Currently in day 3 of 4 at Hexacon and students have created agents that beat some OverTheWire & CSAW .. a paper a few years ago had 7 authors and 6mo of research partially led by one of the engineers at XBOW, so I’d say we are doing some fun stuff :) gdb, Ghidra, etc automated in agentic loops.

Well the initial vibe check isn’t great but I need a larger sample set. QwenCoder 2.5 did an okay zero shot but since it's not a thinking model I followed up with a prompt of "are there any bugs in the harness?" and it went off the rails producing incoherent output

Hah well the previous benchmark I created was evaluated on a curated vuln identification dataset which made it trivial and allowed me to iterate on the input side which led toward agentic prompt selection. I have other ideas and would incorporate more variables for this task ofc ;)

I was going to include it. Will give it a shot. I need to create a new benchmark to give more empirical measurements. I have a plan for that.

Total awareness, understanding marketability of local models, determining which may be competitive with tuning, etc. Current interest is for which to use for agent dev and tuning for the training I’m developing. Will contrast vs best commercial options as well. Students will have diff applied needs.

Visiting family in western Arizona, not too far from Lake Havasu

If you say “Pet Cemetary” three times in the mirror.. REDRUM

Yep

Nah 3D printed reproduction. I do have an original OKI900 and some red boxes I built in the 90s :)

Support your friendly phreaks! www.etsy.com/listing/1763...