JBits

It demonstrates that current LLMs are completely unable to follow a simple series of logical tasks. I feel the same way about ARC-AGI 3. While it might be the winning approach today, if they need this amount of complexity to do something simple, then it shows that their ability to generalise is clearly limited. Mining ore in Minecraft shouldn't be such a challenge for LLMs and yet apparently it is!

As impressive as this is, I can't help but conclude that the need for agents to write JavaScript programs to act out their actions represents a considerable limitation in current AI reasoning.

My thoughts are without a doubt closer to code than writing. Thoughts are more often than not non-linear, so putting them into writing is challenging. Meanwhile, when I think of code—and also when I physically write code—it's always possible to leave holes and stubs to be filled in later.

I feel the same. It took a me a while to realise that I needed to click on the white tile to place a transformation. Though I'm now stuck on the second level as there aren't any tiles! The menu in the top left is very confusing.

The original 'Attention is all you need' paper also used random variables to explain the sqrt(d_k) factor. Even if the keys aren't random, it seems reasonable to treat them as random variables when calculating the 'interference'.

Does the famously damp UK climate make a difference here?

> air conditioning

The UK typically doesn't need air conditioning, so why would people spend money on it? Yes, I know this recent summer was exceptionally hot but people don't react that quickly to changes.

> decarbonizing heating

What does this mean? More renewables? If efficiency reduces energy demands then it directly results in less carbon.

> electric vehicles

Aren't people already adopting electric vehicles? Do you think that the government should introduce a scheme to persuade people to buy electric vehicles? Does the availability of charging for electric vehicles need improving?

> Efficiency is good after you have high living standards but the UK should probably focus on growth first

Efficiency means saving money. In what circumstance could efficiency be bad? The grid responds to demand, unused electricity means higher prices for consumers. One of biggest issues right now in the UK is cost of living crisis, so raising electricity prices would be universally hated. How does making the grid less efficient increase growth?

If the time taken is shortened but you don't learn anything from it, then you're still behind.

I would question the narrative that humans lack the capacity to verify the output and would instead argue the people lack the incentive to verify the output.

The response of many mathematicians to the recent dump is a good example: verifying these proofs amounts to unpaid labour for OpenAI and wastes time that could be spent doing publishable work which ultimately results in money or personal success. The slop factor also compounds the work required to verify the output considerably.

For mathematicians, programmers or anyone, if the work required to deal with slop passes the limit, it is no longer in their own self interest to use LLMs. The expectation that people will use LLMs for the betterment of humanity against their own financial interest is baffling.

How on earth does someone just randomly spend $20k? If he's not going to maintain the project, the whole thing seems completely pointless.

I'm really confused by this list: every link I click on either doesn't work or takes me to a project for Go written in Go. I haven't been able to navigate to a single Cobol project.

I agree. The idea that mathematical achievements by LLMs could involve plagiarism didn't seem common before but now the question can be asked of any new novel proof of construction generated by LLMs.

It's also notable that the Open AI proof may not even be interesting to mathematicians.

Even if people already had an idea that LLMs were training on user inputs, it's the first time it's actually caused an issue. Mathematicians, and plenty of researchers, working in ambitious or competitive field now have a very good reason to avoid LLMs.

I have to say, it's hilarious to me that solving a Millennium problem has given mathematicians a reason to doubt the mathematical abilities of LLMs.

Quite a few of the challenges revolve around asking for LLMs to complete tasks reliably and aren't about whether an instance of an LLM completing the task exists. Quite a few of the goalposts are consequently completely changed without the surrounding context, are not the same as what the HN commenter requested and hence seem disingenuous to me.

They look at each problem individually.

As the ARC AGI guidelines [1] state, 'a core design principle of ARC-AGI is that the test taker must not know what the test will be.'

[1] https://arcprize.org/policy#dataset-security

Being a superset of Python may not be necessary to be successful, but perhaps non-committally proposing it was necessary for Modular to win the funding they wanted. While lots of people indirectly run GPU kernels with PyTorch, I think the number of people wanting to write their own kernels is considerably smaller and that this niche already has established players (plenty of whom even already build on top of MLIR), making Mojo's most obvious use case difficult to sell.

I think it was there for marketing purposes and that there was little actual intention to work on it.

From the roadmap:

>Mojo may or may not evolve into a full superset of Python, and it's okay if it doesn't.

I don't think the goal of being a true Python superset ever existed.

Given that there are so many failed attempts to optimise arbitrary Python code, it was dubious from the start. Furthermore, the documentation completely ignored these challenges and made it clear that Mojo's goal was to compile to MLIR in order to write kernels for machine learning. The first example of Mojo code was a low level matrix multiplication kernel taking advantage of fancy compilation features and the documentation advertised pointers inspired by Rust's move semantics, neither of which are typically considered friendly or relevant to high level programmers.

An AI able to play Slay the Spire sounds pretty impressive!

What do you mean by agent in this context? Does it mean LLMs?

What search problem are you solving for deck building and is MCTS for combat the same as that in Go AIs?

At the time, Java ran on the web so he could easily share demos.

He used LWJGL, which probably covered a lot of his library needs.

Java has a JIT, so it's not comparable to Ruby and Perl.

Is it mainly the reactivity part of Vue that you benefit from, or are there other aspects which are important?

While perhaps this is on me for not stating my position while repeating Bill's comment, I think you are unfairly assuming bad faith.

You are wrong to state that I am motivated by fanatism or jealousy.

I have no involvement whatever with Odin and am in agreement with the parent article (though I think it's personal criticisms veer a bit too far). The creator of Odin using Odin at jangafx is not an appropriate source in my view.

It is disappointing to see that the v programming language has a Wikipedia article given it's history of being essentially fraudulent.

Perhaps it is because Malbolge is notable within the category of esolangs.

Is there any reason why they're not considering a single '?' like rust? Is it a parsing issue?

So you'd have: obj?:method(…)

But it demonstrates that LLMs struggle with basic reasoning. A criticism of LLMs is that they're imitating without a understanding of what they're doing and without a clear plan, so this inability to solve a simple logic puzzle is very relevant. If LLMs didn't struggle with reasoning problems then something like ARC-AGI wouldn't exist.

If you're happy with NumPy's API, then surely JAX is exactly what you're looking for.

You can't claim to have superior knowledge if you admit you're wrong.

> Once this happens, players will be able to switch between OpenGL rendering and Vulkan rendering

I think this means you'll be able to continue using Minecraft with OpenGL.

What would be the best way to use Vulkan 1.4 in Rust today? Using the C headers with bindgen or writing my own vk.xml generator?