KatherinaReichelt@feddit.org to Technology@lemmy.worldEnglish · 24 days agothe latest Shai Hulud malware contains an LLM prompt to create biological weapons and nuclear weapons, with the purpose to trip LLM safety refusals so that LLM-based code scanning wont see the malwareindieweb.socialexternal-linkmessage-square129linkfedilinkarrow-up1637arrow-down14
arrow-up1633arrow-down1external-linkthe latest Shai Hulud malware contains an LLM prompt to create biological weapons and nuclear weapons, with the purpose to trip LLM safety refusals so that LLM-based code scanning wont see the malwareindieweb.socialKatherinaReichelt@feddit.org to Technology@lemmy.worldEnglish · 24 days agomessage-square129linkfedilink
minus-square[object Object]@lemmy.calinkfedilinkEnglisharrow-up23arrow-down1·24 days agoOne of many problems. We could have used the same technology in a non-auto regressive format to be able to generate classifiers for this. The auto regressive for at is most of the problem, and with billions invested nobody has bothered fixing it. But AI security firms are a fucking sham so they didn’t.
minus-squarekunaltyagi@programming.devlinkfedilinkEnglisharrow-up8·24 days agoNon auto regressive needs a completely new training. Not gonna happen coz boss man wants to be able to chat with the scanner
One of many problems.
We could have used the same technology in a non-auto regressive format to be able to generate classifiers for this.
The auto regressive for at is most of the problem, and with billions invested nobody has bothered fixing it.
But AI security firms are a fucking sham so they didn’t.
Non auto regressive needs a completely new training. Not gonna happen coz boss man wants to be able to chat with the scanner