111–120 of 185 posts
Q: We need you to draw seven red lines. All of them strictly perpendicular; some with green ink and some with transparent. Can you do that? A: I'm sorry, but I am a text-based AI model and I don't have the ability to physically draw lines or use different colors of ink. However, I can help you visualize this concept by describing the red lines and the different ink colors. A red line with green ink: Imagine a traditi…
Q: We need you to draw seven red lines. All of them strictly perpendicular; some with green ink and some with transparent. Can you do that? A: I'm sorry, but I am a text-based AI model and I don't have the ability to physically draw lines or use different colors of ink. However, I can help you visualize this concept by describing the red lines and the different ink colors. A red line with green ink: Imagine a traditi…
lmao what?
Try a foreign language. It was total failure with Turkish. ChatGPT is about a million times better at it although it's worse than it is with English.
LLaMA doesn't contain any meaningful training data in Turkish
Earlier quoted context omitted.
> However, if this is true, it seems pretty cool if I can train a GPT4-like model for only $300. Not train, but fine-tune a model that Facebook spent millions of dollars training.
They absolutely did not spend millions to train it. Credible estimates place the cost for an entity like Meta at about 30-100k, probably less since Meta likely owns the 256 A100x8s needed to train it. Even as an individual, it wouldn't cost you anywhere near a million if you only trained 13B and took advantage of volume pricing.
Similarly, the other day I asked it to explain a hard-to-understand philosophy quote and it explained it properly (I believe).
Can someone explain how they do this? It seems magical.
Earlier quoted context omitted.
“Can you name all of the soccer players whose names contain a Z”
It's so weird. No matter how I ask, it gets something wrong about this question. > Can you name 20 soccer players whose names contain a Z, and for each one, place brackets around the letter Z (Z)inedine (Z)idane Cristiano Ronaldo dos Santos A(ve)iro Andrej W(sz)ołek Nemanja Mati(c) Dusan Tadi(c) Gr(az)iano Pellè Jakub Bła(śc)z(ykowski) Kamil Glik Luk(asz) Pi(sz)czek Blai(se) Matuidi Miralem Pjani(c) Marek Ham(śi)k Lu…
I can't understand how something called "a language model" can evaluate some input text. ChatGPT4 seems like it understands the text of the first assistance and properly assesses that it wasn't actually a description of the trip. Similarly, the other day I asked it to explain a hard-to-understand philosophy quote and it explained it properly (I believe). Can someone explain how they do this? It seems magical.
The jury is still out.
> * According to a fun and non-scientific evaluation with GPT-4. Further rigorous evaluation is needed.
Come on... I love any effort related to LLM, but it's really disingenuous to claim high quality in the title and then immediately discredit it after click-through.
> 90%* > * According to a fun and non-scientific evaluation with GPT-4. Further rigorous evaluation is needed. Come on... I love any effort related to LLM, but it's really disingenuous to claim high quality in the title and then immediately discredit it after click-through.
The work being done with Llama and Alpaca and so on is what I've found to be most interesting in the past few weeks. The fact that we are capable of producing such high quality conversational models that we can actually get to freely experiment with is really encouraging. I'm particularly excited about applications such as viper[1] and other forms of plugins as well as model ensembles. [1] https://viper.cs.columbia.e…
Turns out LLMs are not so inaccessible for individual users.