Hacker News: agunapal

New comment by agunapal in "We stopped AI bot spam in our GitHub repo using Git's –author flag"

agunapal — Mon, 18 May 2026 17:34:57 +0000

My first thought after reading the blog was, let me share the blog with Claude and ask it how bots can circumvent this.

imo AI bots have significantly affected OSS and we need better qualitative measures to define success

Most teams optimize the prompt. Agentic systems have more moving parts

agunapal — Wed, 13 May 2026 16:13:36 +0000

Article URL: https://www.aevyra.ai/posts/prompt-optimization-agentic-systems.html

Comments URL: https://news.ycombinator.com/item?id=48123876

Points: 3

# Comments: 0

Show HN: Verdict – model evals on your own data, not someone else's benchmark

agunapal — Thu, 07 May 2026 18:26:03 +0000

Article URL: https://github.com/aevyraai/verdict

Comments URL: https://news.ycombinator.com/item?id=48052944

Points: 2

# Comments: 0

New comment by agunapal in "A report on burnout in open source software communities (2025) [pdf]"

agunapal — Sun, 03 May 2026 04:49:02 +0000

Yes, one can easily setup agents to bump up the stars, increase pip downloads etc

New comment by agunapal in "A report on burnout in open source software communities (2025) [pdf]"

agunapal — Sat, 02 May 2026 02:55:26 +0000

I think it comes down to "Is the juice worth the squeeze"

As someone who worked for a large organization maintaining an OSS project, one issue I faced was how do you show impact? We used to have many organizations really love and use our project , but they would hardly give anything back to the project, including writing blogs where they could have shared some success stories. IMO github stars/pip downloads etc are not good metrics and these are even worser metrics in today's agentic AI world. Its so easy to fake these nowdays.

New comment by agunapal in "Granite 4.1: IBM's 8B Model Matching 32B MoE"

agunapal — Fri, 01 May 2026 10:21:45 +0000

Here is a paper from few years ago where they talk about 7x speed increase, which equates to savings.

https://arxiv.org/abs/2101.03961

New comment by agunapal in "Granite 4.1: IBM's 8B Model Matching 32B MoE"

agunapal — Fri, 01 May 2026 10:18:03 +0000

Do you mean model sharding?

New comment by agunapal in "Grok 4.3"

agunapal — Fri, 01 May 2026 10:13:59 +0000

Very competitive price for the speed and intelligence being offered!

New comment by agunapal in "Why isn't AMD's MI300X competitive?"

agunapal — Thu, 30 Apr 2026 11:41:27 +0000

Nvidia had the first movers advantage. Nvidia spent so many years perfecting CUDA to work well with PyTorch. Before ROCM, there was only CUDA. There were so many developers building their use cases on top of PyTorch+CUDA, and bringing all that feedback to PyTorch, this made CUDA battle ready and stable. AMD can get there, especially now with demand for compute, but as someone already said here, the biggest focus needs to be on PyTorch

New comment by agunapal in "Granite 4.1: IBM's 8B Model Matching 32B MoE"

agunapal — Thu, 30 Apr 2026 11:34:45 +0000

If you really think about why MoE came into existence, its to save significant cost during training, I don't think there was any concrete evidence of performance gains for comparable MoE vs dense models. Over the years, I believe all the new techniques being employed in post training have made the models better.