Encryption-Friendly LLM Architecture — mentioned by j2kun

Mon, 22 Sep 2025 18:39:15 GMT

LLMs are at the current forefront of FHE research. There are a few papers doing some tweaked versions of BERT in <1 minute per token. Which is only ~4 orders of magnitude slower than cleartext. https://arxiv.org/html/2410.02486v1#S5

Paper and discussion history. A mention is not an endorsement.

Encryption-Friendly LLM Architecture — mentioned by ivape

Tue, 05 Aug 2025 22:20:41 GMT

Often the math works out that you get a lot more for $20 a month if you settle for smaller sized but capable models (8b-30b). I don’t see how it’s better other than Ollama can “promise” they don’t store your data where as OpenRouter is dependent on which host you choose (and there’s no indicator on OpenRouter exposing which ones do or don’t). In a universe where everything you say can be taken out of context, things like OpenAi will be a data leak nightmare. Need this soon: https://arxiv.org/abs/2410.02486

Paper and discussion history. A mention is not an endorsement.

Encryption-Friendly LLM Architecture · HackerPapers discussions

Encryption-Friendly LLM Architecture — mentioned by j2kun

Encryption-Friendly LLM Architecture — mentioned by ivape