Turns out not that hard.

In about a weekend, I built a UETA and ESIGN compliant tool. And it was free. And it cost me less than $50. Unlimited free e-sign. https://useinkless.com/

Turns out not that hard.

In about a weekend, I built a UETA and ESIGN compliant tool. And it was free. And it cost me less than $50. Unlimited free e-sign. https://useinkless.com/

Me being naive, I thought “how hard could would it actually be to build a free e-sign tool?”

Turns out not that hard.

In about a weekend, I built a UETA and ESIGN compliant tool. And it was free. And it cost me less than $50. Unlimited free e-sign. https://useinkless.com/

Andrew Wilkinson tweeted the other day "I just found out how much we pay for DocuSign and my jaw dropped." https://x.com/awilkinson/status/1892638803505868824

So I thought "how hard could this be?" and decided to build a free alternative that's UETA and ESIGN act compliant!

This open source library helps you mitigate errors & downtime from @OpenAI's APIs by retrying and falling back to Azure (and vice versa).

About 5 minutes to setup - syntatically the exact same as OpenAI's library.

If you need expedited access to Azure, feel free to email me - I can get you connected to our Azure account executive! (Startups with funding ONLY please!)

Hope this helps some people out there!

Comments URL: https://news.ycombinator.com/item?id=38380985

Points: 2

# Comments: 1

This open source library helps you mitigate errors & downtime from @OpenAI's APIs by falling back to Azure (and vice versa).

If you need expedited access to Azure, feel free to email me - I can get you connected to our Azure account executive! (Startups with funding ONLY please!)

Hope this helps some people out there!

Comments URL: https://news.ycombinator.com/item?id=38372856

Points: 4

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=37063744

Points: 5

# Comments: 0

If we guesstimate that every 100 customers needs 1 NVIDIA GPU (completely random guess), then that means OpenAI needs to buy more GPUs for every 100 new customers using GPT-4. The problem is there's a GPU shortage so it's hard to add more GPUs by just throwing money at the problem.

https://www.fierceelectronics.com/electronics/ask-nvidia-ceo...

For a little background, the task of “Where’s my order” structurally is answered differently than “Does your product do X?”. For the first question, we have to authenticate the user (make sure we don’t give out random order details), make API calls to fetch tracking details, and properly respond. Lots of external information is needed. For “Does your product do X?”, if it’s in the help docs, then we can easily do a retrieval to answer!

So, we had to get creative to solve these range of questions. We first realized that separating task-specific prompts (”agents”) performed better. So now we had to figure out how to classify each request and “hand it off” to the right agent. We wanted it to figure out the type of request and then follow a set of actions (we call them "agents") to solve it. It's like telling it, "Hey ChatGPT, classify this task." And voila, it slots the request into the right category, like recognizing "Where's my order?" as an order tracking request. After that, an agent specifically designed to handle order tracking kicks in.

You might be wondering, "How do you even teach ChatGPT to classify tasks?" Well, there are two main ingredients: examples and a 'chain of thought'. The first one's simple - give it a bunch of examples for each task, and it starts recognizing patterns. But the second one, that's where the magic happens.

It's like teaching a kid that 1+1=2. “Here’s how you get 2. You first start with one, add another, and end up with two.” That's the kind of logic we're trying to instill in ChatGPT. Let's say we want it to classify a request. We start by teaching it how to classify. For each classification, we help it understand the reasoning. For example, for a "Where's my order?" task, we'd tell it, "The customer is asking for updates about their order, therefore it should be classified as an order tracking request". After the classification, we guide it to formulate an appropriate response.

Using this 'chain of thought' approach, we've seen a big improvement in how well ChatGPT handles tasks.

This whole task classification thing has been a game-changer for us. It's letting us automate customer support prompts in a way that we used to do in a “hard coded” way, and we're just scratching the surface here. We're stoked to see where this takes us and the possibilities for improving customer experience.

AI, and especially ChatGPT, has crazy potential for customer support. We're on an exciting journey, and we can't wait to share more of our adventures with ChatGPT with you all.

As a shameless plug, feel free to check us out at https://www.spryngtime.com/

If you guys have any ideas or suggestions around chain of thought/agents/prompt chaining, feel free to hit me up at *[michael@spryngtime.com](mailto:michael@spryngtime.com)*. Cheers!

Comments URL: https://news.ycombinator.com/item?id=36341852

Points: 2

# Comments: 1

Ever try to remember advice from a YC podcast that's on the tip of your tongue but can’t quite remember?

Want YC’s perspective for important startup decisions?

Now you can ask “ChatYC” for all your needs! (Unofficial chatbot)

Some examples:

- What should I include in my monthly investor updates?

- Explain like Im five what pro rata means

- Should I hire a lawyer for my early stage startup?

- whats the difference between a priced round and safe?

- What is dilution? Can you explain like I am five

- any tips for traits to look for in founding engineers?

- when should I raise a seed round?

- are startup advisors valuable?

Try it out here! https://www.spryngtime.com/yc-demo

We built this as a proof of concept and to showcase a new tool we’re building: ChatGPT for customer support. We’ve started working with some partners to ingest their public docs (and previous support chats via email/Slack/Intercom/Discord/etc) to help answer customer support and onboarding questions.

Note: This bot was trained on ONLY public content from https://www.ycombinator.com/library - so it might not be able to answer all your questions. But it's a great starting point for new founders!

Comments URL: https://news.ycombinator.com/item?id=36012249

Points: 3

# Comments: 2

We went through YC W22, raised a few million in seed funding, and are now off to the races with hiring our founding team! We're looking for high energy, no-nonsense, high growth people. We have a lot of big customers (we just launched with the NFL recently! https://rarityleague.com/) and have too much work to do and not enough people!

We started Winter to help more people buy/sell NFTs. Our first product is a checkout for businesses to sell NFTs via credit card!

We went through YC W22, raised a few million in seed funding, and are now off to the races with hiring our founding team! We're looking for high energy, no-nonsense, high growth people. We have a lot of big customers (we just launched with the NFL recently! https://rarityleague.com/) and have too much work to do and not enough people!

Winter (YC W22) is building a checkout widget for businesses to sell NFTs via credit card! We make it easy for anyone to buy/sell NFTs and take their first step into the crypto world. Check us out at https://www.usewinter.com/

We were a part of the latest W22 batch and have just finished fundraising and naturally looking to hire some key team members!

Please reach out if you're interested!

We compensate competitively, are remote-first, and give great benefits (you can even help us design them!). Reach out to me with your resume at michael (at) usewinter.com and let's chat :)