Hey Guys!
I’ve been getting some pretty solid consulting gigs that pay higher than anything I’ve ever worked on before. I’m guessing some of you have also gone through this.
I think where I lack most is the more technical coding side of things. I’m pretty strong on the prompt engineering front.
Anyone interested in potentially partnering together on some projects? (Both prompt engineering, and coding). Would love to chat!
Those kinds of requests generally work better if you are more specific.
A particular area of the world? (“Western Europe” …)
A particular area of a country, even? (“Scotland” …)
A particular area of business? (“enterprise” vs “marketing” vs “government” vs …)
A particular scope/size of business? (“day-long consultations,” “two-week projects,” “year long efforts,” …)
A particular range of payment? ($50/hour? $500/hour?)
And what, in particular, are you looking for?
I think anyone is “interesting in partnering” for the right situation, but the “right situation” looks very different for different people.
I would love to however I am completely new to this but obsessed with the prompt engineering side of things. I want to get into the consulting but have no idea how to even get in to it…
I’d be interested in ways of collaborating. We probably need a Matrix Room or a Discord Room where we can discuss. Probably this OpenAI server is not appropriate for non-OpenAI related stuff, or just doing our own business collab. Want me to create a Matrix room? I had already looked for the place AI devs were hanging out, on Matrix or Discord and didn’t really find it.
I have Python and web application (HTML, sql, etc.). what are you looking for? I did couple things with the Open AI API like embeddings, fine-tuning, instruction-based prompts. Outside of Open API programmed few models from scratch to learn and compare.
I’m in… Would be nice to have a place to discuss
I just created ai-devs room, so anyone can join.
Well, what I have is an actual application. It’s a full CMS with AI chat capability (using OpenAI models) built into it. The proposal I made for it is here: https://youtu.be/qgKiXYP8UBs
It was already half-built when I made the proposal, so I ended up just finishing the thing myself. It’s first iteration, currently in beta, is here: https://ca.RealEstateBooksAI.com. This is basically the “proof-of-concept” site which happens to focus on CA real estate law, but the platform on which it is built is designed for any medium to large business or government entity seeking to embed hundreds or thousands of documents in a fully managed RAG system.
So, if you are consulting with a client who can use this type of application, hey, yeah! Personally, I don’t want to consult. Been there, done that. I’d rather work with consultants and focus my time on improving the system. Right now, unless I can get a deal with the CA DRE, I’ve got to go out and sell this thing myself – something I’m not looking forward to. So, working with people who want to handle that end-user part of it is music to my ears!
Looks like you put together a cool solution with using Solr. I’ve tinkered a lot with Solr and Lucene in the past. I’m sure the Solr team is really excited about AI tech, and will built it into their codebase, because it’s such an obvious fit.
I haven’t done any vector-based semantic search yet, but I understand how it works, and I can definitely see how a legal and real-estate database full of semantic searchable docs will be very useful to the industry. Nice work!
Thanks. Solr vector search was available when I got started on this Dense Vector Search :: Apache Solr Reference Guide, but I didn’t use it because it didn’t have dimensions compatible with the OpenAI model I was using at the time.
I don’t know if that has improved, but even if it has, I will probably stick with my current architecture which utilizes the Weaviate vector database. I mean, they’ve got this thing down to a science – low latency, super fast results, a text2vec transformer specifically for OpenAI models that increases the efficiency of the searches, hybrid ( BM25) search option, hybrid alpha slider to determine the mix of bm25 vs. semantic search, etc… I can go on and on singing their praises. I almost always get back the correct context documents with minimal effort on my part, leaving me to focus on adjusting my model prompts.
Why would I want to even think about building all of that myself?
Hi Chris,
I’m interested, I have 3 years of experience as a ML Developer.
Thanks,
Ramon
Hi Chris5,
I am very strong on the coding side. I took Andrew Ng’s Deep Learning specialization a few years back and am now immersing myself with LLM AI tech. I would love the idea of partnering. We could teach each other.
Let me know
Bart (bjenkins@am-mc.com)
If you are a good prompt engineer, you should try out my plugin, Recombinant AI. You won’t need anyone to code for you. It’s my attempt at a conversational IDE. Sort of an alternative to things like Copilot and Ghostwriter, but on Chat so it’s far more intuitive for newer coders/pair-programmers
Hey Chris,
I am definitely interested in it. Specifically, I have been consulting/developing around the API and plugin stuff. I avoid the finetuning work though. Hit me up on LinkedIn/DM. I’ll shoot you a resume if you are interested so you can see if it is an appropriate skill set you are looking for.
I’m PST based out of Las Vegas but I am working with teams all over the world right now. Mostly Vietnam, Hong Kong, a couple of countries in Europe, and an American and Polish University. They all have American clients/partners though.
Open to working with other as well. Just hit me up.
I suggest we create one and form a community to collaborate and support ourselves.
I’ve been finding the same! There’re are a lot of companies needing LLM experts right now.
Hey Chris,
I’d love to hear more about this and have been looking for opportunities to break into AI consulting. I’ve done quite a bit of consulting over the year, let me know if we can chat!
Caleb
I am playing with prompts via the api with 3 use cases. One of the use cases is on the pricing side. I would be interested in talking to people tinkering with ChatGPT api and/or prompts.
Hey Chris,
I’d love to. Your experience could complement mine. I have built 3 generative AI apps powered by OpenAI’s gpt 3.5, gpt 4, and langchain. Here’s one that’s publicly accessible earningssummary dot com and the demo can be viewed by using this youtube video id 6u5fDEK0ZTQ (sorry can’t include links)
I’m an ex-SWE at Meta (Facebook) and Cornell grad. Here’s my Linkedin Chris Bora
Chris
Hi Chris,
Great to hear that you are getting inbound requests for your content.If you can throw more light on the programming expectations or requirements it will help. Hope they don’t want to become Tony Stark.
-Regards,
Kiran