Dynamic code generation for calling APIs, not sure what is a fancy term for this...

gzalo · 2025-12-09T20:49:35 1765313375

Something like https://github.com/huggingface/smolagents

Needs a sandbox, otherwise blindly executing generated code is not acceptable

ianbutler · 2025-12-09T23:58:28 1765324708

https://www.anthropic.com/engineering/advanced-tool-use#:~:t...

Anthropic themselves support this style of tool calling with code first party now too.

ekropotin · 2025-12-10T00:05:30 1765325130

Yup, that’s I’ve been taking about.

inerte · 2025-12-09T22:47:36 1765320456

Cloudflare published this article which I guess can be relevant https://blog.cloudflare.com/code-mode/

dwampler · 2025-12-10T12:45:27 1765370727

This is a good example of how things are rapidly evolving.

Also, the new foundation isn't called "The MCP Foundation", but the "Agentic AI Foundation". Clearly a buzzword-compliant name, but also hedging the bet that MCP will be the long-term central story.

willahmad · 2025-12-09T20:16:11 1765311371

this assumes generated code is always correct and does exactly what's needed.

ekropotin · 2025-12-09T21:52:23 1765317143

Same for MCP - there is always a chance an agent will mess up the tool use.

This kind of LLM’s non-determinism is something you have to live with. And it’s the reason why I personally think the whole agents thing is way over-hyped - who need systems that only work 2 times out of 3, lol.

anon84873628 · 2025-12-09T22:46:28 1765320388

The fraction is a lot higher than 2/3 and tool calls are how you give it useful determinism.

ekropotin · 2025-12-10T00:04:32 1765325072

Even if each agent has 95% reliability, with just 5 agents in the loop the whole thing is just 77% reliable.

anon84873628 · 2025-12-10T06:38:55 1765348735

Well fortunately that's not what actually happens in practice.