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