Security research, field notes, and practical experiments
Writing
Independent technical notes by Willis Vandevanter.
Recent writing
n-day speed has to be accepted
This normally takes a few days and a release within a week or two is reasonable. Within about ten minutes (!) this website was fielding probes for percent-encoded traversal sequences, indicating that automated watchers are keeping an eye on public …
OpenAI AGI bar
[Sama] estimates they’ll declare AGI achieved internally by December 2026.
Via Latent Space: [AINews] OpenAI to reach …
economics of open versus closed weights
this is a great read by Christian Catalini. i have been enjoying recent discussions on where we see the economy/policy move for closed vs …
gradient-free jailbreaks and cpu-side suffix search
We challenge these constraints by demonstrating that token-level iterative optimization can succeed without gradients or priors. We introduce RAILS (RAndom Iterative Local Search), a framework that operates solely on model logits. … Crucially, …
active defense and adversarial agents: coordination poison (exploratory idea)
in previous posts we have looked at guardrail triggers, token burn, hostname beacons, malicious skills, context bombs, exploding search space, service sandbagging, and GCG attacks. this time: coordination poison. note, although there could be real world …
active defense and adversarial agents: GCG attacks
in previous posts we have looked at guardrail triggers, token burn, hostname beacons, malicious skills, context bombs, exploding search space, and service sandbagging. this time I want to ideate on a potential application of GCG.
active defense is the practice …
active defense and adversarial agents: service sandbagging
in previous posts we have looked at guardrail triggers, token burn, hostname beacons, malicious skills, context bombs, exploding search space, and GCG attacks. this time: service sandbagging.
active defense is planting traps that force an agent to reveal …
active defense and adversarial agents: context bombs
From Tracebit’s
active defense and adversarial agents: exploding search space (academic)
in previous posts we have been looking at different active defense approaches: guardrail triggers, token burn, hostname beacon, malicious skills, context bombs, service sandbagging, and GCG attacks. I want to explore one I recently read in an academic paper. …