Empirical Computation: Prompting versus Programming

📰 ArXiv cs.AI

Learn how Large Language Models can solve computational problems without algorithms, using prompting instead of programming, and why this matters for the future of computation

advanced Published 7 Jul 2026
Action Steps
  1. Explore the concept of empirical computation using LLMs
  2. Compare the differences between prompting and programming approaches
  3. Evaluate the potential benefits of using LLMs for solving computational problems without algorithms
  4. Investigate the challenges and limitations of empirical computation
  5. Apply prompting techniques to a specific computational problem to test its effectiveness
Who Needs to Know This

Researchers and developers working with LLMs and interested in exploring alternative approaches to problem-solving can benefit from this concept, as it challenges traditional programming paradigms and offers new possibilities for efficient computation

Key Insight

💡 Large Language Models can solve computational problems without algorithms, using prompting instead of programming, which can lead to more efficient and flexible computation

Share This
🤖 LLMs can solve computational problems without algorithms! 🚀 Prompting vs programming: a new vision for computation #LLMs #EmpiricalComputation

Key Takeaways

Learn how Large Language Models can solve computational problems without algorithms, using prompting instead of programming, and why this matters for the future of computation

Full Article

Title: Empirical Computation: Prompting versus Programming

Abstract:
arXiv:2503.10954v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents can solve *any* computational problem *without* an algorithm in a runtime *independent* of the computational complexity of that problem. Instead of specifying precisely how to solve problem instance using *programming*, we ask an LLM to solve the problem instance using *prompting*. Outputs are sampled from a distribution rather than generated procedurally. In this vision paper, we explore the challenges a
Read full paper → ← Back to Reads

Related Videos

5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
ChatGPT for Beginners
ChatGPT for Beginners
Kevin Stratvert
ChatGPT Tutorial for Beginners: How to Actually Get Work Done with AI
ChatGPT Tutorial for Beginners: How to Actually Get Work Done with AI
Kevin Stratvert
Running a Streamlit App from Google Colab - Serve an LLM app in Colab
Running a Streamlit App from Google Colab - Serve an LLM app in Colab
Abonia Sojasingarayar
Run Ollama with Langchain Locally - Local LLM
Run Ollama with Langchain Locally - Local LLM
Abonia Sojasingarayar
Easily Run Hugging Face GGUF Models Locally with Ollama #LLM #HuggingFace #GGUFModels #Ollama#asitop
Easily Run Hugging Face GGUF Models Locally with Ollama #LLM #HuggingFace #GGUFModels #Ollama#asitop
Abonia Sojasingarayar