thesandlord
Joined 12 years ago
Karma
1,079
Submissions
267
Member since
Oct 14
Recent submissions
Comment · 10 months ago
I know everyone here is telling you not to hyper optimize, but I've found drafting a prompt for an AI agent (Cursor/Devin/Codex/etc) and letting it run and then using the remaining time to do a quick body weight set (pushups, squats)
Comment · 11 months ago
New Hisense TVs have USB-C DisplayPort support. Pretty cool, but realistically I don't see how it's different from HDMI from a usefulness standpoint.
Edit: It is cool I can plug my phone or laptop into the TV with one cable, no adapters, and get some power as well. For some reason it didn't work with my Steam Deck which was strange.
Comment · 11 months ago
I remember running around campus looking for WiFi hotspots with my N810, using Google Voice to text my friends ($0.10 per text, no thank you!). Learned so much Linux admin skills that became so useful later in life. Favorite device ever! Eventually moved to Android smartphones but the ease of hacking, the amazing community (internettablettalk.com, looks like its gone now :( unfortunately...)
Comment · 1 year ago
Is this primarily for building chat based agents? What if I want to trigger a workflow via API or webhook and the wait for some sort of human in the loop verification? Do you have an example for something like that?
The visual UI + code is really cool, addresses the weaknesses of both approaches.
Comment · 1 year ago
I played all of KOTOR2 on Xbox using a capture card without sound. Good times.
Comment · 1 year ago
If you have an iPad with a USB-C port, you can use the free Orion app to do this too
Comment · 1 year ago
I've been using using [BAML](https://github.com/boundaryml/baml) to do this, and it works really well. Lets you have multiple different fallback and retry policies, and returns strongly typed outputs from LLMs.
Comment · 2 years ago
Don't do that! This was a great post with a lot to learn from.
The fact you came to a very similar solution from first principles is very interesting (assuming you didn't know about this before!)
Comment · 2 years ago
CTO here, using BAML in our stack has let us use LLMs a LOT more in places that wouldn't make sense without the type-safety. We started using it for line item tag prediction and classification, false-positive checking on our fuzzy match algo, and forecasting. Especially with models like 4o-mini and Gemini Flash, its now actually cost effective to do this at scale.
Comment · 2 years ago
What incentive would HN or YC have to do this?
Especially since they are putting out content that argues that you don't even need a business co-founder: https://youtu.be/43RhhwpiSk0?si=NMt8jLFLB9dU0TQ0
Comment · 2 years ago
In my experience, after tip Lyft/Uber are more expensive. The exception is during surges when Waymo's price shoots up like crazy.
Comment · 2 years ago
We use GPT-4o for data extraction from documents, its really good. I published a small library that does a lot of the document conversion and output parsing: https://npmjs.com/package/llm-document-ocr
For straight OCR, it does work really well but at the end of the day its still not 100%
Comment · 2 years ago
Comment · 2 years ago
I think a portion of people would say yes, it's better to keep the status quo. Imo progress always wins because eventually someone somewhere will break the taboo. Technology even gets lost and rediscovered, which means even if you supress the knowledge someone will still eventually do it. So it's pretty pointless to fight, I'd rather try to benefit from it.
If you are looking to add Accounts Payable to your B2B product, drop me a line at sandeep at merc○a d○t c○m
Prev: Eng @ Stripe
Founder @ Kbee.app / Simplemnt.com
Developer Advocate @ Google Cloud
https://twitter.com/SandeepDinesh https://medium.com/@SandeepDinesh
[ my public key: https://keybase.io/thesandlord; my proof: https://keybase.io/thesandlord/sigs/f2WVOvjTgL_9f-Z701fGoqiRtlfAavM5RzczPZjZem8 ]