RSS

Ihor Ivliev

Karma: 8

Thinker

AI Self-Mod­ifi­ca­tion Am­plifies Risks

Ihor IvlievJun 3, 2025, 8:27 PM
0 points
0 comments2 min readEA link

Eigh­teen Open Re­search Ques­tions for Govern­ing Ad­vanced AI Systems

Ihor IvlievMay 3, 2025, 7:00 PM
2 points
0 comments6 min readEA link

Ar­chi­tect­ing Trust: A Con­cep­tual Blueprint for Ver­ifi­able AI Governance

Ihor IvlievMar 31, 2025, 6:48 PM
2 points
0 comments8 min readEA link

How to build AI you can ac­tu­ally Trust—Like a Med­i­cal Team, Not a Black Box

Ihor IvlievMar 22, 2025, 9:27 PM
2 points
1 comment4 min readEA link

Adap­tive Com­pos­able Cog­ni­tive Core Unit (ACCCU)

Ihor IvlievMar 20, 2025, 9:48 PM
10 points
2 comments4 min readEA link

Nav­i­gat­ing AI Safety: Ex­plor­ing Trans­parency with CCACS – A Com­pre­hen­si­ble Ar­chi­tec­ture for Discussion

Ihor IvlievMar 12, 2025, 5:51 PM
2 points
1 comment2 min readEA link