41–50 of 197 posts
Earlier quoted context omitted.
Best closest I stumble on is nouswise. Lets you contain an agent with even more sources and generate almost all outputs.
Like how many sources? And what you mean by sources (tables pdfs...)?
I'd like to have audio overviews of scientific papers, so I can "read" them while I drive. NotebookLM/Gemini Notebook sorta does this, but the two-person podcast format is kind of annoying and it can't pronounce math. Is there something out there that will do this? I'm sure the right harness around frontier models would make it work.
Any people with insight on why this happens? From my corporate experience this generally happens when two teams are working on a similar thing, they complain about turf to leadership, and leadership either makes them consolidate efforts or chooses a winner. Is that what happens at Google a lot? Or do they just constantly tweak things to the point they cease to live or be used?
Eventually, if something makes news or when they try to trim offerings, suddenly the company can focus on it and then does course corrections.
Something of note is that this is now the third name for this product, the first name was impressively bad and so myopic that it feels kinda hilarious.
They wanted to call it Tailwind. Like the #1 CSS framework on earth.
I'd like to have audio overviews of scientific papers, so I can "read" them while I drive. NotebookLM/Gemini Notebook sorta does this, but the two-person podcast format is kind of annoying and it can't pronounce math. Is there something out there that will do this? I'm sure the right harness around frontier models would make it work.
random idea -- driving while you drive?
I'd like to have audio overviews of scientific papers, so I can "read" them while I drive. NotebookLM/Gemini Notebook sorta does this, but the two-person podcast format is kind of annoying and it can't pronounce math. Is there something out there that will do this? I'm sure the right harness around frontier models would make it work.
Feel free to email if you have any questions or feedback.
My current “audio-learning” hack is ChatGPT Live which has become shockingly good after being awful compared to Claude Voice (Let’s not even talk about Gemini voice which is still bad).
I go on a walk and dump a paper or article link in the chat, and ask chatGPT Live to walk me through the content in small nuggets, so I can discuss them interactively. For deeper topics I have it quiz me Socratic style so I’m not just passively listening, and actually thinking through problems or ideas.
I'd like to have audio overviews of scientific papers, so I can "read" them while I drive. NotebookLM/Gemini Notebook sorta does this, but the two-person podcast format is kind of annoying and it can't pronounce math. Is there something out there that will do this? I'm sure the right harness around frontier models would make it work.
How would the right format for you look like? Specially be monologue?
Can pronounce math is the real showstopper for me. Last time I tried, NotebookLM would try to say the TeX out loud. Like underscore dollarsign...
I wondered when the name change was coming as NotebookLM felt a bit out of place brand-wise. Still would have been killer if they called it "Bard Notebook"
I wondered when the name change was coming because this is Google: products be endlessly repackaged and renamed, some only to be killed later.
I wondered when the name change was coming as NotebookLM felt a bit out of place brand-wise. Still would have been killer if they called it "Bard Notebook"
I admonish Gemini and demand explanation nearly every day of how it's possible that Google invented the thing, has the best infrastructure for inference, and somehow falls behind Anthropic and even OpenAI. NotebookLM is pretty cool since it can hold a ton of context but this is so far below my (and frankly just reasonable) expectations of Google. I downgraded my Gemini subscription and got Claude. Still can't believe…
Antigravity sucks so bad that I have started to feel that google really doesn't wanna compete, they just wanna hang in there at number 2 or 3, to just annoy the number 1 and 2.