31–40 of 61 posts
And perhaps it's significantly easier on other routers, but I would not have gotten VLANs working without claude doing it for me...
MikroTik recently updated their documentation site from an Atlassian Confluence Wiki to much more AI-friendly Docusaurus here: https://manual.mikrotik.com/ Any page can be easily converted into Markdown by appending .md to the URL. I mention this because in my experience, the agent is much more accurate when it has access to the docs.
MikroTik recently updated their documentation site from an Atlassian Confluence Wiki to much more AI-friendly Docusaurus here: https://manual.mikrotik.com/ Any page can be easily converted into Markdown by appending .md to the URL. I mention this because in my experience, the agent is much more accurate when it has access to the docs.
Thankfully at least LLMs could figure out things t help me setup SXT LTE 7
Interesting that sending things like network configurations, keys, and credentials to external entities - which BTW are fueled by data - is considered "ok" now.
Perfect job for a local LLM!
MikroTik recently updated their documentation site from an Atlassian Confluence Wiki to much more AI-friendly Docusaurus here: https://manual.mikrotik.com/ Any page can be easily converted into Markdown by appending .md to the URL. I mention this because in my experience, the agent is much more accurate when it has access to the docs.
Earlier quoted context omitted.
> I have the agent write a script that is aimed to be idempotent and then run the script. You can take this one step further and have the agent write Terraform configs [1]. I did this (including having the agent import all the initial resources from the live device), works great and is generally more robust than a script. [1] https://github.com/terraform-routeros/terraform-provider-rou...
I originally wrote specific terraform providers (even one for just configuring an Ubuntu machine), but over time I found that TF is a bit too heavyweight for my use-cases. The shell script works well because state divergence can be investigated by the LLM. The slowness of state refreshing etc. does make a TF apply painful. For me at least.
Yeah, TF is slow if you have thousands of configs and batching not integrated in the provider.
Interesting that sending things like network configurations, keys, and credentials to external entities - which BTW are fueled by data - is considered "ok" now.
It's nowadays the default not to export any credentials when exporting MT configs, and even doing that yourself is trivial. Since the equipment is pretty packed with functionality and very flexible, benefits of LLM assistance is big.
As for "sending network configurations" it's a risk everyone needs to consider individually. Having that private may make attackers job harder, but security by obscurity ain't no replacement for a secure setup.
Interesting that sending things like network configurations, keys, and credentials to external entities - which BTW are fueled by data - is considered "ok" now.
There is also a terraform provider. Not sure if there is a safe mode here. I normally test via ssh safe mode and import the changes afterwards.