mergisi

* * *

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.

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.

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.

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

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.

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

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

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

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.

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.

more options for customizable tuning would be great.

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

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.

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!

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.

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!

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

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.

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.

Thank you for the kind words! I'm glad you liked the site and offering. Let me know if you have any questions or need more information—happy to help!

I've shared a step-by-step guide on GitHub for creating a simple blog page using the OpenAI O1 model. I also explained how to deploy it. https://github.com/mergisi/openai-o1-coded-personal-blog

You can find detailed explanations about ChatGPT o1 and the tools used from scratch on GitHub. I’ve added everything you need to get started! https://github.com/mergisi/openai-o1-coded-personal-blog

I’ve added all the steps for generating a blog website using OpenAI’s O1 model. Check it out here https://github.com/mergisi/openai-o1-coded-personal-blog and let me know what you think!

I’ve been working on a blog website using OpenAI’s o1 and just added some updates https://github.com/mergisi/openai-o1-coded-personal-blog

I’ve been working on some fact-checking projects myself and developed a blog website. Check out my work here https://github.com/mergisi/openai-o1-coded-personal-blog

I've been working on a o1-preview and recently hit some limitations with OpenAI's cap. But I’ve made progress—added all the steps, details, and code on GitHub https://github.com/mergisi/openai-o1-coded-personal-blog . The result isn't bad at all; just a few more CSS tweaks to improve it. Check it out and let me know what you think! How does it compare to tools like Claude Sonnet 3.5?

Cursor can sometimes modify existing code when making changes. I’m curious if anyone else has encountered this and how you managed to work around it.

Good point! SQLite is simple and great for small projects, but its limits with data integrity and concurrency show at scale. Still, it's a more predictable choice than MongoDB, which has its own quirks. Definitely progress!

Writing SQL code is not easy, especially if you’re a non-engineer and don’t have the time or skill to do it yourself.