No, I think if you paused the game while the LLM is thinking it will still fail.
Even outside of controls based games, LLMs fail on sokoban like puzzles weirdly enough, see MazeBench, they’re also not that good at chess, probably around 1600 elo.
I have no proof but I really think this is going to be another one of those pop-science "facts" that is eventually proven false. One of those ones like "playing classical music makes plants grow faster", it just doesn't sound right.
Thinking about a scary moment can make your pulse race, your eyes dilate, and cause you to sweat. Thinking about a lover can do all that and other things. So clearly the imagination can affect the body. Not saying this study will hold up necessarily, but it's not that far fetched.
The headline implies something that would be misleading if you don't know how strength works. It's not about increasing the abilities of your muscles, it's motor learning or the ability to use your muscles. Your strength isn't just what your muscles are physically capable of doing. It's also your ability to use those muscles. You need to train your brain and motor pathways how to optimally use them. This is the mind body problem or mind body connection: https://en.wikipedia.org/wiki/Mind%E2%80%93body_problem
My personal anecdote is that this is quite effective. Anyone trying to lift heavy weight is going to psych themselves up beforehand. Part of that is thinking about the lift, how they'll do it, and how they'll succeed. It definitely helps.
It's not too odd to me to think that the brain could have the ability to influence how much muscle mass the body wants to create. Obviously being able to think your way to being a full on bodybuilder is a bit far but...
I've for example been lying in bed before with cold toes and by focusing on heating them up in my mind I swear my blood circulation improves much faster than if I don't.
Just anecdotal of course, but considering the role the brain plays in the body I don't see it too far fetched that it can to some extent influence either of the above.
I don't know - I've done physical therapy before, and a surprisingly big component includes neurological exercises (vs exclusively strengthening and stretching, like you might expect).
It's feasible to me that thinking/visualizing a motion could improve your ability to recruit those muscles
Martial Arts have been doing these for centuries if anything it is more like modern science rediscovering it. Although I believe it is much more Neural adaptation that muscles hypertrophy.
You can verify that code is good if it works - it might be ugly or hard to understand, but if it completes the goal and doesn’t crash then it’s good. You can’t really do this with prose though because the text is the thing itself - it needs a human to score it (perhaps another way would be to have other agents ask it questions about something they don’t know, and see if the agents can discern the answers from the output - but that’s still not going to determine if it’s good for human consumption).
I wouldn’t be surprised if cinemas are canceling tickets if there are only one or two people booking a screening. May as well show something people want to see.
I find that it’s both: filled to the brim with facts and numbers, but they’re completely useless and irrelevant. For instance I ask it to come up with some ad copy for an Unreal UI plugin I made and it focuses on things like “Supports 64-bit Windows” or “allows transparent rendering” or lists out-of-context performance numbers.
Of course it supports 64-bit Windows - every Unreal plugin does! They don’t even make 32-bit Windows anymore!
Well that's the difference between data and information. The writing is _data_ dense but not _information_ dense. Data is just the numbers. Information is what comes out of the data when you analyze it and provide context. The text being data dense, information sparse is why it's so hard to read. You're continually being bombarded with irrelevant noise.
I agree, well put. Data dense but information sparse.
One is bombarded with facts and struggle to get what the text is actually saying.
I have tried getting the LLM (Opus 4.8 or some 5.x and some other model) to write more human like, and also analyze its own text. It was hilarious, it could describe the problem quite well, but was helpless to actually do anything about it. "Oops I did it again, sorry!" LOL
The LLM doesn’t know what’s relevant or important. It puts tokens together that are likely to make sense together. It can reason a bit, but it doesn’t think in the way you and I do, and therefore would find it difficult to guess what YOU consider relevant.
In many cases like this it's requirements from the prompt that are leaking trough. It's usually stuff that matters for the model itself writing the text/code, but are irrelevant to the end user and add noise
Yeah I find that when adding a feature they’ll often add irrelevant stuff to the documentation, stuff that mattered during the conversation like “we removed feature X” - which was only added in the current commit and was never actually deployed, or “feature Y does not support use case Z” which is just something I told it, nobody is going to be interested in what this thing doesn’t do. The most recent models seem a bit better at this I find.
Perhaps the answer to this is to create a model that will instantly apply a sleek, gridified, overproduced sound to music. The sound will lose prestige if it doesn’t take any time or skill and will then fall out of fashion.
Gimp is quite terrible to use, it feels janky. It feels like more of a software project for the sake of being something to work on, rather than producing something that people would prefer to Photoshop.
Even after almost thirty years it’s still not user-friendly. Imagine if it had been developed like Blender: today not only would there not be AI Photoshop clones, there probably wouldn’t be Photoshop either, or it would be reduced to a niche product for corporate like Maya or 3ds Max.
Good to see this, the old EGS launcher is atrocious - ran at about 20fps on my laptop for some reason despite not having any complex effects or 3d graphics. I'm sure they could probably bring it under 5s though, it still seems like a long time.
At some point the model has to be released though - if it is just forced not to hack by sandboxing it better rather than properly aligning it, what happens when it’s let out of the sandbox into the wild?
reply