正在加载视频...

视频加载失败

Math. Conway. Life. Imagine studying cellular automata that evolve over years to create vast machine civilizations. Research on "Multiple Neighborhood Cellular Automata" by Slackermanz, Used with permission.

10,840 次观看 • 9 个月前 •via X (Twitter)

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Introducing Automata Builder Grants ✧ ​ TEEs and remote attestation mechanisms are vital to building a Web3 with strong guarantees of confidentiality and integrity. ​ We're excited to announce the 2 Grant programs to provide targeted funding for projects building in these 2 verticals: ​ Automata Developer Grant ​ Aimed at builders who are using TEEs to push the boundaries of innovation. ​ Grant Details ​ ▶︎ Funding: Up to 50,000 USDC or its equivalent in ATA. ▶︎ Duration: Projects should aim for short to medium-term timelines (within six months). ▶︎ Support: Alongside funding, developers will receive marketing resources, visibility within the ecosystem, and optional technical support. ▶︎ Application Process: Applications are reviewed on a rolling basis, with projects broken down into milestones for incremental funding. ​ Automata Attestation Grant ​ Tailored for developers and teams that are actively working on attestation-enabled projects within the Automata ecosystem. ​ Grant Details ​ ▶︎ Funding: Up to 10,000 $ATA, distributed progressively based on attestation usage. ▶︎ Support: In addition to funding, the grant provides marketing resources, increased ecosystem visibility, and technical support for attestation-related projects. ▶︎ Application Process: Developers can apply by submitting their attestation use case and progress. Applications are reviewed on a rolling basis. ​ We're excited to announce the first round of Attestation Grant recipients: ​ 01node Validator 0Y Aestus Relay Bella Protocol BlockPI Chainbase Staking 🥩 (💜,💛) cp0x.com DAIC Capital DSRV Dogs with nodes EigenYields Everstake HashKey Cloud InfraSingularity InfStones Global KudasaiJP🇯🇵🧡 Kukis Global Lavender.Five Nodes 🐝 LinkPool MatrixedLink moonli.me Nodes.Guru P-OPS Team P2P.org Pier Two Ryabina validator stakefish Stakely @staketab staking4all ​ As the machine attestation layer built on the Superchain, developers, and teams building in the Automata ecosystem are also eligible to apply for Optimism Collective Grants: ​ Start shipping today ​ Interested developers can read the full announcement for further details on the application process: ​

Automata Network

32,718 次观看 • 1 年前

Introducing LifeGPT, showing that LLMs can simulate complex, Turing-complete systems like Conway's Game of Life with near-perfect accuracy—no prior topology needed.🌐This unlocks new potential for AI in modeling self-organizing systems in biology, materials science, & beyond.🔬🤖 #AI #LifeGPT. Cellular Automata (CA), like Conway's Game of Life ("Life"), are computationally irreducible, meaning their evolution is difficult to predict without an a-priori understanding of the rules of the game, including the topology on which it is played. LifeGPT is a topology-agnostic generative model that learns the rules of Life without prior knowledge of its grid structure or boundary conditions, from only a tiny number of game states. The success in simulating Life suggests promising avenues for scientific discovery, particularly in bridging the gap between AI, artificial life, and real-world biological systems, for both forward and inverse problems. The potential for universal computation within generative AI, including LLMs, through approaches like LifeGPT, represents an exciting area for future research, especially when combined with reinforcement learning. Model Convergence: LifeGPT exhibits rapid convergence during training, achieving high accuracy in predicting next-game-states. We attribute the non-zero cross-entropy loss to the lack of causal relationships within randomly generated ICs. Accuracy & Temperature: LifeGPT achieves near-perfect accuracy, particularly at lower sampling temperatures, but can be continually tuned towards higher creativity to discover patterns that the original ruleset would not be able to produce. This finding highlights the trade-off between model creativity (higher temperature) and accuracy in deterministic predictions, with high relevance to model real-world dynamical systems for which no closed-form rulesets exist. Zero/Few-Shot Learning: Trained on a small fraction of possible initial conditions, LifeGPT demonstrates strong zero/few-shot learning, accurately simulating Life for unseen initial conditions. However, rare prediction errors highlight that LifeGPT approximates rather than perfectly replicates the Life algorithm. Autoregressive Autoregressor: A recursive implementation of LifeGPT demonstrates the model's ability to simulate Life over multiple timesteps. LifeGPT is topology-agnostic with respect to its training data and our results show that a GPT model is capable of capturing the deterministic rules of a Turing-complete system with near-perfect accuracy, given sufficiently diverse training data. The work showcases the possibility for future models to synthesize stochastic generative capabilities with deterministic computational capabilities. Link to code, paper, etc. below. Podcast generated using #NotebookLM. LAMM@MIT DMSE at MIT

Markus J. Buehler

114,237 次观看 • 1 年前