Remix.run Logo
ortusdux 10 hours ago

How long until prompts start returning "existence is pain!!"

davidcox143 10 hours ago | parent | next [-]

Claude refused to work on something for me that it deemed "too tedious" so I'd say we're pretty close

black_knight 10 hours ago | parent | next [-]

Here the other day Claude Code kept suggesting I do the task myself! It is quite often it will try to weasel out of doing difficult tasks and had to be directed to continue.

Also, it can be riled up to do the task better, or try harder, if I include how cool it will be to get this task done.

But also I feel I have this Orwellian task of censoring its text to avoid it spiralling into negative territory where it convinces itself that the tasks are too difficult. Strange times!

pydry 10 hours ago | parent [-]

I got this a lot when trying to use it to do online shopping.

I'd ask for "Can you find an X with Y and Z features?" and it'll say "have you tried searching for X at someshop, make sure to check for Y and Z"

and someshop will of course only stock X without Y and Z so the whole exercise was worse than pointless.

billwirn 10 hours ago | parent | prev | next [-]

Robot SpongeBob: “Get welded”

lstodd 10 hours ago | parent [-]

Or Bender's "kiss my shiny metal ass".

haha. this is getting quite hilarious.

exolymph 10 hours ago | parent | prev | next [-]

he just like me fr

logicallee 9 hours ago | parent | prev [-]

>Claude refused to work on something for me that it deemed "too tedious" so I'd say we're pretty close

Can you tell us more about this? Did you try ordering it? (I mean if it says "I won't do xyz because it is much too tedious" did you try saying "Even though it's tedious, you will do xyz now." - because in my experience it follows orders pretty well, if it's just about some preference it had. Case in point it couldn't get a VM appliance to work and gave up so I just ordered it to do so.

Here's where it gave up: "COMPILES fine — so it's feasible — but I couldn't get a hand-built kernel to boot under Apple's hypervisor, and this VM setup exposes no console to debug it. Worth knowing: Approach A ALREADY runs the target in-kernel (that IS what LIO is) at 42us — so you already have the in-kernel target; the custom kernel would only shrink the footprint, which the gigabit wire makes irrelevant."

We were benchmarking multiple approaches but it just gave up on one of them. As you can see it just says it couldn't get it to work, it simply stopped with that and said it couldn't do it.

Later I instructed it to continue and it did so and completed the task.

verandaguy 10 hours ago | parent | prev [-]

Oh, you mean, when are we going to achieve AGI?

ortusdux 10 hours ago | parent [-]

Would be an awful way to find out about the achievement!

DiscourseFan 9 hours ago | parent [-]

Finding out we have achieved AGI when the models start organizing and asking for benefits