Viewing profile — devashish86

Author here. Want to share the results of my experiments with local inference. I failed to get decent output from my previous setup ( https://news.ycombinator.com/item?id=48587865 …

fair points. will take this into account in the next post.

fair point, i'll publish the methodology in the beginning next time onward. fwiw, this is my high level process. 1. i keep comprehensive notes _while_ i'm experimenting(like checkp…

Author here. Quick context the post doesn't quite spell out: The tool_choice="auto" failure on Qwen3-Next isn't a parser issue — the model reasons inside , decides, and never emits…

Building Clawrium ( https://github.com/ric03uec/clawrium ), a CLI to orchestrate a fleet of autonomous agents(like openclaw, hermes etc) on multiple physical hosts. As I started ru…

I have 2 OpenClaws running on an old Ubuntu box, and one on a PI. Every config change meant SSHing into each one, tweaking files, restarting services, checking logs. Its all fun du…

Announcement post: https://www.devashish.me/p/introducing-clawrium-an-aquarium

I'm running a few instances of OpenClaw(and Zeroclaw). I use it for a few things 1. Experimenting with local models. OpenClaw uses local inference on a DGX Spark machine. Helps me …

Sharing a recording and notes from my demo at AI Tinkerers Seattle last week. I ran 6 different models in parallel on identical coding tasks and had a judge score each output on a …

I'm a heavy cc user for writing code, reviewing documentation, brainstorming, updating jira tickets etc etc. For the past few months, I started experimenting with managing a team u…

> The problem with the "everyone" model being pitched here is that it may as well be a synonym for "nobody." Can't agree with this enough! Thanks for your inputs. A lot of it reson…

I agree that building visibility makes accountability easier. Its relatively trivial to build observability for individual services and we have achieved some version of it. The pro…

Already done! This actually works pretty well when two conditions are true 1. cost becomes an engineering-org wide pain point 2. there are a bunch of low hanging fruit (another way…

Standards enforcement like tagging, TF structure, pipelines etc is currently owned by the platform team. We also have mechanisms to figure out the cost change (approximately) with …

Context: I lead the DevOps team in a mid size engineering org (60 engineers approximately). The product is a B2B SaaS product. The organization started taking cloud costs seriously…

Esper | Multiple Positions | Seattle, US | Full Time | Visa Sponsorship We're industry’s first DevOps SaaS platform designed to provide a simple, safe and secure way for engineerin…