Location: San Jose, CA & St Paul, MN
  Remote: Preferred
  Willing to relocate: No
  Technologies: Python, Bash, Java, C++, C, JavaScript, React, Flask & Quart, FastAPI, PyTest, WordPress, Django, backend systems, Docker, Ansible, Linux, Figma, Prometheus, NGINX, MariaDB, Postgres, MQTT, AWS, Azure, Google Cloud, Supabase, Digital Ocean, Calculus, Vector Calculus, Linear Algebra, Discrete Math & Combinatorics
  Résumé/CV: https://www.linkedin.com/in/mathisentc/ (contact for PDF)
  Email: mathisentrevor at gmail dot com

A senior operations leader pivoting to software development. More than 12 years of expertise in large-scale operations management and problem-solving. Demonstrated expertise in thorough technical root cause analysis across complex cloud, network, and full-stack software infrastructures, halving major incidents in a $2B+ platform. Successfully led cross-functional teams in implementing system improvements and DevOps practices. Now combining proven operational leadership with newly acquired software engineering knowledge. A proven team player and force multiplier in every former role; showing the ability to learn, apply, and teach.

I find it's directly proportional to the inputs you give it. So either you need to break down the requests into smaller boxes, or use a tool like Cursor or my preferred, Aider. They both automatically bring in more context about your codebase, such as Aider bringing in your whole git repo map, to help it integrate better.

my biggest problem in coding is when I'm looking at things spanning 10 directories and 100 files with totally useless name like controller/viewer.js, viewer/controller.js, viewercontrols.js, etc and try to find where, 15 function calls ago and 80 statements ago some bug occurred. I was hoping that AI could help untangle these messes.

It has been paused based on normal steps in bankruptcy proceedings[0].

> A court hearing is typically held after a bankruptcy auction to finalize the winning bids and sales, and to hear any objections, so the process in Jones's case hasn't strayed far from the usual — yet.

[0] https://www.cbc.ca/news/world/onion-infowars-court-1.7385221

Also try and cut out the name calling, especially when you're incorrect.

When it comes to trusting the fake news outlet CBC or Alex Jones, I'd go with Jones on this one: https://x.com/glennbeck/status/1857529776866574769

Trusting Alex Jones is a bold strategy. And not one for anyone who has any media literacy, but you do you!

media literacy is another propaganda term

Damn, got me with the "understanding and being critical of the media you watch is how they get you".

Are you ok over there? It sounds like you might need some help...

I'm in a University course related to AI testing and quality assurance. This is something I'll definitely bring up and see how it can be used.

With OpenAI comparability, hoping it supports OpenRouter out of the box, which means it supports Anthropic and Google too, along with a host of open models hosted elsewhere.

Fantastic to hear! Opik should work with OpenRouter out of the box, particularly if you are using the OpenAI Python client to interface with OpenRouter. Opik's integration with OpenAI is implemented via their Python library, and so it is agnostic with respect to actual backend serving the model.

Your course sounds interesting! If you're doing any research around testing and evaluation, particularly regarding applied LLM applications, we have several researchers and engineers on our team who I'm sure would be happy to connect (myself included).

Is the course focused on LLMs used to generate text or does it also talk about other kinds of testing like search, images, etc?

Sunnyvale and Mountainview both score lower

Your choice

If you've built a thread in OpenAI everything is sent each time

I get “memory updated”. It seems like it has some backend DB of sorts.

Memory is the personalization feature that learns about you.

Ah cool

I'm starting my job search for graduation next year and have found, but not used, Huntr.com

I'm not an expert, but I believe it is the act of the model itself being used to align itself with the intended outputs[0]

[0] https://arxiv.org/abs/2402.05699

Could I ask a dumb question, what does it look like when a model isn't aligned with its intended output? Does the text look off-center?

Alignment really just means how close do the model outputs align with human preferences or some other criteria.

At a glance, this looks like a model pretrained to perform prompt-engineering. It should automatically use Chain-of-Thought in its responses in order to improve it's programming abilities, and, therefore be better aligned with users expectations.

It also has reflection. So they include code to execute the model output and return the response to the model for feedback.

Ah nice thanks for explaining!

That's not the most helpful of explanations =/