An interesting use case for local LLMs that I've been experimenting with: OSINT and research on local policy issues, especially commercially backed developments. A lot of these come in hot on city council and county commissioner court agendas, with a lot of hidden money and connections behind it.Having something that can rip through mind-numbingly boring meeting minutes, regulatory documents, grant proposals and press releases to find leads is kind of amazing.Qwen 3.8 is quite happy to help the citizens find corruption and flimsy business plans with public open sources. A bit slow, but also unstoppable.#neverslop and all that, but it is a useful tool for search, at a scale I would not have time or energy for. I'd prefer it didn't have to exist at all, but also, I got the system to fuck the system. Something kind of ironic in using an LLM to fight data center developments (and nuke bros, and good ol' boy self-dealing, and..)So far I'm just asking questions in a pi sandbox to find leads ...
Related
Calling =TECHTO_MLREGRESSION for Machine Learning supervised regression in Excel is just a matter of copying and pasting...
Calling =TECHTO_MLREGRESSION for Machine Learning supervised regression in Excel is just a matter of copying and pastinghttps://thierrymoudiki.github.io/blog/2025/07/06/r/python/te...
An interesting use case for local LLMs that I've been experimenting with: OSINT and research on local policy issues, esp...
An interesting use case for local LLMs that I've been experimenting with: OSINT and research on local policy issues, especially commercially backed developments. A lot of these com...
The cheap agent model has a reliability problemMeta’s Muse Ember is built for tool calls, routing, extraction and coding...
The cheap agent model has a reliability problemMeta’s Muse Ember is built for tool calls, routing, extraction and coding subtasks. Its value depends on how often it finishes routin...