1,919 karma · joined August 12, 2018
Not only giving an API key to an agent can leak to the model because of harness issues or too broad reading rights, but also most providers don't give the ability to apply principle of least privilege to an API key.
I don't want to give an agent full R/W access to any of my services/accounts.
I've never been in a cliché-looking restaurant that is actually decent.
Meanwhile, the best restaurants I know have, at best, a flag or some kind of small drawing to give a clue about their nationality, but otherwise they look like a regular local one.
I could be mistaken but in my case I never forced anyone to use their artistic skills, it was actually more often voluntary from them.
Basically everyone was doing their part using their skills if they had some useful for the project, or just their time/sweat.
The relationship we had (still have, actually) was healthy enough so they could just tell us to piss off if they didn't want to do it. I particularly remember one such instance, because I ended up doing an ugly poster but when asked, I said it was the work of our skilled friend.
On the other hand I've been spending at least an hour per week doing sysadmin work for various groups/clubs, it's not the funniest thing in the world, particularly in the evening when I already spent the whole day doing it at work, but it's just me doing my part for the greater good!
And also it's not like I'm saying I love all the man-made posters. Or that I never been "fooled" by gen AI content.
It's just that as soon as I start seeing some gen AI tells on an image, I can't unsee them and I feel disgusted by it.
> Also, it's just nostalgia
But sometimes I also purposefully made myself some Comic Sans stuff, exaggerating them in every possible way, as a joke. And it was well received because people knew it was my own work and understood the joke.
If I made this today, it would not be seen the same. People would thought I'm trying to fight gen AI trash or I'm nostalgic of the past. While I'm just trying to make a joke by making something awful on purpose.
And I couldn't do the same joke using gen AI. The "on purpose" cannot be conveyed. People would just see gen AI trash.
Idk how to express it exactly, but I don't see how a human would have come to something like this
> I'm old enough to remember that people also complained about WordArt and Clipart and too many fonts etc.
- those made by someone skilled/savvy (not necessarily a professional)
- those made by someone without skills/knowledge
But still, they were nice because you knew someone took the time to create them to promote an event and share the important information about it, and each person was producing their own awful posters.
Now with gen AI we have something filled with trash, everything looks the same, the important information is hard to find...
Sure, the variations offered in the article are a bit better and more opinionated, but they still reek AI conformity and I feel sick looking at them.
> a bit too minimalistic for my liking
You have to scroll while everything could fit in a single screen.
I don't know how to express it but I feel exhausted trying to consume the content.
There was a trend of non-diabetic people wearing huge glucose monitoring patches on their arms
I don't see how an earlobe cuff would be a deterrent for non-athletes with the right marketing
And marketing it's all the rage since those people don't need those gadgets in the first place
> people whose knowledge of esoteric patterns and language features was their whole identity
The worst were the ones acting as gatekeepers during hiring process. You could have built S3 and they'd still look down on you because you didn't knew about some weird feature in Java.
I bought some complete series in DVD in the past but, even putting aside the inconvenience of having to manage discs in the player, there's the quality issue.
I got my 1080p copies on the high seas and that's just a whole different experience.
I wanted to check if the 5 customers for which I already did a change on their Cloudflare settings today where on the list, but can't do.
> for home lab testing
> just giving the LLM the ssh keys and having at it. It’s pretty good.
Whereas, it you let the AI go free on a server, you mostly have no idea what it did and where, so it's quite hard to audit and even harder to try and fix things.
So, unless relying on a declarative paradigm like NixOS does, I'm not ready to give AI the keys to my castles
> So no fail over/redundancy? I think at minimum it should be two machines, so one can break.
It's clear this product is intended for personal use.
I guess you have a couch in your home. This couch can seat friends/family. Yet you don't have a spare one?
Sometimes it means "rented virtual resources", sometimes it means "stack of intertwined services", sometimes it means "SaaS", sometimes it means "alternatives to SaaS"...
Here it seems to be the latter.
Particularly this one: https://lafibre.info/images/ovh/202202_incendie_ovh_strasbou...
Only SBG1 was built from containers, it partially burnt due to its proximity to SBG2, but its SBG2, which was not built from containers, that burnt down.
> For anyone else wondering
> Oh and their "data centers" are just shipping containers that are prone to the occasional fire.
AFAIK there have been ONE instance of a DC taking fire, and it wasn't built from containers.
https://lafibre.info/ovh-datacenter/incendie-sur-un-site-ovh...
> But digging to invent a reason to hate it also doesn't seem necessary.
But I don't see how they both fit together honestly.
The pros of eInk:
- low energy usage -> don't matter, current GPS units have +30 hours of battery life already
- low eye strain -> don't matter, you don't look at the screen for hours at a time
- visibility -> don't matter, current GPS units adapt to ambient light
- angle visibility -> don't matter, the screen is right in front of you
The cons of eInk:
- refresh rate -> yeah, I don't want the map display to be laggy
- visibility in the dark -> tunnels, tree cover... I don't want to my GPS to be invisible
- lack of color -> colors provide lots of information on the map display
Before AI, the only way I could get in the flow was by isolating myself from everything to avoid direct distractions (phone, emails, IM...) or indirect (having something else on my mind). It was something I was able to achieve only a few times a year. It did felt incredible. As soon I was getting stuck on something tedious, I had to resort to a web search and it broke the flow.
With AI, I can achieve this state every weekend for personal projects, and every day I'm WFH or when I'm alone in my corner of the office. I start with a list of goals/tasks, put X agents at work (I prefer working on multiple projects in parallel, with only one task per project) and while they're doing their stuff, I'm thinking about the next steps, filling the backlog, catching issues needing rework... I don't get stuck: either the agent we'll offer a workaround, or I'll push it in the backlog. Most often, the solution comes to me while I'm not in front of my computer. I can focus on the big picture, the actual problems that I'm trying to solve. Yesterday I did exactly this: started at 8am, leaving my desk just to fill my water bottle or empty my bladder... and it's only because a friend came to my place at 8pm that I stopped. I thought I was at it for only two hours...
I hate how this comment can make me look as an AI preacher; but I'm not trying to convince anyone to stop doing anything they're doing because I found the ultimate solution. No. I'm just describing how I'm enjoying _doing stuff_ on the computer more than I ever did in the ~30 years I've been doing it.
I feel bad for him as a human, but as a cycling fan I'm glad that we'll have an interesting WC in Canada
Because it doesn't make sense: you don't make a website in English, with prices in USD... while expecting users to have an AZERTY keyboard.
We even had a meme and tshirts about it: https://wiki.nofrag.com/Jte_niaue_q_lq_Kqlqsh