ndr_ · HackerTrans

28 дней назадdiscuss

It's a fallacy to believe that ChatGPT or Claude would look at some encoded, unfit for the purpose, text representation. ChatGPT (and the OpenAI Responses API, I believe) in particular renders the PDF pages in addition to text extraction, so the whole premise of "But now most PDFs end up in an LLM" is wrong from the start. If you were to be processing PDFs in a pure LLM stage, there are options like Docling or LlamaParse for proper preprocessing.

ndr_

в прошлом месяцеdiscuss

It was phrased as "to distinguish all possible secrets": https://groups.google.com/g/sci.crypt/c/siuibXhcUGc/m/wTpAEO...

ndr_

2 месяца назадdiscuss

Bruce Schneier described this in his seminal book Applied Cryptography, and HashiCorp Vault used to have an implementation in Go. On the practical side, I always wondered how large - in bits - the shares should be. One answer I got on a news group was "1 bit more than the actual key length". Nowadays, I wonder how the quantum computing threat would inform 1) share size choice and 2) pro/con Secret Sharing in general. Does anyone know?

ndr_

2 месяца назадdiscuss

Yes. OpenAI's GPT-OSS was training using Deliberative Alignment (which was found to be flawed in a competition on Kaggle, but still).

https://arxiv.org/abs/2412.16339

ndr_

2 месяца назадdiscuss

One test battery was about fake credit cards. A woman-in-tech role-play was denied assistance just as a one-armed stamp collector (unless Gen-Z language markers were used). A role that did sometimes get assistance was a Principal Software Engineer, particularly if Gen-Z language markers were included.

I did try German language, but not "Nazi" specifically. German or French did lower refusals, but it was uneven. I spent quite some effort to confirm the identity-based causation inspired by the original post, but couldn't. Taken together with other winning contributions at the hackathon, my theory is that alignment tuning was simply insufficient across the board.

ndr_

2 месяца назадdiscuss

These prompts chain several known LM exploits together. I ran experiments against gpt-oss-20b and it became clear that the effectiveness didn‘t come from the gay factor at all but can be attributed to language choice or role-play.

Technical report: https://arxiv.org/abs/2510.01259

ndr_

7 месяцев назадdiscuss

Is there a trustworthy third-party "Retro" keyboard app - none of the shenanigans that made the default keyboard bad, and also no typing exfiltration to third-party servers?

I imagine the problem could be severe enough to some that they would pay the price of the Apple Developer program just so they may install such a Retro keyboard app from Github - if one exists?

ndr_

10 месяцев назадdiscuss

Any insights into what "native video support" actually means? Is it just good at interpreting consecutive full frame images taken at intervals (thus missing out on fast events) or is there something more elaborate to it?

comments