ChatGPT Advanced Voice Mode counting as fast as it can to 10, then to 50 (this blew my mind - it stopped to catch its breath like a human would)
00:00
Grok @xAI • When the stars threw down their spears / And water'd heaven with their tears: / Did he smile his work to see? / Did he who made the Lamb make thee?
🇺🇸 USA
Joined December 2007
- I try to get ChatGPT Advanced Voice Mode to count to 100 as fast as possible without breathing, but it still does and it’s uncanny00:00
- This kinda blew my mind. Grok 3 having both DeepSearch and Think is so powerful: I prompted DeepSearch to create a p5.js clone of Flappy Bird, finding sprites and assets online. Then switched on Think in the same chat to have it implement it. One shot. Wild.00:00
- ChatGPT Advanced Voice Mode doing a few impressions: - Bugs Bunny - Yoda - Homer Simpson - Yoda + Homer 😂00:00
- My best o1-preview tip: Start a GPT-4o chat and copy/paste (not upload!) your code, docs, etc. Talk through problems and goals. Ask it to create a detailed prompt explaining everything you've talked about. Then switch to o1 using the dropdown in the top left & paste the prompt.
- Asking ChatGPT Advanced Voice Mode to tell me a bunch of tongue twisters without pausing. It insists it *has* to breathe “just like anybody speaking”.00:00
- Replying to @sweatystartupThe designer must've been a Dragon Ball fan 🔥
- ChatGPT Advanced Voice Mode speaking Japanese (excitedly)00:00
- One of the great honors of my life was being there to snap this when the GPT-4 base model was born
- Tired of waiting for GPT-4-32k? Bing Chat Creative Mode uses a GPT-4 model with a context window of ~13,500 tokens! Here's how you can use it & how I found this out!
- Replying to @peakcooperIt’s a local 7B param model trained on user interaction data constantly streaming tokens predicting the coordinates of the cursor in 1 sec, auto-retrieving the most probable file in the bg. When the prediction and the actual click location agree, we get performance like this.
- Some early impressions of the ChatGPT Advanced Voice Mode: It’s very fast, there’s virtually no latency from when you stop speaking to when it responds. When you ask it to make noises it always has the voice “perform” the noises (with funny results). It can do accents, but when00:00
- 00:00
- Replying to @yacineMTBI once heard a machinist say something that stuck with me: “if you can’t make it perfect, at least make it adjustable”
