I'm a Melbourne-based software dev with 8 years of experience. I've worked all over the stack: on backend, frontend, DevOps and scientific computing. I'm looking to work with an organised, productive team to ship great software. I love coding and getting things done. Happy to work remote with US-based teams.
I might be wrong about this but doesn't ollama do some work to ensure the model runs efficiently given your hardware? Like choosing between how much gpu memory to consume so you don't oom. Does llama.cpp do that for you with zero config?
I would even say that Ollama is a step back. For example llama.cpp supports vulkan, which is a huge gamechanger for consumer grade hardware. Ollama does not support vulkan, eventhough it's probably fairly easy to do so.
If you care about running efficiently on your hardware, then llama.cpp is they way to go, not ollama.
I'm a Melbourne-based software dev with 8 years of experience. I've worked all over the stack: on backend, frontend, DevOps and scientific computing. I'm looking to work with an organised, productive team to ship great software. I love coding and getting things done. Happy to work remote with US-based teams.
I've been using this for the last few weeks and it's been a lot of fun, both for work and just screwing around.
Curious if there are any other tiny jobs or workflows people have been using LLMs for (how do I do this bash command, check my diff, generate a commit message, please explain clipboard text) that I could add in
+1 you beat me to the punch! I think its helpful to start with simple RL and ignore the "deep" part to get the basics. The first several lectures in this series do that well. It helped me build a simple "cat and mouse" RL simulation https://github.com/gtoubassi/SimpleReinforcementLearning and ultimately a reproduction of the DQN atari game playing agent: https://github.com/gtoubassi/dqn-atari.
We provide free, online legal assistance to people who can’t access it otherwise (in Victoria). Anika provides this help to the community through an online platform, which is powered by law students seeking practical legal experience through paid university programs. Currently our sole focus is supporting people to access safe, secure and affordable homes, by helping renters:
- Get their landlords to repair their homes
- Get their bonds back after moving home
- Negotiate a payment plan with their landlords and avoid eviction
We plan to expand our service offerings over time.
We're hiring our first full-time software developer to lead the development and implementation of the our tech strategy with a high degree of autonomy, with the aim of developing towards becoming our CTO. This will include responsibility for our public website, case management system, client intake form and reporting. All of this infrastructure is in-house, custom built software which we will be continuing to maintain and extend.
why does employer not say "dear whoever, this employee is clearly an idiot, and whatever they say on their private twitter does not represent our views"
> why does employer not say "dear whoever, this employee is clearly an idiot, and whatever they say on their private twitter does not represent our views"
Because:
1. It wasn't private, it was public and tagged the subject of the abuse directly.
2. "This employee" was on company time and actively representing the company at the time.
It doesn't matter what role you are, you are always at risk of getting fired if you embarrass your employer.
https://opentheory.net/2023/05/autism-as-a-disorder-of-dimen...
I'm just a casual reader I can't vouch for the veracity of the content, but I found it very interesting