Some months ago, I saw a tweet from @awilkinson: “I just found out how much we pay for DocuSign and my jaw dropped. What's the best alternative?”
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/
A few months ago, I saw a tweet from @awilkinson: “I just found out how much we pay for DocuSign and my jaw dropped. What's the best alternative?”
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/
A couple of months ago, I saw a tweet from @awilkinson: “I just found out how much we pay for DocuSign and my jaw dropped. What's the best alternative?”
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/
Stemming from OpenAI's APIs being down the last few days (and us being down subsequently), we launched an open source OpenAI + Azure fallback and retry tool: https://github.com/Spryngtime/openai-load-balancer
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!)
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.
Hey everyone, I wanted to share how we've been scaling our prompts with classification! For context, we build “ChatGPT for customer support” and our AI-based customer support system has to handle all sorts of questions ranging from "Where's my order?" to "Does your product do X?" As our range of support questions increase, we can’t just keep adding more instructions onto a huge, “mono prompt”.
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.
If you guys have any ideas or suggestions around chain of thought/agents/prompt chaining, feel free to hit me up at *[[email protected]](mailto:[email protected])*. Cheers!
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 :)
I might be totally wrong, but isn't this a good way to get orphaned processes? Kill the parent arbitrarily with SIGTERM (I don't think this automatically cleans up the children/forked processes) and viola, you've got an orphaned process.