Viewing profile — theOGognf

I feel like both this comment and the parent comment highlight how RL has been going through a cycle of misunderstanding recently from another one of its popularity booms due to be…

I really enjoyed it. Very Hitchhiker’s Guide -like. It’s been a while since I’ve read something like that. Thanks for sharing

I used to follow advancements in RL pretty closely since 2016; it’s cool to see how far methodologies and algorithms have come to be able to do complex tasks completely offline. Dr…

I didn’t see this before, but I work at a non-profit, government hospital system. So increasing profits, although probably a good answer most of the time, is probably not as applic…

Along the same lines of missing good junior engineers at work, we occasionally interview stellar engineers that’ve inflated their resume a bit to get an interview, but we end up re…

Not sure about other hospital systems, but the one I work at is developing CV systems to help fill workforce gaps in places where there isn’t as many trained professionals or even …

No, that is the norm. Radiologists speak with their colleagues the most, and patients rarely

This article is pretty good. My current work is transitioning CV models in a large, local hospital system to a more unified deployment system, and much of the content aligns with c…

It’s ironic that HN threads, arguably one of the forums where the majority of users should understand a tech company and its tech, about Palantir always devolve into some weird spe…

I’ve used Diesel for a bit now but haven’t had issues wrangling the type system. Can you give an example of an issue you’ve encountered?

Is it common to see Metaflow used alongside MLflow if a team wants to track experiment data?

Along with burning tokens, how MCP servers are ran and managed is resource wasteful. Running a whole Docker container just to have some model call a single API? Want to call a smal…

That is true too

Right, this is only power usage. Factoring in labor and all that would make it more expensive for sure. However, it’s not like it’s a complex system to maintain. We use a popular i…

Some anecdotal data, but we recently estimated the cost of running a LLM at $WORK by looking at power usage over a bursty period of requests from our internal users and it was on t…

I was wondering this myself and made a tool-calling endpoint with OpenAPI to see if it worked well. Turns out it does: https://github.com/theOGognf/toi

This project is less about the personal assistant and AI part, and more about integrating a bunch of interesting Rust crates together to get something that's easily extensible. Tur…

It’s funny seeing this blog post again. This is actually a reference I used to make a poker game as a state machine last year: https://github.com/theOGognf/private_poker It made th…

This looks like an article about the recent Nature publication. Was confused at first because DreamerV3 is a couple of years old now

Hey Justin. First time coming across one of these postings. I saw a role that matched up to what I do now and applied (Sr MLE).

By hitting it sufficiently hard

They do this in subsets of aerodynamics for optimizing the tradeoff between simulation speed and fidelity in cases where there will be a lot of runs with the same geometry but diff…

Ive come to like coding in Rust a lot more than any other language Ive tried. It is really nice having a ton of tooling out of the box that helps the development experience (format…

I've been interested in making a TUI application and learning Rust for a while now. Since some friends and family started playing poker, I found it a good opportunity to make my "l…