Hacker News: mergisi

New comment by mergisi in "Show HN: Rocky – Rust SQL engine with branches, replay, column lineage"

mergisi — Wed, 29 Apr 2026 08:15:32 +0000

* * *

New comment by mergisi in "Show HN: Pgsemantic – Point at your Postgres DB, get vector search instantly"

mergisi — Thu, 26 Mar 2026 08:04:18 +0000

The "zero-config" angle is strong here — the biggest friction with pgvector is the manual pipeline: choose an embedding model, write the chunking logic, create the index, tune the distance metric. Abstracting that into a single CLI command removes the part that stops most teams from even starting.

Question on the embedding side: are you generating embeddings at INSERT time via triggers, or is there a batch sync step? The trigger approach gives you real-time search but adds write latency. Batch sync is friendlier for high-throughput tables but means search results can lag behind.

Also curious how you handle schema evolution — if someone adds a new text column they want searchable, does pgsemantic pick that up automatically or require a re-config?

One pattern I've seen work well alongside semantic search: pairing it with natural language → SQL translation (tools like ai2sql.io do this) so users can combine structured filters with vector similarity in a single query. Something like "find invoices from Q1 similar to 'billing dispute'" where the date filter is SQL and the similarity part is pgvector. That hybrid query pattern is where most real-world use cases end up.

New comment by mergisi in "SQLite: Query Result Formatting in the CLI"

mergisi — Mon, 09 Mar 2026 11:26:01 +0000

The .mode options in SQLite's CLI are surprisingly comprehensive for what most people treat as a lightweight embedded database. Table mode and box mode in particular make ad-hoc queries readable without piping through external tools.

One underrated use case: switching between .mode json and .mode csv lets you prototype data pipelines entirely inside the SQLite shell. You can validate query logic, check edge cases in formatting, and export in the right shape without writing a single line of application code.

The challenge for newcomers is discoverability. Most people learn about .mode column and .headers on from Stack Overflow answers, then never explore further. Having the full formatting reference documented in one place helps bridge that gap — especially for people coming from tools like ai2sql.io (disclosure: I work on this) where the focus is getting the query right first, and formatting the output is a separate step they often haven't thought about yet.

New comment by mergisi in "GitHub cuts AI deals with Google, Anthropic"

mergisi — Wed, 30 Oct 2024 10:39:40 +0000

I understand your concerns, but I see a positive side to this evolution. While increased accessibility can lead to an influx of less polished code, it also brings diverse perspectives and innovations that might not have emerged otherwise. With AI, we have an opportunity to enhance productivity and assist developers in writing better code by automating routine tasks and catching errors early. If we focus on mentoring and setting strong standards, we can harness these tools to improve overall code quality rather than detract from it.

New comment by mergisi in "Computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku"

mergisi — Wed, 23 Oct 2024 18:49:04 +0000

My First Experience with Claude Computer Use - It's Mind-Blowing!

Just tested Claude's new Computer Use feature and had to share this simple but powerful test:

My Basic Prompt: "Please: 1. Search Amazon for 3 wireless earbuds: Find price Rating Brand name

2. Make a simple Excel file 'earbuds.xlsx': Put the information in a basic table Add colors to the headers Sort by price

3. Show me the results"

What blew my mind: - Claude actually looked at my screen - Moved the mouse by itself - Clicked buttons like a human - Created reports automatically

It's like having a virtual assistant that can really use your computer! No coding needed - just simple English instructions.

For those interested: https://mergisi.medium.com/8f56f683e307

New comment by mergisi in "Ask HN: Which analytics platform do you use?"

mergisi — Mon, 21 Oct 2024 09:57:44 +0000

Consider Microsoft Clarity—it's free, offers session recordings, heatmaps, and detailed insights. It's easy to integrate with Vercel, and unlike usage-based platforms, has no hidden costs. A good alternative if you want more than basic analytics.

New comment by mergisi in "Un Ministral, Des Ministraux"

mergisi — Thu, 17 Oct 2024 10:36:23 +0000

Just started experimenting with Ministral 8B! It even passed the "strawberry test"! https://x.com/mustafaergisi/status/1846861559059902777

New comment by mergisi in "Canvas is a new way to write and code with ChatGPT"

mergisi — Thu, 03 Oct 2024 21:43:05 +0000

I used OpenAI Canvas to help with the conversion. Essentially, I took the static HTML/CSS and wrote TypeScript to dynamically render blog posts.

