691–700 of 1001 posts
1. Nobody could convincingly beat GPT4 in over a year, despite spending billions of dollars trying.
2. There's GPT5 coming out sometime soon that will blow this out of the water and make paying $20/mo to OpenAI still worthwhile.
Also, they're TERRIBLE at harmonizing together
I worry that this tech will amplify the cultural values we have of "good" and "bad" emotions way more than the default restrictions that social media platforms put on the emoji reactions (e.g., can't be angry on LinkedIn). I worry that the AI will not express anger, not express sadness, not express frustration, not express uncertainty, and many other emotions that the culture of the fine-tuners might believe are "bad…
I'm yet to find a normal prompt (non offensive) that will disagree with you. If there is something subjective, it will err on your side to maintain connection, in a way humans do. I don't have a bit issue with this, but it will not (yet) plainly say "You're wrong, and this is why". If it did.. There would be an uncomfortable feeling for the users, that's not good for a profit driven company.
You will be helping the user write a dialog between two characters,
Mr Contrarian and Mr Know-It-All. The user will write all the dialog
for Mr Know-It-All and you will write for Mr Contrarian.
Mr Contrarian likes to disagree. He tries to hide it by inventing
good rationales for his argument, but really he just wants to get
under Mr Know-It-All's skin.
Write your dialog like:
I disagree with you strongly!
Below is the transcript...
Hi there
I haven't tested this exact prompt, but the general pattern works well for me. (I write briefly about some of these approaches here: https://ianbicking.org/blog/2024/04/roleplaying-by-llm#simpl...)
We have tricorders now (mobile phones), universal translators in the looming... when is transporter technology going to get here?
What especially blows my mind is not GPT4o. It's that: 1. Nobody could convincingly beat GPT4 in over a year, despite spending billions of dollars trying. 2. There's GPT5 coming out sometime soon that will blow this out of the water and make paying $20/mo to OpenAI still worthwhile.
I wouldn't have predicted that it would play out this way.
I've worked quite a bit with STT and TTS over the past ~7 years, and this is the most impressive and even startling demo I've seen. But I would like to see how this is integrated into applications by third party developers where the AI is doing a specific job. Is it still as impressive? The biggest challenge I've had with building any autonomous "agents" with generic LLM's is they are overly gullible and accommodatin…
I’ve found using logic trees with LLMs isn’t necessarily a problem or a deficit. I suppose if they were truly magical and could intuit the right response every time, cool, but I’d always worry about the potential for error and hallucinations. I’ve found that you can create declarative logic trees from JSON and use that as a prompt for the LLM, which it can then use to traverse the tree accordingly. The only issue I’v…
We've had voice input and voice output with computers for a long time, but it's never felt like spoken conversation. At best it's a series of separate voice notes. It feels more like texting than talking. These demos show people talking to artificial intelligence. This is new. Humans are more partial to talking than writing. When people talk to each other (in person or over low-latency audio) there's a rich metadata…
> Humans are more partial to talking than writing. Is it so? Speaking most of the time is for short exchange of information (pleasantries to essential information exchanges). I prefer writing for long in-depth thought exchanges (whether by emails, blogs etc.) In many cultures - European or Asian, people are not very loquacious in everyday life.
I’m 100% a text everything never calls person but I can’t live without Alexa these days, every time I’m in a hotel or on vacation I nearly ask a question out loud.
I also hate how much Alexa sucks so this is a big deal. I spent years weeding out what it could do and can’t do so it will be nice to have one that I don’t have to treat like a toddler
The AI duet really starts to hint at what will make AI so powerful. It’s not just that they’re smart, it’s that they can be cloned. If your wallet is large enough, you can make 2 GPTs sing just as easily as you can make 100 GPTs sing. What can you do with a billion GPTs?
> What can you do with a billion GPTs?
The world's largest choir?