I have a design background as well, and I'm currently the CEO of a YC-backed startup (https://beau.to). Source: almost 3 years ago

We are working on an online tool, Beau (https://beau.to). It's a no-code tool for businesses to onboard and automate interactions with their clients. Customers use our software to collect submissions, payments, send messages and more. Source: almost 3 years ago

> Beau (YC S21) - Automate repetitive client-facing tasks - https://beau.to/, https://news.ycombinator.com/item?id=27930568 get your own name! >:[. - Source: Hacker News / almost 3 years ago

We are working on a solution for this. We will add conditional logic functionality in June. Source: about 3 years ago

It's Beau, a no-code solution to improve the last mile of customer experience: collect documents, forms, files, payments, etc. From clients as well as guide them through the business processes, step-by-step. Source: about 3 years ago

How does this compare in terms of latency, cost, and effectiveness to jsonformer? https://github.com/1rgs/jsonformer. - Source: Hacker News / 11 months ago

I'm not sure how this is different than: https://github.com/1rgs/jsonformer or https://github.com/mkuchnik/relm or https://github.com/Shopify/torch-grammar Overall there are a ton of these logit based guidance systems, the reason they don't get tons of traction is the SOTA models are behind REST APIs that don't enable this fine-grained approach. Those... - Source: Hacker News / 11 months ago

You're correct with interpreting how the model works wrt it returning tokens one at a time. The model returns one token, and the entire context window gets shifted right by one to for account it when generating the next one. As for model performance at different context sizes, it's seems a bit complicated. From what I understand, even if models are tweaked (for example using the superHOT RoPE hack or sparse... - Source: Hacker News / 11 months ago

From here, we just need to continue generating tokens until we get to a closing quote. This approach was borrowed from Jsonformer which uses a similar approach to induce LLMs to generate structured output. Continuing to do so for each property using Replit's code LLM gives the following output:. - Source: dev.to / 12 months ago

Https://github.com/1rgs/jsonformer or https://github.com/microsoft/guidance may help get better results, but I ended up with a bit more of a custom solution. Source: 12 months ago