robertk · HackerTrans

4 เดือนที่ผ่านมาdiscuss

You don't know what you are talking about. Obviously refusal circuitry does not live in one layer, but the repo is built on a paper with sound foundations from an Anthropic scholar working with a DeepMind interpretability mentor: https://scholar.google.com/citations?view_op=view_citation&h...

robertk

6 เดือนที่ผ่านมาdiscuss

Why not just open it inside of and print to a static image output within a fully sandboxed Docker container?

robertk

6 เดือนที่ผ่านมาdiscuss

Why not leak a dataset of N full text paraphrasings of the material, together with a zero-knowledge proof of how to take one of the paraphrasings and specifically "adjust" it to the real document (revealed in private to trusted asking parties)? Then the leaker can prove they released "at least the one true leak" without incriminating themselves. There is a cryptographic solution to this issue.

robertk

6 เดือนที่ผ่านมาdiscuss

It’s slightly biased. ( P(even) = 0.5702; Bias = +0.0702 (about 7 percentage points toward heads) ). You can use this Claude Code prompt to determine how much:

Use your web search tool call. Fetch a list of English words and find their incident frequency in common text (as a proxy for likelihood of someone knowing or thinking of the word on the fly). Take all words 10 characters or longer. Consider their parity (even number of letters or odd). What is the likelihood a coin comes up heads if and only if a word is even when sampled by incidence rate? You can compute this by grouping even and odd words, and summing up their respective incident rates in numerator and denominator. Report back how biased away this is from 0.5. Then do the same for words at least 9 characters to avoid “even start bias” given slight Zipf distribution statistics by word length. Average the two for a “fair sample” of the bias. Then run a bootstrap estimator with random choice of “at least N chars” (8 <= N <= 15) and random subsets of the dictionary (say 50% of words or whatever makes statistical sense). Report back the estimate of the bias with confidence interval (multiple bootstrap methods). How biased is this method from exactly random bits (0.5 prob heads/tails) at various confidence intervals?

robertk

6 เดือนที่ผ่านมาdiscuss

“Slightly fringe”

robertk

7 เดือนที่ผ่านมาdiscuss

I am sorry for your loss, Aella. I sobbed with you.

“Each passing minute is a greater percentage of the final minutes we have,” and yet “these [final] seconds are so soft”.

Death needs to die, some future dying day, not yet.

from everyone who’s had a mom, we join you: “Momma, I love you”.

comments