Krishna

@krishnadotdev

Founding Engineer at AiStrike, AI Agents, distributed systems, real-time pipelines, building whatever it takes to make things actually work.

Pinned
Krishna
@krishnadotdev
Feb 14
Thanks for the shoutout in the weekly update ! Excited to see my contribution live in production. More contributions on the way! @geminicli
Srinath Padmanabhan
@SriThreePO
Feb 12
Here is Gemini CLI’s February 2nd weekly update for v0.28.0 - ⚙️ Extension Settings: Gemini CLI extensions now support extension settings, allowing users to be prompted on installation to set API keys, base URLs, passwords, etc. - 🎨 Custom Themes for Extensions: Extensions can
4
Krishna
@krishnadotdev
Nov 10
Built a content factory with Claude Code that runs my Hinglish tech channel "Senior Bhai" Claude writes the script, a second Claude pass critiques it → AI voice → rendered with code → I approve on Telegram → posts to Instagram + YouTube Shorts from the cloud. Laptop can be off 😄 instagram.com/your.senior.bh… youtube.com/@YourSeniorBhai
Krishna
@krishnadotdev
Nov 6
@Apple can you please fix this ux please
Krishna
@krishnadotdev
Oct 27
Are you looking at code generated by Claude before merging nowadays?
Krishna
@krishnadotdev
Apr 5
The bigger your LLM context window, the more your KV cache bloats and that means more GPU memory, more cost, more pain. this is one of the dirtiest bottlenecks in running LLMs at scale. you want long context? pay up. Google just dropped turboquant. turboquant compresses your KV
research.google
TurboQuant: Redefining AI efficiency with extreme compression

Krishna’s posts