Built a podcast clipping app with Inkling from @thinkymachines β¨
The model is exceptional at reasoning over long-form audio - so I have it listen to full episodes and direct FFMPEG on which clips to cut.
You can have it choose the best moments or search for specific topics π
Netflix's CEO revealed that the company has already used AI in production across 300+ titles.
In many cases, gen AI tools were used for "key shots" that would've been left out due to cost.
And they just released a documentary with 17 minutes of AI-enhanced footage.
I've tested a bunch of podcast clipping tools - but they typically convert the audio to a transcript first.
Inkling natively understands the audio input, so it can use verbal cues like vocal emphasis, emotion, and speech cadence to decide what to clip.
Makes a big difference!
Big news: Kimi-K3 by @Kimi_Moonshot is now #1 in the Frontend Code Arena with 1679 pts, surpassing Claude Fable 5.
This is a 17-place jump from Kimi-k2.6 (#18 -> #1).
In Frontend, Kimi-K3 ranked #1 in 6 of 7 domains: Brand & Marketing, Reference-Based Design, Data & Analytics, Consumer Product, Simulations, and Content Creation Tools, landing #2 only in Gaming behind Fable 5.
The full model weights will be released by July 27.
Congrats to the @Kimi_Moonshot team on this major milestone!
I've tested a bunch of podcast clipping tools - but they typically convert the audio to a transcript first.
Inkling natively understands the audio input, so it can use verbal cues like vocal emphasis, emotion, and speech cadence to decide what to clip.
Makes a big difference!
@thinkymachines Full app was built in @cursor_ai.
It does the following:
(1) Download YouTube vid + convert to WAV
(2) Split long audio into batches
(3) Inkling reasons across audio + proposes candidates
(4) Correction pass checks that each one starts + ends in right place
(5) FFMPEG renders
The headline is very good, "How Town Became Silicon Valley's New Favorite AI Tool", but what I am most proud of is that people everywhere are getting so much value of the product.
https://t.co/8XlxdA62V9
From a user who took his first vacation in a while because of Town: "Itβs given me the ability to walk away from my emails. β¦ Weβre still hitting targets and making our budget without me β¦ being there."
@MickC_1 They def still make mistakes but I've found (at least for what I'm doing) that they no longer continuously insist nothing is wrong when there are clearly bugs...they're better at actually investigating + implementing solutions
Nine days ago, someone asked the LLMs to predict who would win the world cup.
Fable was the only one that predicted France would get knocked out and correctly guessed the two finalists π€―
ChatGPT, Qwen, and Kimi each got one of the finalists.