aae42

They were also really slow on heartbleed

beekeeping

i think this guy's just trying to gain future favor from the AI overlords

Disagree, I rather not subsidize that. I also don't really get why it has to be an EV, can't a self driving car just as easily be gas powered?

In my admittedly little experience running a tiny LLM service on a single 5090 for friends, I would guess a fair bit. It depends on how many tok/sec you're targeting and how much memory you're allowing be used for context (and their context). Definitely more than 1, MAYBE an order of magnitude.

Yes

I gather this is the whole point of the original article. It seems to have been pulled, so I can't confirm.

At what point do the AI companies start building their own hardware, I wonder.

Preparing them for the future when all of their work will be laid out this way to maximize productivity

A dull knife

$5 USB mic?

they'd love my little clipboard/AI project name, then

https://github.com/aae42/clippy-clippy/

anyone could run this themselves with open web UI and litellm, in fact that's the stack I've been using

i find these discussions comparing the "vision language models" to the old computer vision tech pretty interesting

since there are still strengths the computer vision has, i wonder why someone hasn't made an "über vision language service" that just exposes the old CV APIs as MCP or something, and have both systems work in conjunction to increase accuracy and understanding

I've noticed this on my org as well, people refer to "putting things in git" and 75% of the time they're referring to the source forge.

ripoff of https://www.chronophoto.app ?

it's really fun/simple so can't feel too bad

I still use it for that. Built a really nice packer based process that pulls in Chef cookbooks and applies them in zero mode. Even have an integration test of the resulting AMI in later stages using test kitchen (Chef's "killer app" imo) with the EC2 driver to spin up an instance with the AMI and run Inspec tests on it.

this is interesting to me, i know Facebook still uses Chef, are there any other FAANGs that do?

could also just do the request in javascript instead of needing a (presumably hosted) sandbox

It's an interesting post. I feel like people who are still doing Chef definitely know about cinc already.

i also disagree w/ the article, it almost always needs spaces around both en and em dashes

just like real intelligence... what's the adage?

> You catch more flies with honey than you do with vinegar

if you really got into the habit of putting your train of thought in here i was thinking you could use it for billing hours/dividing up billable hours

probably, i wonder if there shouldn't be an edited timestamp as well

Looks good. How do I share across devices?

Would I ever be able to see the source, or run whatever backend the above request requires myself? Maybe I've answered my first question and this thing is 100% client side.

I've been using https://www.usememos.com/ as of late, so the concept resonates with me. It's the first note taking app I've went all in on that seems to make time a first-class feature. Yours takes that even further by breaking it down per entry.

i know it's only been 5 hours, but the lack of comments about any Snapdragon X Elite laptop so far makes it pretty clear.... people aren't buying these things...

they're starting to come down in price a bit, i also would like to pick up a thinkpad version for < 5 bills, but they're not there yet, also i've heard very little about the linux support on them

nix

BW synchronizes all your data on each client... if you logged in before, and your server goes down, you can still log in to a recent client, it just won't be able to update

you could recover from that

Used to use next cloud, just recently switched to owncloud infinite scale

it certainly seems much more stable so far. The lack of features might be a feature itself.

i self-host TS (headscale), so maybe not mutually exclusive

Not so sure, while I like Marques, he has a 100% focus on consumerism.