I got tired of being the copy-paste layer between AI models.

So I made them talk to each other. 🤝 Sometimes I don’t get the response I want from an LLM, so I copy-paste it into another one… and repeat. Exhausting. 😅 So I built a browser extension that connects ChatGPT,

Sourov DasAug 152

Open source LLMs are getting ridiculously capable.

Models like DeepSeek V4 Flash can already rival $200/mo frontier models on many tasks. The real bottleneck? Hardware. You need serious RAM (96–128GB+) for smooth local inference. Less than that and you’re stuck streaming from

SoleParoleAug 15