Hacker News: manishsharan

New comment by manishsharan in "How will OpenAI compete?"

manishsharan — Thu, 26 Feb 2026 15:41:17 +0000

>> Apple has offered products with little value over competitors

My Pixel dropped connections unexpectedly. The battery would barely last till end of day.

Apple hardware is simply better value for the money

New comment by manishsharan in "Writing code is cheap now"

manishsharan — Tue, 24 Feb 2026 04:33:54 +0000

maybe writing code is cheap . But writing unit tests that actually test stuff that matters is suddenly so much more important and expensive.

New comment by manishsharan in "Breaking the spell of vibe coding"

manishsharan — Sun, 15 Feb 2026 15:57:07 +0000

Humans are accountable to each other. Humans can be shamed in a code review and reprimanded and threatened with consequences for sloppy work. Most, humans once reprimanded , will not make the same kind of mistake twice.

New comment by manishsharan in "AI is killing B2B SaaS"

manishsharan — Wed, 04 Feb 2026 20:23:58 +0000

I used to be a big advocate for Salesforce in my organization. And it was really great .. allowing us to deliver new functionality without the usual IT procurement bureaucracy.

Now with cloud maturity and Vibe coders who will get better and cheaper, I think it's possible to replace all the features we use on Salesforce at a fraction of the cost of our Salesforce licensing cost.

New comment by manishsharan in "AliSQL: Alibaba's open-source MySQL with vector and DuckDB engines"

manishsharan — Wed, 04 Feb 2026 15:09:24 +0000

FoundationDB Record layer doesn't get much attention here but I have found that all my use cases are satisfied by it.

And I get the benefit of resiliency and DR for free.

If you are a developing for My SQL and you are using Java/kotlin/closure/scala consider this as well.

New comment by manishsharan in "ChatGPT Containers can now run bash, pip/npm install packages and download files"

manishsharan — Tue, 27 Jan 2026 01:34:52 +0000

If I may ask, does the code produced by LLM follow best practices or patterns? What mental model do you use to understand or comprehend your codebase?

Please know that I am asking as I am curious and do not intend to be disrespectful.

New comment by manishsharan in "Show HN: Mastra 1.0, open-source JavaScript agent framework from the Gatsby devs"

manishsharan — Wed, 21 Jan 2026 04:46:46 +0000

Spring AI is fantastic for Java shops. I am assuming Typescript devs will enjoy Mastra just as much .

New comment by manishsharan in "Vibe Coding Killed Cursor"

manishsharan — Fri, 02 Jan 2026 17:11:16 +0000

Gemini's large context window is incredible. I concatenate the my entire repo and repos of supporting libraries and then ask it questions.

My last use case was like this : I had a old codebase code that was using bakbone.js for ui with jquery and a bunch of old js with little documentation to generat UI for a clojure web application.

Gemini was able to unravel this hairball of code and guiding me step by step to htmx. I am not using AI studio; I am using Gemini subscription.

Since I manually patch the code, its like pair programming with an incredibly patient and smart programmer.

For the record, I am too old for vibe coding .. I like to maintain total control over my code and all the abstractions and logic.

New comment by manishsharan in "The future of Terraform CDK"

manishsharan — Thu, 11 Dec 2025 13:36:12 +0000

I had Gemini ingest our huge aws cloudformation repo . I had it describe each infrastructure component and how it related to others and creation hierarchy and IAM.

I got a nice and comprehensive infrastructure requirement document out of this.

Now I am using it to create Terraform repo , deploying it via OpenTofu and comparing it to my existing AWS cloud formation . This part is still a WIP .

New comment by manishsharan in "Has the cost of building software dropped 90%?"

manishsharan — Tue, 09 Dec 2025 15:18:42 +0000

Yes the cost of building software dropped by 90%.

However, the cost of software maintenance went up by 1000% . Lets hope you don't need to ever add a new business rule or user interface to your vibe coded software.

