TLDR version: the fine-tuned model they describe improves things, but I still don't think "improves" is good enough If you are facing an adversarial attacker then reducing the chance that they might find an exploit just means they’ll try harder until they find one that works
ETHICS
-
OpenAI releases detailed prompt injection evaluation paper
By
–
New paper from @OpenAI on prompt injection – it's the most detailed evaluation of the problem I've seen from them so far, and has some very interesting details Posted some of my notes on the paper on my log here: https://
simonwillison.net/2024/Apr/23/th
e-instruction-hierarchy/
… -
LLMs as Arrays: Meditation on Entropy and Truth
By
–
As I emerged from meditation it dawned on me that LLMs are just one array of floats and a while loop over some super simple arithmetic on its elements. It is entropy that is the root of suffering. It's by deleting the superfluous that we uncover truth. And thus I was enlightened.
-
Common Research Pitfall: Confounding Variables in Experiments
By
–
common dark thought pattern in research
> run baseline experiment
> change thing A
> also change thing B
> run new experiment
> collect results
> "wow, thing A works!" -
Explainable AI: Challenges Across Telecommunications and Research
By
–
Looking to gain a deeper understanding of Explainable AI? Experts from Eckerson Group, Orange and Georgia Tech dive into the challenges of AI explainability from telecommunications networks to academic research. https://
buff.ly/3vNcwMr -
Mass Digital Surveillance Versus Historical Freedom From Monitoring
By
–
"Our societies have not previously tolerated spaces that are beyond the reach of law enforcement" For 100s of 1000s of years, almost EVERY space was 'beyond the reach' of LE surveillance. Mass digital surveillance is a VERY recent development. PLS, read a book before spewing
-
US Tech Surveillance Monopolies Military Ties Geopolitical Risk
By
–
I am surprised you reflexively see large surveillance monopolies jurisdictioned in the US yoking themselves to the US military at a time of increasing volatility in the US (and beyond) as a solution to said “dangers”
-
LLMs Struggle With Complex Individual Identities in Social Research
By
–
There are many good uses for AIs in social science research, but also many clear cases when they are inappropriate as well. This paper shows how LLMs struggle with portraying complex individual identities (like race or gender), suggesting important limitations for research use.
-
AI sheep technology threatens democratic systems worldwide
By
–
That sheep may end up killing democracy.
-
Meta AI’s Inadequate Safety Guardrails Criticized
By
–
Half-baked guardrails FTW @metaai Cc @KatieConradKS @Rahll https://
x.com/RosenzweigJane
/RosenzweigJane/status/1782168285384994846
…