Natural emergent misalignment from reward hacking in production rl [pdf]assets.anthropic.com3 points·by neapolisbeach·8 เดือนที่ผ่านมา·0 comments
Whisper leak: a side-channel attack on large language modelsarxiv.org3 points·by neapolisbeach·8 เดือนที่ผ่านมา·0 comments
Google Private AI Compute [pdf]services.google.com1 points·by neapolisbeach·8 เดือนที่ผ่านมา·0 comments
Finding a command injection vulnerability in my smart thermostat (CVE-2023-4212)hmcguinn.com2 points·by neapolisbeach·3 ปีที่แล้ว·0 comments
Vm2 discontinued due to unfixable security issuesgithub.com2 points·by neapolisbeach·3 ปีที่แล้ว·0 comments
neapolisbeach·ปีที่แล้ว·discussNsjail, firecracker, gVisor, or v8 isolates are all good options with different tradeoffs
neapolisbeach·3 ปีที่แล้ว·discussIf you're interested in time-lock puzzles, drand [1] achieves this but through randomness instead of computational effort.[1] https://drand.love/