Sounds like you don't have enough experience with coding agents. Deterministic scripts must always be preferred instead of LLM tool calls.
In fact, you should instruct your agents to write code to execute instead of letting them call tools.
Then why did you comment what you commented, good sir/madam. Claude and Codex are good at remembering to use scripts instead of tools these days, especially if your <32kb .md file mentions it. Not even talking about the skills designed to catch such issues.
Sounds like you completely lack all reading comprehension ability
LLMs sometimes like to execute one-off Python scripts to make edits to files rather than just calling the edit tool directly. Both are tool calls so saying that you should have it write code instead of doing tool calls makes no sense because writing code is a tool call for it...
There is nothing to disprove as you don't understand what does a word mean. Deterministic is not a spectrum, they can either be deterministic or not. In both cases, they are not.
How dared I to imply that some LLM output is more deterministic than the other, your LLM majesty. Shame on me and my entire family! For generations to come!
So sorry I implied that the code that doesn't work and has to be fixed later is deterministic in its execution and can be reused later instead of being re-generated from scratch!
Holy moly. How did you arrive to that conclusion? Why do you think openai and anthropic train their models to generate scripts instead of tool calls now? Maybe you work there, or maybe not good enough?
Calling scripts wins long term. Maybe you haven't had a chance to work with agents for months on the same task and observing them getting looped. That is your ignorance talking.
Why am I even discussing it with people who don't understand basic costs of time and money, ffs.
They're talking about writing a file with a harness-native Edit tool. They're saying the agents aren't doing that, but are using ad-hoc methods of writing the files. (My agents seem to prefer see these days.)
Why do you think your agents prefer to create scripts instead of doing tool calls these days?
I wonder, is it easier to modify a script that agent wrote before to satisfy your prompt, or is it easier to write a new one from scratch each time a retry happens?
Are input tokens more expensive than output tokens?
My god. They are not reusing the scripts. They are adhoc, inline Python scripts just used to make a single edit. You seem to fundamentally not understand what everyone else is talking about
Nobody else is talking about the reusable scripts they create, we are talking about it using inline Python to make edits to files instead of just editing it with the Edit tool. But I don't know why I'm explaining this to you again because you clearly don't understand lol
Vibe coders like you who don't even understand basic fundamentals are pretty infuriating because you don't even understand what everyone else is talking about
It's funny because you pretend to know something but unwilling to provide any proofs for your claims.
I believe you are one of your so called vibe-coders. Who just think they know something but in fact they have an inflated ego.
That will pass with time, once you get more experience around people, I hope. Or now, and then you'll become one of those edgy bullshitters.
And I'm so sorry that I'm allegedly distilling openai and claude models for the sake of deepseek in china, while being an US citizen. You must be feeling very butthurt about it. And that's what keeps my night sleep sound. I wish I could taste your tears.
