Viewing profile — social_quotient

Would be curious about the model and the prompt for this. Not kidding at all. I had a similar issue with a project where I needed to classify images into specific demographics, and…

Hey your dates are wildly wrong... It’s important people know aider is 2023. 2 years before CC

I’ve run millions of jobs on MTurk. For a major mall operator in the USA, we had an issue with tenants keeping their store hours in sync between the mall site and their own site. S…

For the oldest… The primary driver for us was realizing that most alternative learning models just don’t align well (maybe id say incompatible) with the structure of college/higher…

There is an internal financial aid. I don’t know the qualifications for it but I know it’s used extensively. What’s wild.. at Alpha. Money is no issue or object of discussion other…

So here’s part of the trade-off to consider: (great questions and thinking btw you’d be surprised by the number of people that treat education as day care… even at a 40k per year s…

A couple of thoughts based on my own experience, as both of my girls attended Alpha for 4 and 5 years. First, not all the students come from wealthy backgrounds, which is a common …

I’m reminded of this story https://terminalbytes.com/iphone-8-solar-powered-vision-ocr-... 83,418 OCR requests processed over more than a year of operation Up to 1,000+ requests on…

Exactly! You can use tools like https://github.com/musistudio/claude-code-router which let you use other LLMs. The way I would use this $50 Cerebras offering is as a delegate for s…

Unrelated, but this reminds me of a persistent headache on Windows. My screensaver refuses to kick in, no matter what. After tumbling down a rabbit hole longer than I’d care to adm…

Yeah I get that, I’m not “stuck” it’s that I don’t think the comms make sense and it’s troubling none of these teams have figured out a pricing model that isn’t a rug pull. If all …

I love Claude Code, but Anthropic’s recent messaging is all over the map. 1- “More throughput” on the API, but stealth caps in the UI - On Jun 19 Anthropic told devs the API now su…

Runpod is worth a look for these on demand workloads https://www.runpod.io/pricing I use a lot for ffmpeg workloads. Found this a few days ago which might be neat for finding cheap…

Yeah, I think a couple of points here: 1. Inference time is not training anything. The AI model has been baked and shipped. We are just using it. 2. I’m not sure “gaslight” is the …

I should note, some of this falls apart in the new multi modal world we are now in , where you could ask the llm to print the secrets in an image/video/audio. My similarity search …

I have not found a way yet, even conceptually, and in our case the extra layer comes at a cost to the ux. To overcome some of this we use https://sdk.vercel.ai/docs/reference/ai-sd…

I think you’re spot on! We’re using a similar trick in our system to keep sensitive info from leaking… specifically, to stop our system prompt from leaking. We take the LLM’s outpu…

I spend a ton of time in FFmpeg, and I’m still blown away by how it uses abstractions to stay modular—especially for a project that’s been around forever and still feels so relevan…

Cool comment, got me thinking a bit and I’d like clarity if you don’t mind. Sorting in a GET request param doesn't alter the server's state. It only changes the data representation…

Concat to a file but it helps to make an ascii tree at the top and then for each merged file out its path and orientation details. I’ve also started playing with adding line ranges…

I found myself thinking about Cloudflare Durable objects new SQLite offering. Nicely detailed here https://simonwillison.net/2024/Oct/13/zero-latency-sqlite-st... And https://devel…

Good job on the launch and the write up. I'll be interested to play with this api. I'm glad to see the ttft talked about here. As someone who's been deep in the AI and generative A…

Would love if you could de identify and share a bit more detail on a prompt that big.

I’d be curious if people really ever switch from ffmpeg and if yes, what to?

With query expansion do you find it needed for ux purposes to tell the user what you have done to their original query? or do you just run with it and let the result interactions s…