x.com/i/article/2002…

Sold on the "Classifier to Vector Search" architecture for NL-to-SQL. 🧠 But how are you actually implementing the routing layer? • Fine-tuned BERT/Encoder models? • A small LLM (Llama-3-8B/Groq)? • Just the semantic-router library? Curious what's winning on latency. 👇

Sold on the "Classifier to Vector Search" architecture for NL-to-SQL. 🧠 But how are you actually implementing the routing layer? • Fine-tuned BERT/Encoder models? • A small LLM (Llama-3-8B/ Groq)? • Just the semantic-router library? Curious what's winning on latency. 👇

Sold on the "Classifier to Vector Search" architecture for NL-to-SQL. 🧠 But how are you actually implementing the routing layer? • Fine-tuned BERT / Encoder models? • A small LLM (Llama-3-8B / Groq)? • Just the semantic-router library? Curious what's winning on latency. 👇

Sold on the "Classifier to Vector Search" architecture for NL-to-SQL. 🧠 But how are you actually implementing the routing layer? • Fine-tuned BERT/Encoder models? • A small LLM (Llama-3-8B / Groq)? • Just the semantic-router library? Curious what's winning on latency. 👇

Learn to code. Build something small. Ship it. Repeat 100 times. That’s the roadmap.

Unpopular opinion: In 2026, AntiGravity is just going to eat all the other AI IDEs for lunch.

Google Gemini is now my default AI for daily tasks (not coding). I also use Grok and sometimes ChatGPT. Gemini 3 Pro by Google DeepMind tends to get most tasks right on the first try, which is really convenient. Which is your daily workhorse AI?

Google Gemini is now my default AI for daily tasks (not coding). I also use Grok and sometimes ChatGPT. Gemini 3 Pro by Google DeepMind tends to get most tasks right on the first try, which is really convenient. Which is your daily workhorse AI!

Front end: Gemini 3.0 Pro Back end: Claude Opus 4.5 That’s the combo you need!

99.9999999% of READMEs are now AI written!

As a dev, which one do you build first? - frontend - backend

Gemini 3 Deep Think is getting a significant upgrade. We’ve refined Deep Think in close partnership with scientists and researchers to tackle tough, real-world challenges. And it’s pushing the frontier across the most challenging benchmarks, achieving an unprecedented 84.6% on

We made a skill for the Gemini API! github.com/google-gemini/…

Just published a new article on Medium! Implementing Server-Sent Events (SSE) with FastAPI – real-time updates made simple and elegant. Check it out medium.com/@rkamathvenkat… #FastAPI #Python #SSE #Realtime #WebDev

Just published a new article on Medium! Implementing Server-Sent Events (SSE) with FastAPI – real-time updates made simple and elegant. Check it out medium.com/@rkamathvenkat… #FastAPI #Python #SSE #Realtime #WebDev

Just published a new article on Medium! Implementing Server-Sent Events (SSE) with FastAPI – real-time updates made simple and elegant. Check it out medium.com/@rkamathvenkat… #FastAPI #Python #SSE #Realtime #WebDev