Unfortunately if you're not in the deep end when it comes to these tools, your brain will only be able to parse gibberish.

I was expecting a bit more care from Armin in explaining what does codemode actually do, from first principles.

Well that was my best attempt so far. I have to say that I find it quite tricky to convey.

Someone managed to do it in 4 sentences https://news.ycombinator.com/item?id=49991584

Or 4 paragraphs https://news.ycombinator.com/item?id=49990199

Or 1.5: https://news.ycombinator.com/item?id=49989503

Or essentially 4 again: https://news.ycombinator.com/item?id=49989503

Or literally 1 sentence: https://news.ycombinator.com/item?id=49992276

etc.

----

Honestly, psychologists need to study AI psychosis in depth when people become so enamoured with bullshit, they will spend any and all amount of words inventing new useless bullshit like "hands and brain" for the simplest concepts.

> Like what does this passage even mean:

It means that a LLM side tool (bash) can expose larger (and structured) outputs to Codemode than it normally does when that tool is executed straight to the LLM back as text.

I understand what codemode is from other blog posts, and I think this is a suboptimal explanation. It seems that you are explaining it at the wrong level each time, either too deep (here) or too high (elsewhere in-thread when you talk about 'hands' and 'brain').

Once again it still makes no sense. I guess I need to be familiar with Codemode before trying to understand an article called "what is Codemode".

i was also confused. this introductory post by the creators of Codemode is much easier to follow: https://blog.cloudflare.com/code-mode/

Someone explained the entire thing in just one sentence: https://news.ycombinator.com/item?id=49992276 (more links to other explanations here: https://news.ycombinator.com/item?id=49998923)

Cloudflare Blog actually makes a good job explaining it at the very top, also in one sentence: "Convert the MCP tools into a TypeScript API, and then ask an LLM to write code that calls that API.". The rest of the blog post could probably be skipped :)

The harness exposes tools to the model. The model, during its turn, can request that the harness execute a tool. It may even request multiple tools.

However, natively, the model has no way of composing the tools it sees that it can call. It cannot say, effectively, "use the output of the get_email_id tool, as input for the get_email_Metadata tool."

This is what codemode is. Allowing for the model to interact with the tools that the harness exposes, programmatically.

So, TLDR; Codemode allows for composing at the harness level, rather than just at the inner-tool level.

Thank you!

I read a bit and gave up. Same feeling as when I read “What is gas station” or whatever it was called. But Gas Station was much worse.