Stew
LightNews LightNews
banner
yngstew.bsky.social
Stew
@yngstew.bsky.social
16 followers 140 following 7 posts
Tea Enjoyer | Software Engineer | Streamer
twitch.tv/yngstew
Posts Replies Media Videos
Reposted by Stew
stepheng29.bsky.social
AWS just released a new Multi-Agent AI framework
It lets you manage multiple AI agents, dynamically route LLM queries, maintain context across AI Agents and can be deployed locally on your computer.
100% opensource.
November 19, 2024 at 3:29 PM
yngstew.bsky.social
Very cool new OAI specification called Overlay I just came across. Ideal for defining extra values for different languages or configurations

github.com/OAI/Overlay-...
#OpenAPI #API #programming
GitHub - OAI/Overlay-Specification: The OAI Overlay Specification
The OAI Overlay Specification. Contribute to OAI/Overlay-Specification development by creating an account on GitHub.
github.com
November 19, 2024 at 11:38 AM
yngstew.bsky.social
Top VSCode Extensions 👨‍💻
1. Codesnap - Cool screenshots of code
2. Material Icon Theme - Its in the name and its great!
3. Tabnine - AI for basic code completion
4. Trailing Spaces - Great for my OCD over hidden spacing...
5. Markdown Viewer - Great for those READMEs you spend a lot of time writing
November 17, 2024 at 5:14 PM
yngstew.bsky.social
How much do you think those Lofi Work / Hip Hop Beats / Study blah blah blah youtube channels make? Could be an idea to have an AI Music generator create songs that feed directly into a playlist for these channels to then constantly live stream...

www.digitalocean.com/resources/ar...
10 AI Music Generators for Creators in 2024 | DigitalOcean
Delve into 10 AI music generators for creators for innovative multi-media business applications
www.digitalocean.com
November 17, 2024 at 4:59 PM
yngstew.bsky.social
Been trying this recently with other models but running into RAM issues (only 18GB available on my pc). Is there cheap options to rent servers online?
simon.fedi.simonwillison.net.ap.brid.gy Simon Willison @simon.fedi.simonwillison.net.ap.brid.gy · Nov 13
Thanks to the combo of Ollama and the llm-ollama plugin you can now run Meta's Llama 3.2 Vision image model (7.9GB) on a Mac and use it to run prompts against images https://simonwillison.net/2024/Nov/13/ollama-llama-vision/
If you have Ollama installed you can fetch the 11B model (7.9 GB) like this: ollama pull llama3.2-vision Or the larger 90B model (55GB) like this: ollama pull llama3.2-vision:90b I was delighted to learn that Sukhbinder Singh had already contributed support for LLM attachments to Sergey Alexandrov's llm-ollama plugin, which means the following works once you've pulled the models: llm install --upgrade llm-ollama llm -m llama3.2-vision:latest 'describe' \ -a https://static.simonwillison.net/static/2024/pelican.jpg A photograph of a California Brown Pelican in a harbor $ llm -m llama3.2-vision:latest 'describe' \ -a https://static.simonwillison.net/static/2024/pelican.jpg This image features a brown pelican standing on rocks, facing the camera and positioned to the left of center. The bird's long beak is a light brown color with a darker tip, while its white neck is adorned with gray feathers that continue down to its body. Its legs are also gray. In the background, out-of-focus boats and water are visible, providing context for the pelican's environment.
November 17, 2024 at 4:52 PM
yngstew.bsky.social
Any m.2 recommendations? 2TB 5000+ mb/s
November 17, 2024 at 1:05 PM
yngstew.bsky.social
Do monolith applications still have a place outside of building rockets? I feel like everything is a microservice now and maybe there is good reason for this.

Cool article by Romin Irani medium.com/romin-irani/...
Monolith v/s Microservices debate
There is a lot of discussion going on in the Monolith v/s Microservices world. Most of my early career was spent building monoliths and of…
medium.com
November 17, 2024 at 1:04 PM