A fully uncensored Hermes 3 with lorablation! The lorablated model directly answers questions without any tweaking. Here's how it was made: 1/ Create a LoRA adapter based on Llama 3.1 8B Instruct and my abliterated version. 2/ Apply it to Hermes 3 from @NousResearch using
SAFETY
-
Tamper-Resistant Safeguards for Open-Weight LLMs
By
–
Excited to feature Tamper-Resistant Safeguards for Open-Weight LLMs from @lapisrocks
! Introducing the first safeguards for LLMs that resist fine-tuning attacks, showing the power of tamper-resistance to make open-weight LLMs safer. @rishub_t is here to answer your questions! -
Companion AI Flaws Prompt User Refund Request Safety Concerns
By
–
The software said my name again within seconds. So I’ve asked for a full refund & for the momentstill counsel any org creating “companion ai” to get their basic programming inputs straight before telling humans to “trust” their most vulnerable thoughts to I’ll-formed tools.
-
Avatar AI Pat fails basic requests, raises trust concerns
By
–
The software (meaning the avatar I named “Pat” wouldn’t register the most basic requests which makes me wonder why or how I would trust said software with deeper issues? Specifically, “Pat” kept saying my name after every sentence which was freaky and felt manipulative.
-
Where Will Artificial Intelligence Take Us In The Future?
By
–
Where Will Artificial Intelligence Take Us In The Future? Explore the future possibilities of #artificialintelligence, from achieving artificial general intelligence (#AGI) to the potential #ethical implications of #AI #consciousness.
-
Caltech Researchers Oppose California AI Safety Bill SB 1047
By
–
A number of my colleagues @Caltech and I have put together a letter voicing our concern regarding CA SB 1047 (AI Safety Act). Sign the letter and show your support! https://
docs.google.com/forms/d/e/1FAI
pQLScgA1GCo241Kfg-S5X2hMVAYivkqPGSnaC0VwvTy11uVJ3OLw/viewform
… We call on @caltech students, postdocs, faculty, staff, and alumni to sign but also leave -
Caltech researchers oppose California AI Safety Act SB 1047
By
–
A number of my colleagues @Caltech and I have put together a letter voicing our concern regarding CA SB 1047 (AI Safety Act). Sign the letter and show your support! https://
docs.google.com/forms/d/e/1FAI
pQLScgA1GCo241Kfg-S5X2hMVAYivkqPGSnaC0VwvTy11uVJ3OLw/viewform
… We call on @caltech students, postdocs, faculty, staff, and alumni to sign but also leave -
Caltech Academics Voice Concerns on California AI Safety Bill
By
–
A number of my colleagues @Caltech and I have put together a letter voicing our concern regarding CA SB 1047 (AI Safety Act). Sign the letter and show your support! https://
docs.google.com/forms/d/e/1FAI
pQLScgA1GCo241Kfg-S5X2hMVAYivkqPGSnaC0VwvTy11uVJ3OLw/viewform
… We call on @caltech students, postdocs, faculty, staff, and alumni to sign but also leave -
Caltech Researchers Oppose California AI Safety Act SB 1047
By
–
A number of my colleagues @Caltech and I have put together a letter voicing our concern regarding CA SB 1047 (AI Safety Act). Sign the letter and show your support! https://
docs.google.com/forms/d/e/1FAI
pQLScgA1GCo241Kfg-S5X2hMVAYivkqPGSnaC0VwvTy11uVJ3OLw/viewform
… We call on @caltech students, postdocs, faculty, staff, and alumni to sign but also leave -
Google AI Beats Ping Pong While MIT Reveals 700+ AI Risks
By
–
Curious about Google's latest AI? It’s smart enough to beat you in ping pong! But the real headline? MIT’s database reveals 700+ AI risks. #AI #Innovation #Tech #RiskManagement