"OpenAI Releases Point-E, an AI For 3D Modeling"
https://news.slashdot.org/story/22/12/21/2255216/openai-releases-point-e-an-ai-for-3d-modeling
To produce a 3D object from a text prompt, we first sample an image using the text-to-image model, and then sample a 3D object conditioned on the sampled image. Both of these steps can be performed in a number of seconds, and do not require expensive optimization procedures.The first chess playing engine source code created by an AI and published?
>>Provide me with a minimal working source code of a chess engine
It's difficult for me to provide a minimal working source code for a chess engine, as the process of creating a chess engine involves a significant amount of complex programming and knowledge of computer science and chess. Additionally, the specific details of a chess engine's source code can vary depending on the design and goals of the engine. Here is a very basic example of a chess engine written in the Python programming language:
import chess
board = chess.Board()
while not board.is_game_over():
# Generate a list of all legal moves
legal_moves = list(board.legal_moves)
# Choose a random move from the list of legal moves
move = random.choice(legal_moves)
# Make the move on the board
board.push(move)
# Print the final game state
print(board)
This code creates a chess board using the chess library, and then enters a loop where it generates a list of all legal moves and chooses a random move to make on the board. The loop continues until the game is over, at which point the final game state is printed.
Keep in mind that this is a very basic example and doesn't include many of the features and capabilities that a more advanced chess engine would have. It's only intended to provide a minimal working example of a chess engine. If you're interested in creating your own chess engine, I recommend doing some research and studying the field to gain a more thorough understanding of the process and necessary techniques.ChatGPT thread on TalkChess:
https://talkchess.com/forum3/viewtopic.php?f=2&t=81097&start=20#p939245
MIT's Newest fMRI Study: 'This is Your Brain on Code'
[...]
What the group wanted to find out was whether the brain signals seen in their study when participants were examining pieces of code resembled the patterns of activation observed when neural networks analyzed the same piece of code. And the answer they arrived at was a qualified yes. "If you put a piece of code into the neural network, it produces a list of numbers that tells you, in some way, what the program is all about," Srikant says. Brain scans of people studying computer programs similarly produce a list of numbers. When a program is dominated by branching, for example, "you see a distinct pattern of brain activity," he adds, "and you see a similar pattern when the machine learning model tries to understand that same snippet."
[...]AI tells chess programmers how to use AI in chess...
> consider how stable diffusion deep generative neural networks could be used to help to evaluate chess positions
It is possible that stable diffusion deep generative neural networks (SDDGNs) could be used to help evaluate chess positions. SDDGNs are a type of neural network that is designed to be able to generate high-quality samples from a given dataset, even when the dataset is noisy or incomplete. This ability to generate samples from incomplete data could potentially be useful in the context of chess, where the position of the pieces on the board at any given time may not provide a complete picture of the game state.
By training an SDDGN on a large dataset of chess games, it might be possible to create a network that can generate hypothetical positions based on the current position of the pieces on the board. This could be useful in helping to evaluate chess positions, as it would allow the engine to consider a wider range of possible moves and outcomes, rather than just the immediate position of the pieces on the board.
However, it is worth noting that using SDDGNs in this way would likely be a very complex and challenging task. Training an SDDGN to generate high-quality samples from a chess game dataset would require a significant amount of data and computational resources, and there is no guarantee that the resulting network would be able to generate useful samples for evaluating chess positions. Furthermore, even if a trained SDDGN were able to generate useful samples, it would still be necessary to develop algorithms and heuristics for evaluating the quality of those samples and selecting the best moves based on them.ChatGPT thread on TalkChess:
https://talkchess.com/forum3/viewtopic.php?f=2&t=81097&p=938856#p938855
This blog has two major topics, AI vs. ELE, takeoff of the technological singularity vs. extinction level event. But of course there are other things going on in the memesphere, physics and meta-physics. It seems to me that the fragee of this world is going to open up, Einstein's theory of relativity and quantum-mechanics seek for an merger, the separation of spirit and matter seeks for an merger, the 3.5 dimensional mind seeks to expand. IMO we already have all puzzle pieces out there for an TOE, we just need a genius who is able to merge them into a bigger picture, or alike.
We had three waves, the agricultural revolution, the industrial revolution, the information age, and now AI based on neural networks creates new kind of content, text, images, audio, video. They write already Wikipedia articles, they outperform humans in finding mathematical algorithms, is this another breaking line, is this the fourth wave? I see currently AI split in a lot of dedicated weak AIs with specific purpose, do we have a strong AI incoming, an AGI, artificial general intelligence, which will combine all those into one big system? Interesting times.
Reflecting a bit on my recent posts in here, I am convinced that the TS (technological singularity) already did take off, but now the question is if it is stable. If we consider the current negative feedback loops caused by the use of human technology the question is now if the takeoff of the TS is able to stabilize a fragile technological environment embedded in an fragile biological environment on this planet earth. Time will tell.
Hmm...
We need matrix-multiplications for running neural networks, and neural networks find better ways for matrix-multiplications...
DeepMind's Game-Playing AI Has Beaten a 50-Year-Old Record In Computer Science
"[...]Overall, AlphaTensor beat the best existing algorithms for more than 70 different sizes of matrix," concludes the report. "It reduced the number of steps needed to multiply two nine-by-nine matrices from 511 to 498, and the number required for multiplying two 11-by-11 matrices from 919 to 896. In many other cases, AlphaTensor rediscovered the best existing algorithm.Hahaha, capitalism and Super-AI does not sum up ;)
The paper envisions life on Earth turning into a zero-sum game between humanity, with its needs to grow food and keep the lights on, and the super-advanced machine, which would try and harness all available resources to secure its reward and protect against our escalating attempts to stop it. "Losing this game would be fatal," the paper says. These possibilities, however theoretical, mean we should be progressing slowly -- if at all -- toward the goal of more powerful AI. "In theory, there's no point in racing to this. Any race would be based on a misunderstanding that we know how to control it," Cohen added in the interview. "Given our current understanding, this is not a useful thing to develop unless we do some serious work now to figure out how we would control them." [...] The report concludes by noting that "there are a host of assumptions that have to be made for this anti-social vision to make sense -- assumptions that the paper admits are almost entirely 'contestable or conceivably avoidable.'" "That this program might resemble humanity, surpass it in every meaningful way, that they will be let loose and compete with humanity for resources in a zero-sum game, are all assumptions that may never come to pass."We analyze the expected behavior of an advanced artificial agent with a learned goal planning in an unknown environment. Given a few assumptions, we argue that it will encounter a fundamental ambiguity in the data about its goal. For example, if we provide a large reward to indicate that something about the world is satisfactory to us, it may hypothesize that what satisfied us was the sending of the reward itself; no observation can refute that. Then we argue that this ambiguity will lead it to intervene in whatever protocol we set up to provide data for the agent about its goal. We discuss an analogous failure mode of approximate solutions to assistance games. Finally, we briefly review some recent approaches that may avoid this problem.