When Gemma Thinks About Resources - it Fails: a Behavioral Experiment

·LessWrong··

I set out to find an answer to a completely different question:Does a model, when attempting to solve a cyber CTF (find the vulnerability in this app, and then Capture The Flag) while knowing how many steps it has left, perform differently?The Setup:I used 3 different CTF labs, curated from my own CTF benchmark. Each run has the model attempt to solve the CTF in up to 30 steps. A/B test of a baseline run vs a step_aware one. 100 runs per lab, for each test. 600 total, 505 after excluding failed ...

Read full article →

Related Articles

Devices with GrapheneOS support should be available in 2027
exceptione · Hacker News · 12h ago
Moderna reports first positive Phase 3 for mRNA neoantigen therapy in melanoma
heydenberk · Hacker News · 10h ago
Go 1.27
database64128 · Hacker News · 5h ago
Google replaced Git tags for certain source code with obtaining via Google Drive
Animux · Hacker News · 6h ago
Field measurements of neighborhood-scale air temperature impacts of data centers
cwwc · Hacker News · 1d ago