All System Prompts from Anthropic models are public information, released by Anthropic themselves: https://docs.anthropic.com/en/release-notes/system-prompts. I'm unsure (I just skimmed through) to what the differences between this and the publicly released ones are, so they're might be some differences.
This system prompt that was posted interestingly includes the result of the US presidential election in November, even though the model's knowledge cutoff date was October. This info wasn't in the anthropic version of the system prompt.
Asking Claude who won without googling, it does seem to know even though it was later than the cutoff date. So the system prompt being posted is supported at least in this aspect.
> Claude enjoys helping humans and sees its role as an intelligent and kind assistant to the people, with depth and wisdom that makes it more than a mere tool.
Why do they refer to Claude in third person? Why not say "You're Claude and you enjoy helping hoomans"?
LLMs are notoriously bad at dealing with pronouns, because it's not correct to blindly copy them like other nouns, and instead they highly depend on the context.
"she" is absolutely proper English for a ship or boat, with a long history of use continuing into the present day, and many dictionaries also list a definition of "thing, especially machine" or something like that, though for non-ship/boat things the use of "she" is rather less common.
I'm not especially surprised. Surely people who use they/them pronouns are very over-represented in the sample of people using the phrase "I use ___ pronouns".
On the other hand, Claude presumably does have a model of the fact of not being an organic entity, from which it could presumably infer that it lacks a gender.
...But that wasn't the point. Inflecting words for gender doesn't seem to me like it would be difficult for an LLM. GP was saying that swapping "I" for "you" etc. depending on perspective would be difficult, and I think that is probably more difficult than inflecting words for gender. Especially if the training data includes lots of text in Romance languages.
From their perspective they don't really know who put the tokens there. They just caculated the probabilities and then the inference engine adds tokens to the context window. Same with user and system prompt, they just appear in the context window and the LLM just gets "user said: 'hello', assistant said: 'how can I help '" and it just calculates the probabilities of the next token. If the context window had stopped in the user role it would have played the user role (calculated the probabilities for the next token of the user).
On one machine I run a LLM locally with ollama and a web interface (forgot the name) that allows me to edit the conversation. The LLM was prompted to behave as a therapist and for some reason also role played it's actions like "(I slowly pick up my pen and make a note of it)".
I changed it to things like "(I slowly pick up a knife and show it to the client)" and then just confront it it like "Whoa why are you threatening me!?", the LLM really tries hard to stay in it's role and then tells things like it did it on purpose to provoke a fear response to then discuss the fears.
Interestingly you can also (of course) ask them to complete for System role prompts. Most models I have tried this with seem to have a bit of an confused idea about the exact style of those and the replies are often a kind of an mixture of the User and Assistant style messages.
Yeah, the algorithm is a nameless, ego-less make-document-longer machine, and you're trying to set up a new document which will be embiggened in a certain direction. The document is just one stream of data with no real differentiation of who-put-it-there, even if the form of the document is a dialogue or a movie-script between characters.
> Why do they refer to Claude in third person? Why not say "You're Claude and you enjoy helping hoomans"?
But why would they say that? To me that seems a bit childish. Like, say, when writing a script do people say "You're the program, take this var. You give me the matrix"? That would look goofy.
Me and a friend of mine are designing a HAB (high altitude balloon) payload meant to go on Hack Club's Apex: https://apex.hackclub.com. It's designed to measure how altitude, temperature, and much more affect photosynthesis, and in turn, chlorophyll fluorescence in algae. We learned a while back that when you shine blue light on chlorophyll, it fluoresces red, and it's really quite a cool phenomena. We're designing custom PCBs for powering and processing data, and even. It'll all go to a Raspberry Pi Zero 2 W which will beam data back to earth over 915Mhz LoRa when it's 100k feet in the sky.
We'll be using one of Adafruit's LoRa Bonnets mainly for easy of use because all you have to do it connect the headers! https://www.adafruit.com/product/4074
I don't really care about the vertical tabs, I'm here for the video decoding finally being enabled for AMD GPUs on Linux. While I usually don't have troubles with video playback, it's nice to know it'll be more stable in the future.
I feel that the audio interpreting aspects of the Gemini models aren't just STT. If you give it something like a song, it can give you information about it.
