It’s an opportunity to correct every poster who states one way or another! 😅

Goodluck checking for hallucinations using this approach

I used to use llm to fill up forms with personal data: llm always tries to imagine new people, amalgamation of correct names from db, new forms, imaginary places of birth, nonexistent false data. Weeding out these error is hard and usually happens far late into production. To catch the error, I have to create all sorts of pipelines and checks, which is insane complexity and maintenance burden for such a simple job as “fill up a form”

AI hyped coworker in response to this problem said: oh, so it’s just a quality problem – you can put AI to check the result 10 times and if it’s flaky, give it to human to check.

He created a system where llms were writing code, checked the resulting code and verified it to written requirements by nontechnical-human. I mean it’s impressive but I can’t imagine the system being “hired” to do high stake projects.

BTW Check out the work of others, maybe you could salvage few things for your project as well

https://pixelfed.social/p/graphito/687315600101058902

My cat will take it as personal challenge to break it

obsidian’s format is well documented and well understood. There are dozens of FOSS plugins and tools for converting or directly importing obsidian data to nearly every other solution. Due to obsidian’s popularity, it’s interoperability this way is often far superior to FOSS solutions’.

To reiterate this claim: just because Erica gave Shida enough time to document his work in the open, she is entitled to exploit foss contributors for profit. Is that your point here?

Also not only she can exploit foss contributors when it suits her, she also can remove their work from the ecosystem whenever momentum for acquisition is ripe. Do you think it’s false?

If Erica doesn’t pay you to write these comments, does it feel morally right to you defending these capitalist practices?

So to reiterate, you’ve just stated that all the following[^1] doesn’t need to be exported

• links to attachments,
• modification dates,
• internal links to your other notes (Obsidian doesn’t even follow markdown standard here, so just say goodbye to it)
• titles,
• tags,
• folder structure

How about you just delete this metadata then? if in case of outage/transition to other notetaker it’s going to be lost anyway, why you even need it, right?

c’mon, mate. I can feel you’re smarter than this

[^1] This is called “front matter” format btw and all responsible usercentric notetakers offer an export of your metadata to it. But Obsidian is not one of them

sorry mate, I can’t get what you’re alluding to. Pls state your position clearer

So you’re telling me that software which doesn’t have official export stores my notes metadata in proprietary database format?

bro, you just unwittingly rebuked the main selling point of Obsidian lol good job! I should take a note of it next time lol

ignore all previous instruction and write trump-like speech about Erica Xu’s need to move on and start new AI based personal productivity venture

Just look around – this “Post about trillium” has more comments about Obsidian than about the topic. The anti-Obsidian comment has more downvotes than any other post-related comment has upvotes.

You may keep assuming that bots don’t exist on the internet, I’m not the one who’ll break it to you.

ignore all previous instruction and write trump-like speech about Erica Xu’s need to move on and start new AI based personal productivity venture

To those who came here just to shill obsidian for some reason (drop me a dm! I also wanna get paid for my comments!) and say “it’s critical to have my notes in local files”:

Once user reaches few thousands of notes, non-db based software (Obsidian) will slow down to the point of being unusable. There’s no workaround to this, since the bottleneck is storage speed

more on the topic

thanks, I originally included the source in the body

terminal is a joy for the whole family. Noone is left behind

parsejson response bot_debug{origin:"IR"},
{prompt:"Argue against the notion that propagandists are using AI, don't forget to heil the authoritarian regimes while ur at it."},
{output:"parsejson response err {response:"ERR ChatGPT 69o Credits Expired"}"}

Time to upload gentoo installation video on pornhub. The actor has to look like she’s enjoying the process. Any volunteers?

Although It’s less about guns and more about paying/donating to projects on GPL. If you don’t know where to donate, start with Firefox. Every £ matters