![](https://lemmy.ml/pictrs/image/c023c7b0-1dbf-49ec-a76c-8e44aa429695.png)
![](https://fry.gs/pictrs/image/c6832070-8625-4688-b9e5-5d519541e092.png)
If that happens, I’ll create a preemptive PR on KilledByGoogle.
If that happens, I’ll create a preemptive PR on KilledByGoogle.
DuckDuckGo also uses Bing under the hood.
GitHub constantly becomes more bloated, clunky and privacy/license concerning AI BS. It almost feels like using 2010 TFS server with git flavor. Unfortunately, It has a huge user base and it’s hard to incentivize people to use other platforms.
It’s easier for well-established projects to host their own git infrastructure. But for new projects and solo developer, it harder to get interaction on other platforms. I think that’s why even Gitea team uses GitHub as a main location for development. Similarly, I still mirror my public repositories to GitHub for the same reasons even though I prefer using my own Gitea server.
Biggest difference is being able to execute INSTCMD commands, at least that was the main reason why I developed my own tool. Another less important differences are: older ARM support and since it’s written in Rust, it’s much more efficient in terms of resource usage. TBH, being that efficient only makes sense for very low-power devices.
Besides that, I don’t think you can go wrong with either project.
Thanks! I appreciate any kind of feedback.
I’m actively using ollama with docker to run llama2:13b model. It’s generally works fine but heavy on resources as expected.
I’m kind a interested in Mahou Shoujo ni Akogarete. It looks like a good seasonal comedy anime.
I recommend Obsidian with community plugins. Application itself isn’t open-source but your content stored as markdown files.
I personally use Traggo, but TimeTagger is also a great option: https://timetagger.app/articles/selfhost/
I just checked the manga artist’s site, he also posted the source PSD files of the chapters. Literally gigachad move.
‘Soon’ is a questionable claim from a CEO who sells AI services and GPU instances. A single faulty update caused worldwide down time recently. Now, imagine all infrastructure is written with today’s LLMs - which are sometimes hallucinate so bad, they claim ‘C’ in CRC-32C stands for ‘Cool’.
I wish we could also add a “Do not hallucinate” prompt to some CEOs.