Viewing profile — vishnumenon

Yeah I've been using it with prompts that ask it to cite sources as well, honestly I think the best results are when I'm still interacting w/ the docs directly in addition to havin…

My current hypothesis here is that the way to make coding assistants as reliable as possible is to shift the balance towards making their output rely on context provided in-prompt …

I've been working on Lightrail for a couple months now, just added gpt-4-vision-preview support and figured it was as good a time as any to do a Show HN. It's still very rough arou…

The Magical Japanese Art of Luggage Forwarding: https://craigmod.com/ridgeline/170/ (iirc this was on HN front-page a day or two ago, which might be why its top of mind)

Not the GP, but I've been working on an open platform [0] for integrating OpenAI APIs with other tools (VSCode, JupyterLab, bash, chrome, etc) that you might find interesting, the …

Seems similar in spirit to Nushell[0], which is a project I'm really rooting for, a super interesting update of the shell/pipes framework [0]: https://www.nushell.sh/

Lightrail: https://github.com/lightrail-ai/lightrail Basically, I think that LLMs will enable a whole new set of app UXes, and I'm trying to build a platform for those UXes. In a s…

Author of the piece, and I... can't really argue with any of this, tbh. I'll admit both those parts you called out were probably heavily tinged by my own desires, and your more-sob…

OP here, as someone who does love cooking, I've gone down this route pretty heavily in the last few years - been growing my collection of physical cookbooks and definitely enjoy fl…

I'm the author, and I don't disagree with this at all - I do use LLMs pretty meaningfully in my day-to-day engineering work, and I definitely agree that they hold a ton of promise …

Love it! Reminds me of the hilarious "Typing the technical interview" [1] and "Typescripting the technical interview" [2], a couple of my favorite blog posts of all time. [0] https…

I've wanted exactly this for quite a while, awesome project! do you plan to keep it free? Or is functionality going to paywalled soon?

Thanks! I actually initially had it doing transcription in 5- and 10-second chunks for close-to-realtime results, but the CPU usage on my laptop (which admittedly doesn't have the …