Profile avatar
diptanu.bsky.social
CEO @tensorlake.bsky.social Past - AI Infrastructure at Facebook, LinkedIN, Hashicorp, Netflix
60 posts 1,913 followers 111 following
Regular Contributor
Active Commenter
Posts 13 Comments 37

Structured Extraction is essential for AI engineering teams, we are now making it faster and more reliable than ever, whether you're turning PDFs, invoices, or reports into structured data. Here is a sneak peak into our Structured Extraction engine.

submitted 30 days ago • 1 comment

Python Folks - which data/workflow engine has the best developer experience for packaging code? We have looked into - Modal, Beam, Airflow, Flyte, AWS Lambda, Prefect, Dagster and Spark. Haven’t seen any approach which is fast, reliable and intuitive.

submitted 75 days ago • 6 comments

Taking a break for 10 days for the first time since December last year! January is going to be great and you will hear about @tensorlake.bsky.social more often :)

submitted 78 days ago • 0 comments

We have been using O1 or Sonnet to solve a problem to understand the upper bounds of what models are capable of, and falling back to our internal models or open source models for economy and security. Been working pretty well, is this a common workflow?

submitted 83 days ago • 0 comments

At the Hasicorp ReInvent party, no mention of Nomad and Consul 😭

submitted 88 days ago • 1 comment

Landed in Vegas for reinvent! Say hello if you are around, would love to chat :)

submitted 89 days ago • 0 comments

Turned on Apple Intelligence this morning. We are a long way from having a personal assistant on the iPhone! It wish it summarized all unread from Slack, Gmail, WhatsApp and messages and came up with a list of things I needed to respond :)

submitted 90 days ago • 1 comment

Alibaba has done an amazing job with open source models. At this point, the difference between @Alibaba_Qwen and closed vendors is just the product on top of models.

submitted 90 days ago • 1 comment

Qwen2VL 72B is just better than every other closed and open source vision model for document understanding. Like every other vision model, it's still incapable of retaining every single ground truth on dense documents.

submitted 91 days ago • 1 comment

Throwing the kitchen sink at a small problem. Whenever I work on an Applied AI problem I work with unconstrained compute to see if we can solve a business problem if money was not a constraint. If there is enough value in solving the problem, the economy of scale can kick in later.

submitted 92 days ago • 0 comments

Does NVIDIA have a 2 x H100 SKU or cloud vendors are slicing up 8 x H100 machines into 4 VMs?

submitted 92 days ago • 0 comments

Building a solid compute engine is time and capital intensive - Probably a big reason why we see execution engines use SQL as a front end. They can re-use some parts of the planner and the DSL. But then they make the trade off of pushing SQL in domains where it doesn’t make sense.

submitted 94 days ago • 1 comment

I love that DMs are open to chat with people on BSKY by default! Had some great conversations with folks today! Please DM if you are working on anything related to unstructured data, LLMs and Document Understanding!

submitted 102 days ago • 2 comments