Maybe. I'm just spitballing but as I've been thinking about this, maybe just like a set of shell scripts.
The idea could be that the agent runs as a unix user. That user has execute access to these scripts but not read or write access.
So the agent can only do what those scripts allow, the scripts present an API. You could let agents call the scripts with -h to get instructions, and just put some text into context saying like "to access helper scripts call ./showHelp".
Still not useful enough for me and I really want this feature!
The problem I encounter is the inability of the LLM to look stuff up and respond to me. "What's that name of that database table?" "What are all the services that call this endpoint?" "Are there any open PRs for this repo right now?"
Once information can flow in both directions not just one it will be a gamechanger for me.
Or do you want it to speak to you too? I think this would have to be TTS on your phone. You can have ChatGPT speak to you but I don't see that feature in Codex.
Sure I speak to ChatGPT all the time and I've used the feature you've linked but it can't do the things I described. It won't be like, "hey let me go look into that" and then come back in 3 minutes with an answer. It's essentially a dictation feature.
I hear a lot of praises. Can you explain? If I can type as fast as I speak, does that still matter in such case? Does it make use of intonation or is it pure speech to text?
For me it's because I've been walking 10-20k steps per day on a walking pad at my standing desk while working.
I can still type while doing it but it's so nice to just hold a button (or double tap to lock recording) and just brain dump what I need.
I type very fast but I feel like the unaltered speech to text allows me to express more quickly any uncertainty or doubt that I have or when I don't know exactly how to best ask for what I want.
I also like to play dumb with agents and ask it for the best option for something that I already know the answer to, just to see if it's gonna be correct, it helps get a sense of the limits of each model. That's also quicker on voice.
I don't think it makes use of intonation for the built in one, I use Hex on mac for speech to text
These cloud LLMs are not the tool for you then I suppose. There are local models too, unless your point is why use LLMs, in which case, you don't need to.
Curious how HN is using this information to plan your investing approach. Does the typical approach, broad market globally diversified still hold assuming dedollarization?
TandemAI | Senior Front-End Engineer | HYBRID in New York City | https://tandemai.com
TandemAI is focused on lowering the barrier to entry to the most advanced tools in drug discovery. We designed our fully integrated pre-clinical drug discovery platform to empower researchers to discover therapeutic candidates faster and more efficiently.
What You'll Do: Develop highly specialized drug discovery interfaces. These are data-intensive applications that are highly interactive and allow researchers to launch and analyze simulations right from the browser.
Must-Haves: Fluent in English. Proficiency in React. Some knowledge of Chemistry (i.e. you should know what the difference is between a stereoisomer and a tautomer)
Send a message with title "HN Senior Front-End Engineer" to frederick dot parsons at tandemai dot com
TandemAI | Senior Front-End Engineer | HYBRID in New York City | https://tandemai.com
TandemAI is focused on lowering the barrier to entry to the most advanced tools in drug discovery. We designed our fully integrated pre-clinical drug discovery platform to empower researchers to discover therapeutic candidates faster and more efficiently.
What You'll Do: Develop highly specialized drug discovery interfaces. These are data-intensive applications that are highly interactive and allow researchers to launch and analyze simulations right from the browser.
Must-Haves: Fluent in English. Proficiency in React. Some knowledge of Chemistry (i.e. you should know what the difference is between a stereoisomer and a tautomer)
Send a message with title "HN Senior Front-End Engineer" to frederick dot parsons at tandemai dot com
A front end is simply an application that talks to a different application to receive its data instead of processing it directly. It can be as threaded as you like.
My team is currently using this and I've been wondering if there are reasons to move to something like jotai or Zustand. The ergonomics of react-hooks-global-state with TS is quite nice already.
Tandem AI is an advanced technology company dedicated to reinventing drug discovery infrastructure. The company integrates proprietary AI-driven, high-performance computation with its efficient, large-scale in-house wet lab operations to deliver a turnkey drug discovery solution.
We are looking for a Senior Engineer to join our growing Web Applications team. You will actively contribute to back-end and front-end initiatives for our cutting-edge computational platform with a focus on back-end. The candidate, will work to create a state-of-the-art client-facing molecular design web application that seamlessly integrates the Tandem AI molecular dynamics-based computational platform.
Our stack is React 18, Java Spring Boot, PostgreSQL and we use Slurm to manage our HPC jobs.
If you have a science background and strong engineering skills this could be an exciting opportunity for you!
If you're interested feel free to email me with subject "Hacker News TandemAI" directly at frederick [dot] parsons [at] tandemai [dot] com
