Sarvam’s 105B model (and its smaller 2B sibling, Sarvam-1) solved a problem that global giants like OpenAI & DeepSeek ignored: the Tokenization Tax.
In most AI models, an Indian word like Namaste takes 4-8 tokens to process, while an English word takes only 1.4 & this makes AI 4x more expensive for us.
Sarvam built a custom tokenizer from the ground up that brought Indian language fertility down to 1.4 tokens/word, matching English for the first time in history. This is how 40 people outperformed others in local efficiency :)
I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit.
My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently.
So, here goes.
@think_in_points I purchased one in Venice for 10 euros . It broke down by the time I reached my hotel walking through canals . Had to buy another one next day for 20 euros
We are proud of Prof Madhavi Latha & her team's contribution to the #ChenabBridge inaugurated by Hon'ble PM Narendra Modi🎉
The team worked on stability of slopes, design & construction of foundations, design of slope stabilisation systems incl. rock anchors to withstand hazards.