103 karma · joined March 22, 2022
That's my way to say I too built an orchestrator like this and reached into a similar flow. Personal use only but now I'm considering publishing it somehow.
Apart of the operational challenges mentioned in the article, of course, making it happen isn't trivial, it has costs as well.
Including to serve.
For everyone else, chains.
Last year I started using it as a copilot and in the second semester I started building AI/LLM based sales and marketing systems that now are most of my income.
I'm becoming one of those "and this is just the beggining for AI" enthusiasts :P
Remote: Yes
Location: Brazil
Willing to relocate: No (Remote only)
Technologies: Custom AI systems from scratch, SvelteKit, Azure functions, Netlify functions, AWS Lambda, Node, Docker, Appwrite, Caddy, HTML, CSS, JS.
Generalist web developer.
Email: vini.britox@gmail.com
Remote: Yes
Location: Jobs worldwide, I'm from Brazil
"Time to kick off that new priority in your company!"
Web developer, mainly frontend and application logic, with basic infra and backend skills to get my work online.
Examples:
AI systems from scratch (no Langchain and similar), Interactive app screens, PDF generators, payment processing, maps and routes, VoIP, browser extensions, SFTP server client and more.
Stack: SvelteKit, Microsoft Azure functions, Netlify functions, AWS Lambda functions, Node, Docker, Appwrite as a full backend (Supabase alternative), Caddy as a front door (Nginx alternative).
Reach out to me vini.britox@gmail.com or just reply here.
That's us, developers. That will never change. We're the ones dedicated to it.
Execs, managers, HR, salesmen, designers etc won't suddenly want to spend their whole days, not even half of their time, tinkering with a computer so it can do what they want.
Else Basic and Fortran would have made everyone software developers.
Do you feel calmer now? (:
Lasts for a few months.
How would this be zero sum?
Now, I'm open to the idea that I am just using it wrong, but I have seen several reports around the web that the most that people got in tool calling accuracy is 80%, which is unusable for any production system, also for info retrieval I have seen it lose coherence the more data is available overall.
Is there a model that actually achieved 100% tool calling accuracy?
So far I built systems for that myself, surrounding the LLM, and only like this it worked well in production.
No need for new protocol or anything like it, just a convention, as you mentioned, similar to robot.txt.
Perhaps aidata.json.
I'm tired of losing sales due to that. And clients needing to increase their costs massively due to that.
Remote: Yes
Location: Jobs worldwide, I'm from Brazil
"Time to kick off that new priority in your company!"
Generalist web developer, mainly frontend and application logic, with basic infra and backend skills to get my work online.
Examples:
Interactive app screens, PDF generators, payment processing, maps and routes, VoIP, browser extensions, SFTP server client, AI systems and more.
Stack: SvelteKit, Microsoft Azure functions, Netlify functions, AWS Lambda functions, Node, Docker, Appwrite as a full backend (Supabase alternative), Caddy as a front door (Nginx alternative), HTML/CSS/JS.
Reach out to me vini.britox@gmail.com or just reply here.
Remote: Yes
Location: Brazil
Willing to relocate: No (Remote only)
Technologies: SvelteKit, Azure functions, Netlify functions, AWS Lambda, Node, Docker, Appwrite, Caddy, HTML, CSS, JS. Generalist web developer.
Email: vini.britox@gmail.com