ripped_britches

lol I was going to say this too! I think the inverse is true: nobody wants to install a PWA

I’m all-in on agents but this is a “you’re holding it wrong” situation.

If you want to give your agents a DB for their own work as a scratchpad or something that’s great. They can not only go to town, but also analyze their own work and iterate on it.

If you are talking about a production base, agents should not be hitting it directly under any circumstances. There needs to be an API layer with defined usage patterns, rate limits, etc.

This is basically the same as saying “databases weren’t designed for interns to run live inline migrations in prod”. Yeah of course they aren’t.

At this point we should make a GitHub repo with a huge list of unsolved “dry lab” problems and spin up a harness to try and solve them all every new release.

I mean better that than false negative right? It’s obviously an unsolved problem.

This is the break right now, we will smile back on these times

Mockups for what type of work? Web or mobile UI?

How does the inference work correctly if the payloads are encrypted?

I agree that it seems most likely that things are going to rapidly improve as they have been.

But the reality is that global unemployment levels are as of yet unaffected.

This is clearly the hardest bar to meet, but it’s also the most important.

If AI fully automates 5% of global jobs (or pick your number), I think it would be fair to say that this specific definition of AGI is achieved.

As a SWE, I feel immensely augmented by AI. But you can’t yet fully deploy an AI to do a job end to end without any human involvement.

I use like ~1b input tokens per week on codex or something like that, and while it does an insane amount of work, you have to have a skilled hand guide it.

This might not be the case for long, but it’s not here yet (in that narrow definition at least).

I’m not on either side of the argument, but one popular definition is missing which is “can automate most knowledge work”.

Not that this is my definition or anything, just pointing out that this is the one people actually care about, even if the acronym doesn’t say anything about economics or social change.

Strange, I had the same thought about doing this exact exercise this weekend.

I think the overall percentage is the wrong approach here.

It’s easy to say a lot of things that are factually true or predictions that are inevitably true.

However the more salient point with Gary Marcus is the one unforgivable thing he was wrong about and continues to double down on which is that deep learning is hitting a wall.

Starting in early 2022 and going through today, there is still so much low hanging fruit with deep learning.

Today’s LLM progress is mostly being made in RL. But world models are also still so early and they’re deep learning all the way down.

It would be nice if he would just admit he was wrong.

Too funny that the subcontractor working for meta is “sama”

No surprise to have not heard anything from xAI

Traditional cloud providers got zero primary picks

Good - all of them have a horrible developer experience.

Final straw for me was trying to put GHA runners in my Azure virtual net and spent 2 weeks on it.

Looks extremely impressive! Genuine question - why are you sharing your methods openly? I am grateful for it, but just curious your motivations.

Maybe I’m not understanding but what is different than just using existing wolfram tools via an API? What is infinite about CAG?

Yep this has been my experience as well

I think local inference is great for many things - but this stance seems to conflate that you can’t have privacy with server side inference, and you can’t have nefariousness with client side inference. A device that does 100% client side inference can still phone home unless it’s disconnected from internet. Most people will want internet-connected agents right? And server side inference can be private if engineered correctly (strong zero retention guarantees, maybe even homomorphic encryption)

@dang is this allowed?

You too are going to have to change the name! Walked right into that one

You can’t legislate intelligence

Au contraire

Is that for real? Sounds like an abuse vector

Apparently it had another name before Clawdbot as well, I think BotRelay or something. It’s on pragmatic engineer

Send callers not in contact book to voicemail on ios

I’m surprised they were surprised because operating costs should be pretty much nil. What do they do, pay a few thousand app reviewers, a few hundred software engineers? Pretty sure if they had to, they could operate App Store for a few tens of millions of dollars per year.

Wow this is why I feel comfortable in a Waymo. Accidents are inevitable and some point and this handling was well-rehearsed and highly ethical. Amazing company

Maybe I haven’t dug in enough, but why is the second GET request a different trace?

Is it clicking a different result from same search?

It’s possible that the requirements here are not clear, given that the instructions don’t detail how to handle such a situation and it’s not obvious to me as a human.

with full privs

No that’s just a misconfigured container then.

Unless there is an exploit on an unpatched kernel bug, a properly configured container shouldn’t allow break out

Why is it a problem to use containers?

Very freaking impressive!

One claim in article is definitely very wrong or at least needs to be narrowed. Claude is the only closed agent harness and there are about two dozen open ones. Many models may be closed, but when people say agent they are generally referring to the harness, not the underlying model.