New comment by mergisi in "Canvas is a new way to write and code with ChatGPT"

mergisi — Thu, 03 Oct 2024 21:18:18 +0000

Canvas lets you interact with and edit code/documents more fluidly. I used it to transform my HTML blog into TypeScript in no time! Super helpful for coding and experimenting. https://x.com/mustafaergisi/status/1841946224682774536

New comment by mergisi in "Ask HN: Are new AI code editors adding superficial value?"

mergisi — Mon, 30 Sep 2024 12:39:38 +0000

AI2SQL can connect to your database and assist with tasks such as query generation. It can analyze your database schema, including tables, indexes, and relationships, to provide more accurate and efficient SQL queries based on your database structure.

New comment by mergisi in "Ask HN: What to do about startup job"

mergisi — Fri, 27 Sep 2024 22:19:19 +0000

Since immigration sponsorship is crucial, it’s wise to stay while passively exploring new opportunities and networking. Focus on upskilling or working on side projects to keep yourself prepared for future moves. If the current role isn’t providing value, think about how it can still support your long-term goals.

New comment by mergisi in "Shape the Future of AI: Llama Users, We Need Your Feedback at Meta!"

mergisi — Fri, 27 Sep 2024 22:16:08 +0000

more options for customizable tuning would be great.

New comment by mergisi in "Shape the Future of AI: Llama Users, We Need Your Feedback at Meta!"

mergisi — Fri, 27 Sep 2024 14:20:19 +0000

I tested Llama 3.2 on my MacBook, and it runs impressively fast. I plan to look more deeply into its capabilities and have some specific use cases in mind for further testing. Fine-tuning could be improved, and better integration with AI stacks like RAG would be helpful. Overall, it's a solid model with great potential! https://x.com/mustafaergisi/status/1839647877498278311

New comment by mergisi in "Ask HN: What's the Alternative to Agile?"

mergisi — Mon, 23 Sep 2024 07:24:18 +0000

An alternative to Agile is Deep Work, which focuses on uninterrupted time for focused problem-solving instead of frequent meetings and updates. While Agile promotes quick iterations, Deep Work emphasizes sustained concentration, allowing teams to tackle complex tasks without distractions. It’s not a framework, but a focus-oriented approach that could complement or enhance existing workflows.

New comment by mergisi in "Ask HN: What do you use for your personal blog?"

mergisi — Sat, 21 Sep 2024 12:48:21 +0000

I recently created a blog website using OpenAI o1, and it’s been great for generating content with minimal effort. If you're looking for something self-hosted, you can check out my project on GitHub here: [https://github.com/mergisi/openai-o1-coded-personal-blog . Let me know if you have any questions or need more details!

New comment by mergisi in "Ask HN: Are you making money from LLMs? How?"

mergisi — Sat, 21 Sep 2024 12:30:02 +0000

I totally get that feeling! AI tools like ChatGPT can be great for basic code generation, but they still have limitations when it comes to complex or highly customized outputs, like your menu. That’s why tools fine-tuned for specific tasks, like AI2SQL for database queries, can be more reliable in those areas. As AI continues to evolve, I'm hopeful we’ll see improvements that bridge these gaps for more complex coding tasks like JS, CSS, and HTML.

New comment by mergisi in "Ask HN: Are you making money from LLMs? How?"

mergisi — Sat, 21 Sep 2024 12:25:16 +0000

Thanks for the feedback! Aside from SQL query generation, we're exploring ideas like automating data transformation tasks or simplifying API integrations using GPT. There’s a lot of potential for solving niche problems like these. I'd love to hear any ideas you have!

New comment by mergisi in "Ask HN: What are your use cases for o1 so far?"

mergisi — Fri, 20 Sep 2024 15:30:41 +0000

I’ve been experimenting with o1 as well, and while it hasn’t radically changed my workflows, I did use it to create a blog webpage with minimum human effort required. It helped automate much of the content creation process, reducing the need for constant oversight.

You can check out the project here: https://github.com/mergisi/openai-o1-coded-personal-blog

New comment by mergisi in "Ask HN: What reasonable person would work as a founding engineer?"

mergisi — Thu, 19 Sep 2024 13:32:54 +0000

Not everyone wants to start their own company. As a founding engineer, you can make a significant impact, gain valuable experience, and potentially reap rewards through equity—without bearing all the risks and responsibilities of being a founder.

New comment by mergisi in "Ask HN: Are you making money from LLMs? How?"

mergisi — Wed, 18 Sep 2024 21:04:30 +0000

LLM costs are indeed a significant part of our operating expenses. While I can't share exact percentages, I can say that they constitute a meaningful portion of our revenue. We continually optimize our usage and explore cost-effective strategies to manage these expenses while maintaining the quality of our service.