Computation Beyond Tool Use: Executing Programs Inside a Transformer
By
Madhu Shantan
3mo ago
Source
MaximComputation Beyond Tool Use: Executing Programs Inside a Transformermaxim-blog.ghost.ioWhen LLMs need to compute something reliably, we've settled into a familiar pattern: the model writes code, an external interpreter runs it, the result gets injected back into the context, and the model carries on. It works well enough that we rarely stop to question the architecture. But
You might also wanna read
How Interface Design Impacts LLM Coding Performance More Than Model Selection
The article argues that the current focus on comparing which large language model (LLM) is best at coding is misguided because the real bott
blog.can.ac·4mo ago
Reflections on LLMs and Their Impact on Software Development Practices
The author shares personal reflections on the current state of Large Language Models (LLMs) and AI in software development, questioning whet
martinfowler.com·10mo ago
Examining the Compiler Analogy: Are LLMs the Next Evolution in Programming Abstraction?
The article explores the debate around whether Large Language Models (LLMs) are similar to compilers and whether we're moving toward a world
alperenkeles.com·5mo ago
A Journey from AI to LLMs and MCP - 2 - How LLMs Work – Embeddings, Vectors, and Context Windows
iceberglakehouse.com·1y ago
Context orchestration: what it is & how it works
Redis·1mo ago
Comparing Code-Driven and LLM-Driven Workflows for Internal Agent Development
The article discusses the author's experience building internal agents and compares code-driven versus LLM-driven workflows. While initially
lethain.com·6mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.