I've had the same problem for a couple years - specifically the GPU crashing. Had a very hard time isolating the issue - seems like a mix of static + the EMI spike OP talks about (it happens most reliably when I stand up quickly from my desk chair).
My guess is that, like OP, we're both getting interference in the our DP connections, and that that interference is in our cases causing the GPUs to crash.
Haven't had a chance to try ferrite cores yet but that was going to be my first test.
other things not encapsulated in the parts list: My PC sits on the bottom shelf of a foodservice-style wire shelving rack. My motherboard's I/O shield is integrated and wasn't a perfect fit into the case.
The DP cable is, probably, in-spec. I usually buy Cable Matters or BlueRigger.
I do wonder if ferrite cores would help.
edit: The only similarity I notice in our builds is lower-end ASRock b650 motherboards.
My guess is that, in the vein of the "monitor flickering" symptom, your PC sees the DP/HDMI cable disconnect and reconnect due to the static. The reconnection wakes it up.
I don't know. Manually {dis,re}connecting the cable doesn't wake the PC up, but it's too hard to reproduce reliably to tell if having it disconnected makes a difference.
I pretty much only use o1 for more rigorous tasks (coding/math). Eg the other day I gave it the tax rates for my area and used it to explore different tax scenarios
That's true, but I'd assume the server would like to double-check that the hashes are valid (for robustness / consistency)... That's something my little experiment doesn't do, obviously.
Great writeup. To add an example, I personally use JSON for most of my work, but have found myself using XML for certain AI use cases that require annotating an original text.
For example, if I wanted an AI to help me highlight to the user where in a body of text I mentioned AI, I might have it return something like:
<text>Great writeup. To add an example, I personally use JSON for most of my work, but have found myself using XML for certain <ai-mention>AI</ai-mention> use cases that require annotating an original text with segments.</text>
SelectIQ works with clinical trial sites and their referring physicians to automate the patient referral process, massively speeding up enrollment.
Bringing new drugs to market is primarily rate limited on the speed of clinical trials, which are themselves bottlenecked by patient recruitment. 80% of clinical trials don’t meet their recruitment timeline, and being behind on recruitment can cost pharma companies millions of dollars per day.
I recently evaluated Dagster, Prefect, and Flyte for a data pipeliney workflow and ended up going with Temporal.
The shared feature between Temporal and those three is the workflow orchestration piece. All 3 can manage a dependency graph of jobs, handle retries, start from checkpoints, etc.
At a high level the big reason they’re different is Temporal is entirely focused on the orchestration piece, and the others are much more focused on the data piece, which comes out in a lot of the different features. Temporal has SDKs in most languages, and has a queuing system that allows you to run different workflows or even activities (tasks within a workflow) in different workers, manage concurrency, etc. You can write a parent workflow that orchestrates sub-workflows that could live in 5 other services. It’s just really composable and fits much more nicely into the critical path of your app.
Prefect is probably the closest of your list to temporal, in that it’s less opinionated than others about the workflows being “data oriented”, but it’s still only in python, and it deosn't have queueing. In short this means that your workflows are kinda supposed to run in one box running python somewhere. Temporal will let you define a 10 part workflow where two parts run on a python service running with a GPU, and the remaining parts are running in the same node.js process as your main server.
Dagster’s feature set is even more focused on data-workflows, as your workflows are meant to produce data “assets” which can be materialized/cached, etc.
They’re pretty much all designed for a data engineering team to manage many individual pipelines that are external from your application code, whereas temporal is designed to be a system that manages workflow complexity for code that (more often) runs in your application.
This is a pretty good way to go bankrupt when you have a real health emergency
EDIT: I doubt OP is reading this but I would highly recommend they get insurance before giving birth...sure, they won't cover your at home birth, but they will cover your hospital stay if you end up having potentially fatal complications
I didn't say faster build times weren't faster. I said people whose entire focus is on speed will speed-read the cliff notes instead of fully reading the original Shakespeare. There's a difference.
My guess is that, like OP, we're both getting interference in the our DP connections, and that that interference is in our cases causing the GPUs to crash.
Haven't had a chance to try ferrite cores yet but that was going to be my first test.
Curious what system specs you have in case we have overlap in anything that could isolate the issue. Mine: https://pcpartpicker.com/list/Xpdb8Z
reply