alienbaby

`| tee inspect.sh | bash`

Isn't that a bit like shutting the stable door after the horse has bolted?

Lots of built in APIs for it to access, and meta have access to all your data

I thought I'd give muse a go after discovering openai's dots were not available in the UK yet.

So, yeah that was disappointing. No muse in the UK either.

What an incredibly annoying zoom/spin thing is going on there

Terribly

Because their prompt would have to include everything that’s unique to your game.

Well, yes. You need to unambiguously describe what you need to be built. That's not a problem this going to take 'a long time's to solve.

? so you start working on something without any idea what you will end up with ?

I will say, having built something similar for tracking 'memory' and items at home, it can quickly consume your tokens when dealing with both reading and updating, keeping stale info relevant etc.. when the amount of data starts to grow. Smaller tasks can balloon in their token cost as documents a read, updated, collated, refreshed etc..

however, I have found keeping a good solid reference to my home infrastructure, services, ci/cd setup, hosts, storage , networking etc.. really works wonders as a set of 'memories' to share across projects that I expect to be tested / deployed / acceptance tested etc.. using the home infra bits and pieces.

As well as the teeth, I understand they had issues along the lines of using preview rendering tech in unity that then was not further developed and dropped from the engine? Causing them to need to write a fair amount of render stuff themselves? .. something similar to that at least I'm sure.

build the biggest beowulf cluster you can!

Waaa waaa. It's fun, not a museum piece quality reconstruction.

chatting with your dots does not. work dots do, does.

yea that annoyed be, being in the UK :/

Great I thought. I'll go set one up!

To discover the rollout for Pro users does not currenly include the UK :/

was fun, but disappointing the projected trajectory does not match the final trajectory

Just curious, where has this term 'noul' come from for yes/no ansers?

/a bit more digging and..

A Noul performs a Bernoulli trial—an experiment with exactly two outcomes (yes or no)—but instead of picking one, it returns the calibrated probability (ranging from 0.0 to 1.0) that the statement is true.

I hate it :)

better local performance from a fine tuned model, don't need to use a cloud instance? Avoids guardrails on cloud instances? and yes, you can plug the model into your own harness?

when everyones fighting to be 'somewhere in the pile' they need some way to advertise they have made progress while not being the best.

'billions' . I think the exact estimates are classified. https://www.washingtonsun.com/technology/classified-estimate...

though this is controlled and planned, I assume. As opposed to random numbers of customers dropping dead whenever they feel like it.

can they be considered to have compressed the entirety of their training data into their weights?

Really, people don't pay for 'ad free' .. rather, they do, but what they really want is 'interruption free', which I think is why Disney+ promoting their own content as part a stream is essentially perceived as an 'ad'. I personally think it should be considerd an ad regardless of it being your own content or not. I don't care if it's someone else's , or your content, it's an advert for that content.

Hey Claude, re word this until it passes pangram as not AI written.

It doesn't matter whose problem it is, it shouldn't be there.

Rubbish. Such use cases are extremely common anywhere it can't be expected everyone has access to their own device.

That's still a terrible solution. Plenty of people don't have phones that can do that, or dont have e it with them when they do etc..

Status page is still showing all red tho

Haven't they got some kind of new fancy ai interface they can use to fix it?

My thought exactly. What a terrible background!

So we are calling the developers as sloppy now just because they use AI? It is entirely possible to use AI and still produce good code - the effort required changes, but so long as it is done by a diligent developer capable of asessing and correcting AI code, it should be fine.