Alien Life AI emblemALIEN LIFE AIThe AI Deck

Alignment

The newest safety and alignment documents

What was actually published on making these systems safe, newest first. Research, evaluations, incident write-ups, policy documents and the arguments about them.

46 documentssources checked 21 Sep, 2:42 PM CDT

Newest first

How a document gets onto this page

Two ways, and the difference is worth stating because one of them is more reliable than the other.

It came from a source whose whole subject is this. That is a register lookup, not a judgement, and it accounts for 40 of the 46 below:

And every link here went through the reader's door first, the same as every article link on this site: 35 document(s) that would otherwise be on this page were dropped because a reader could not open them.

Or the deck's classifier labelled it a safety story. That axis measured 36.1% against a sample it was never tuned on, well under the 70% floor this site requires before a label may be printed anywhere. It is used here regardless, and deliberately: this page selects with it, it does not label with it. Showing you an extra document costs you nothing; printing a category on one would be a claim.

And it is not trusted alone. A story selected that way must ALSO carry an alignment term in its own headline, checked against the same register the classifier uses. One weak signal put a story about posters on this page; two signals is what removed it. That pairing brought in 6 of the 46, and turned away another 55 the classifier alone would have included. The whole table is on the ledger.