New DFIR Thoughts post: Put AI in the code, not the conclusions 🎯
Ask a chatbot the same question ten times, get ten answers. Tested code gives one, and if it's wrong, you fix it once.
https://leapps.org/blog-post?post=2026-10-20-put-ai-in-the-code-not-the-conclusions
LEAPPsDFIR Thoughts: Put AI in the code, not the conclusions — LEAPPs BlogHanding examiners a chatbot that draws conclusions from parsed data is the wrong way to bring AI into digital forensics. Here is why, and what I do instead with a known-data corpus, tested code and CI checks.