Scott J Roberts

543 Followers
162 Following
122 Posts
@DaveMWilburn Oh, it’s a legit issue in any classification system.
If you’re releasing a TLP Amber report that’s nothing but a rehash of public reporting you’re using TLP incorrectly.
@chrissanders88 what’s the business professional way of saying “delusionally unrealistic”? Reminds me of a company that wanted sub minute containment. Tell me you don’t know intrusion detection without telling me you don’t know intrusion detection.
@Oreoshake oh, you can have the same fun… but in text.
@Oreoshake Or…. Make diagrams with code. https://www.mermaidchart.com/
Mermaid Chart

A smarter way of creating diagrams.

Ever tried combining Large Language Models with Structured Analytic Techniques? It’s like teaching an AI to think like an intelligence analyst—minus the SCIF and crippling paranoia.

Dive into the experiment: https://sroberts.io/posts/llm-sats-ftw/

#LLM #StructuredAnalysis #IntelligenceAnalysis

LLM SATs FTW

Unless you’ve spent the last 5 years asleep you know that every team, business, and industry is being turned upside down by AI. Every startup is trying to create the newest AI offering, every tech giant is trying to add LLM functionality everywhere, and every business is trying to replace employees with agents. But what does this mean for intelligence analysts? How can we use LLMs to help us with our work? And what are the limitations? Can we overcome them? Or are we just going to end up with a bunch of over hyped tools that don’t really help us at all?

@sroberts
@Oreoshake I'd raise you our new ODNI
One of the nicest things about my transition to academia is the time to read, often reading stuff I'd argue I should have been reading while running threat research.
@AlexandreSieira @alex Great event! I still have wonderful memories, even if my slides borked!
@grubbslinger @pdxbek @likethecoins Super glad you’re enjoying it! Very proud of how it turned out.