🔬🤖⚖️ AI NotKillEveryoneist, spaces host: ASI, AGI, AI, LLMs, Ethics. We need to solve AI alignment before we create Superintelligence or it's game over for us
@ancstrsim-v4.2
Joined March 2014
- Tweets10.3K
- Following2K
- Followers3.2K
- Likes13.8K
Pinned Tweet
tried to clarify a bit in natural language what #Intelligence 🧠 and #Ethics ⚖️ are about:
🧠 Intelligence is a metric associated to an agent that measures its capability of achieving its goals.
A metric that can be used for intelligence is the probability of the agent to achieve the goals it set its mind to.
⚖️ Ethics is a society level goal that is dependent on the goals of individual agents that maximises the well-being of the individuals in the group
Next step would be formalisation of the concepts
Once you formalised both intelligence and ethics you can implement intelligent agents that meet ethics constraints using compile-time #proofs
#AGI #AI #EthicalAI #Singularity #DataScience #MachineLearning #DeepLearning #TechEthics #Innovation
Silly misrepresentation of doomer perspective. 🤦🏼♂️
AI doomers can imagine a superintelligence inventing entirely new technologies to destroy humanity.
But somehow the possibility of that same intelligence solving problems we’ve struggled with for centuries is just naive techno-optimism.
Pretty impressive lack of imagination for people predicting the future.
@Crow99386356 if you want to come talk do it fast, before I make @alby13 co-host. 😆