arjun-mavonic

Joined 1 year ago

Karma

Submissions

Member since

Feb 7

An entrepreneur and a technical founder. I've worked as a full stack software engineer, devops & SRE and then a technical architect for over 12 years. I live riding motor bikes and have traveled India on it. Riding in the Himalayas for 2 years during covid was the best time of my life.

Me, Motor bike and the Mountains <3

View on Hacker News

Recent submissions

Comment · 5 months ago

Yet to try this. But from what I heard from a friend is that Gemma 4 12b calls same tool’s repeatedly. Maybe harness can be made to handle it.

Comment · 6 months ago

I knew they were burning money with those earlier limits. But thanks we had them a good price until we needed them. Now that GLM, Opencode Go, Crof AI, Synthetic.new, and many many more. They give these opensource source models. I have switched from all big subscriptions and now have moved to many small subscriptions and I am now trying see who gives best accuracy(quants), Speed (tokens/second) and Usage Limits at low price.

Comment · 6 months ago

I'll try yours as well. Thanks

Comment · 6 months ago

Have you tried the plannatator? https://github.com/backnotprop/plannotator I've been using it for few months now and I like how it let's me annotate the plan as I review and then send feedback or approve.