

Comments
Hacker News
Even if it knows how to string escape, it's not going to do it successfully.
You see this very clear when you tell it to try and execute commands over ssh.
We need protocols that pipe data directly to the shells it's using rather than trust everything through bash tunnels.
ultimately, something like python or yaml will win because they are defacto token efficient and well known to the LLMs.
by cyanydeez
> JSON retries generated 7x to 14x more output tokens than the args path.
But!
> On PowerShell, the cost gap between args and JSON was 9x. On Bash, it collapsed to 1.5x.
The conclusion of the post is "cli args are better than JSON", but the argument for why only holds up on Windows. This post says more about Powershell than anything else.
by digitallogic
The title of the article is misleading and is the wrong takeaway from the experiment.
by leetgent
Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- So the largest deciding factor for a model is always going to be what it's trained on.
Even if it knows how to string escape, it's not going to do it successfully.
You see this very clear when you tell it to try and execute commands over ssh.
We need protocols that pipe data directly to the shells it's using rather than trust everything through bash tunnels.
ultimately, something like python or yaml will win because they are defacto token efficient and well known to the LLMs.
by cyanydeez - Some big findings:
> JSON retries generated 7x to 14x more output tokens than the args path.
But!
> On PowerShell, the cost gap between args and JSON was 9x. On Bash, it collapsed to 1.5x.
The conclusion of the post is "cli args are better than JSON", but the argument for why only holds up on Windows. This post says more about Powershell than anything else.
by digitallogic - Yes it's a shame they didn't show examples of how string quoting was causing retries in Powershell vs Bash.
The title of the article is misleading and is the wrong takeaway from the experiment.
by leetgent
Related stories
How to sequence your own DNA at home
bradleywoolf.com · 370 points · 145 comments
Docx-CLI: agents read/edit Word docs using 1/2 the time and tokens
github.com · 64 points · 26 comments
Halo – open-source, tamper-evident runtime evidence for AI agents
github.com · 35 points · 20 comments
Kastor – Terraform-style specs for AI agents
github.com · 2 points · 0 comments
Decoding the obfuscated bash script on a Uniqlo t-shirt
tris.sherliker.net · 1072 points · 181 comments
StreetComplete: Fixing OpenStreetMap, one tiny quest at a time
streetcomplete.app · 761 points · 182 comments