The description in the docs is inaccurate. The error code means it detected recitation of training text — and there’s lots of false positives for this, like famous integer sequences. Anecdotally streaming the response seems to bypass it.
RESEARCH
-
RNNs Making a Comeback: State-Space Models Analysis
By
–
RNNs are not dead yet In fact, they are coming back with a vengeance recently. Very nice paper about “The Illusion of State in State-Space Models” (
https://
arxiv.org/abs/2404.08819) and thread -
Sakaná Challenges LLM Scaling Laws with Swarm Intelligence
By
–
サカナが崩すLLM｢規模の法則｣
群知能でOpenAIに挑む @nikkei -
Intense Research Day Yields One Very Important Discovery
By
–
today was an intense day of research. running commands, writing code, checking numbers, being confused, looking at notes, running more commands, taking a nap, literally going then at the end of the day i figured out one (1) Very Important Thing. so today counts as a good day
-
Naming Phenomena in Academia: Entropy and Conceptual Clarity
By
–
Highly recommend that academics spend the time to come up with good names for phenomena they study. And this is great: “In the second place, and more important, nobody knows what entropy really is, so in a debate you will always have the advantage."”
-
What Prompts Do You Use for Relevance Judgements?
By
–
What kind of prompts do you use for relevance judgements?
-
Setting up proper evaluations for AI model selection
By
–
Yet another case where I really need to setup proper evals for my projects so I can get to a definitive answer about which models are "good enough" for what I'm trying to do
-
LLM Model Scaling: 7B to 8x22B Capability Comparisons
By
–
Yeah I can believe that – but compared to each other I think 7B/8x7B/8x22B may have similar relative characteristics to the differences between Haiku/Sonnet/Opus
-
Geoff’s departure over weapons research rejection explained
By
–
On Geoff moving due to rejection of weapons research (a mention, I'd love a more fulsome account if anyone knows one)