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