Related Posts
From Common Factors to AURELIS
If only common factors work, then only common factors should we teach and reimburse. Does this point towards AURELIS? You bet. The science According to a ton of scientific studies, clearly and robustly, psychotherapeutic methods are ineffective. This may be hard to swallow, so I repeat. Lots of studies and even many meta-analyses show no Read the full article…
Why A.I. Needs Inner Coherence, Not Just Oversight
What if the real danger in Artificial Intelligence isn’t raw power, but a hollow core? This blog explores why A.I. that merely appears aligned is not enough — and why genuine safety demands an inner coherence that cannot lie. A scientist’s warning In April 2025, Yoshua Bengio stood on a TED stage, showing concern. He Read the full article…
Rewards or Value?
Are people driven more by direct rewards or broader value? Should A.I. be driven rather by one or the other? What about end values? Zero-sum values These are nothing but the sum of individual rewards. For instance, one earns tokens on several timesteps. The eventual zero-sum value is the sum of all tokens earned ― Read the full article…