AFAIK people drop their bank statements to their agent chats
57 karma · joined January 11, 2018
I am using Replicate to run docker images with a pipeline based on faster-whipser, VAD, pyannote and a custom LLM enhancement flow.
Thanks for sharing candle/ort. Interesting to see the WASM in-browser opportunities
What led you to choose Leptos for the frontend besides the shared code advantage?
How would you expect to get an understanding of the backlog? Would a dedicated page for the entire backlog be helpful, or would you prefer to see which episodes are being transcribed on each podcast page?
Any insights on what would be most helpful for you would be greatly appreciated!
Once you grasp Rust's concepts, you'll find the control and efficiency rewarding. It's worth the effort!
The LLM pipeline is built into the Rust code and makes calls to the OpenAI API.
We hit the front page on Hacker News and received many submissions, which led to network errors when fetching some podcasts. I've just added retry logic and scheduling for new podcast fetches and pushed these changes to production.
The Criminal[1] podcast is now added. Due to the current demand, our transcription queue is a bit backed up, so transcription for this podcast will appear in a few days. Please be invited to have a look the next days again.
I'm actively working on securing more GPUs to help scale this process efficiently so in the future you don't have to wait that long.
Would it be interesting if I add e-mail "transcription ready" notifications for those who submit a new podcast?
Folders often just add an extra layer to search through. It's basically a search param. With Neovim and strict naming conventions, I've found managing everything in one file works quite well. Keyboard navigation can make folders feel like a hassle in the vi context. This setup has been effective so far, though potential downsides might appear later on.
As for backups, the setup is straightforward: just periodically copy the SQLite file to a secure location. Since it's a single binary and a database file, this keeps things simple and low-maintenance.
Some people used the share feature of Audioscrape to emphasize their points in discussions on X. For example, 'Here, this is what Zuckerberg said recently about Y <Link to moment>'
While we currently have fewer users, I've also found Rust's type safety and robust system invaluable for building reliable software. In my experience, if it compiles, it just works—quite a contrast to dealing with runtime error minefields in Python, Java, or TypeScript.
The first version will be available for early sign ups in January 2024.
Very friendly and down to earth personality. He said that Nvidia had tough competition when he started (there was only on chip graphics acceleration in 1994) and literally no market for his product because no applications/games supported external graphic acceleration. Still, he and his team were convinced that general purpose computing (CPUs) for everything is not as good as providing a dedicated, specialized computing unit (in this case for graphics). So they just built it and made it. Even though they were nearly bankrupt for multiple times, they survived until 2023 and established themselves as a leader in their field.
He basically worked on this for 30 years. Not many founders show the same endurance.
I couldn’t reproduce what has been described in the article. For example it is able to find the results of the FIFA World Cup outcomes.
But same as with GPT3 and ChatGPT, you can define the context in a way that you might get weird answers.
Interesting how many here took early conclusions, especially many writing that it’s the fault of Elon.