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