024 15:02:11 +0000

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.

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 ?

Can LLM's produce useful code?

kshitij_libra — Tue, 30 Apr 2024 15:02:10 +0000

Article URL: https://Kshitij-Banerjee.github.io/2024/04/30/can-llms-produce-better-code/

Comments URL: https://news.ycombinator.com/item?id=40211754

Points: 2

# Comments: 1

Can LocalLLMs write React Code?

kshitij_libra — Sun, 21 Apr 2024 07:30:02 +0000

Article URL: https://Kshitij-Banerjee.github.io/2024/04/14/exploring-code-llms/

Comments URL: https://news.ycombinator.com/item?id=40103837

Points: 1

# Comments: 0

New comment by kshitij_libra in "[dead]"

kshitij_libra — Sun, 14 Apr 2024 10:29:53 +0000

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 ?

New comment by kshitij_libra in "More Agents Is All You Need: LLMs performance scales with the number of agents"

kshitij_libra — Sun, 07 Apr 2024 02:37:35 +0000

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

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

kshitij_libra — Sat, 30 Mar 2024 16:21:04 +0000

I keep thinking about this, and it’s a fun game.

AI, Robotics, EVs & crypto - There is a lot going on. If you got 1M$ to be invested now, in one stock/asset, and could only take it out after 10 years - where would you put it? And why ?

Hacker News: kshitij_libra

New comment by kshitij_libra in "Ask HN: What are you working on? (March 2025)"

New comment by kshitij_libra in "You might not need Redis"

New comment by kshitij_libra in "IMG_0001"

New comment by kshitij_libra in "Ask HN: Do you already see the impact of LLMs on the job prospects for dev's?"

New comment by kshitij_libra in "Ask HN: Independent Research, Review and Publication"

Ask HN: Independent Research, Review and Publication

Can LLM benchmarks evaluate React coding skills?

New comment by kshitij_libra in "Ask HN: Can LLM's produce useful code?"

New comment by kshitij_libra in "Ask HN: Can LLM's produce useful code?"

New comment by kshitij_libra in "Ask HN: Can LLM's produce useful code?"

New comment by kshitij_libra in "Ask HN: Can LLM's produce useful code?"

Ask HN: Can LLM's produce useful code?

New comment by kshitij_libra in "Ask HN: Can Devin genuinely replace the roles of developers?"

New comment by kshitij_libra in "Can LLM's produce useful code?"

Can LLM's produce useful code?

Can LocalLLMs write React Code?

New comment by kshitij_libra in "[dead]"

New comment by kshitij_libra in "More Agents Is All You Need: LLMs performance scales with the number of agents"

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

How to build – Tony Fadell [Book summary]