New comment by manishsharan in "How AI is transforming work at Anthropic"

manishsharan — Wed, 03 Dec 2025 02:49:39 +0000

I am curious : could GenAI have written the paper "Attention is all you need"? We were trapped in CNN RNN architectures for a while : could genAi have arrived at a better architecture ?

New comment by manishsharan in "India orders smartphone makers to preload state-owned cyber safety app"

manishsharan — Tue, 02 Dec 2025 13:50:01 +0000

BS. I grew up in Delhi. We used to have a large open space where I and neighborhood kids used to play cricket . Eventually the whole area converted to slums with people from Bangladesh. They took over the whole area. I was too young to care about ethnicity but the loss of my cricket field still bothers me. My neighbor was a bank manager and he once said that the government politicians forced him to give "loans" to Bangladeshi people , with no documents and only their thumbprint,before elections to those people to ensure victory of the ruling party.

New comment by manishsharan in "You should write an agent"

manishsharan — Thu, 06 Nov 2025 21:45:22 +0000

When I ask for Patterns, I am seeking help for recurring problems that I have encountered. Context management .. small llms ( ones with small context size) break and get confused and forget work they have done or the original goal.

New comment by manishsharan in "You should write an agent"

manishsharan — Thu, 06 Nov 2025 21:37:26 +0000

How.. please don't say use langxxx library

I am looking for a language or library agnostic pattern like we have MVC etc. for web applications. Or Gang of Four patterns but for building agents.

New comment by manishsharan in "Cloudflare tells U.S. govt that foreign site blocking efforts are trade barriers"

manishsharan — Thu, 06 Nov 2025 20:50:49 +0000

Fine .. say your country has a several years of drought and bad harvest. What happens then ? Do you trade then ?

Or .. lets say due to weather, your farmers can not grow enough oranges or some fruit which drives up local prices. Should only the richest people in your country get to eat fruits ?

Or you discover lithium deposits that your national industry can not use . Should you let that just sit there knowing it could make your province prosperous if traded.

New comment by manishsharan in "Ask HN: Who uses open LLMs and coding assistants locally? Share setup and laptop"

manishsharan — Fri, 31 Oct 2025 15:59:32 +0000

I am here to hear from folks running LLM on Framework desktop (128GB). Is it usable for agentic coding ?

New comment by manishsharan in "Production RAG: what I learned from processing 5M+ documents"

manishsharan — Mon, 20 Oct 2025 17:04:02 +0000

>> Have you measured your latency, and how sensitive are you to it?

Not sensitive to latency at all. My users would rather have well researched answers than poor answers.

Also, I use batch mode APIs for chunking .. it is so much cheaper.

New comment by manishsharan in "Production RAG: what I learned from processing 5M+ documents"

manishsharan — Mon, 20 Oct 2025 16:30:03 +0000

Thanks for sharing. TIL about rerankers.

Chunking strategy is a big issue. I found acceptable results by shoving large texts to to gemini flash and have it summarize and extract chunks instead of whatever text splitter I tried. I use the method published by Anthropic https://www.anthropic.com/engineering/contextual-retrieval i.e. include full summary along with chunks for each embedding.

I also created a tool to enable the LLM to do vector search on its own .

I do not use Langchain or python.. I use Clojure+ LLMs' REST APIs.

New comment by manishsharan in "AWS multiple services outage in us-east-1"

manishsharan — Mon, 20 Oct 2025 15:10:46 +0000

You mean multi-cloud strategy ! You wanna know how you got here ?

See the sales team from Google flew out an executive to NBA Finals, Azure Sales team flew out another executive to NFL superBowl and the AWS team flew out yet another executive to Wimbledon finals. And thats how you end up with multi-cloud strategy.

New comment by manishsharan in "NIST's DeepSeek "evaluation" is a hit piece"

manishsharan — Sun, 05 Oct 2025 19:13:17 +0000

>> The CCP literally revoked the visas of key DeepSeek engineers. That's all we need to know.

I don't follow. Why would DeepSeek engineers need visa from CCP?