Hacker Newsnew | past | comments | ask | show | jobs | submit | esac's commentslogin

This is exactly right! I'm happy people are starting to care about compounding errors, we use the sigma terminology: https://www.silverstream.ai/blog-news/2sigma

Agents are digital manufacturing machines and benefit from the same processes we identified for reliability in the real world


Silverstream | https://www.silverstream.ai/ | Founding Software Engineer, Senior Software Engineer | Full-Time | Remotely(Initially) then On-Site | San Francisco Bay Area

Silverstream is a fast-growing early-stage startup democratizing AI agents. We’re developing a cloud platform to create production-ready, in-house, browser-based AI agents. We’re at an inflection point in our growth and moving quickly. We’re in search of a passionate software engineer who will help scale our platform and influence the core technology. This position can be tailored to either a Senior Software Engineer or a Founding Software Engineer, depending on your experience and career goals.

For more details and to apply, please check the links below:

- Founding Software Engineer : https://silverstream.zapier.app/founding-software-eng

- Senior Software Engineer : https://silverstream1.zapier.app/senior-software-eng

For questions, please reach out to me : jobs at silverstream.ai


SilverStream | Bay Area / Remote | Founding engineer | Full Time

Heroku for AI agents

Drop me an email (in the profile)


Heya,

I am also interested but have not been able to find your email ID.

My email is shashank DOT personal@gmail.com and github : https://github.com/shashanksingh


Super interested in building this. I can't find an email in your profile but here's mine tarun@axra.org


hey there! can't seem to find your email in your profile


leaving mine here as well! hi@kenif.xyz


Dating, intros, chit chat Emails, bullletpoints to text CLI commands lookup, what was SO Brainstorming when I get stuck on my research


>genetic algorithms combined with RL where the genetics determine the reward function.

I have been working on this problem for years (2+ as researcher, 2 as PhD student).

The main issue is that evolution is both massively parallel and had plenty of runtime to get to human level intelligence.

The person that pushes this evolution/evolved reward point is Andrew G. Barto and his students/collaborators over the years.

Satinder Singh in particular is actively working on gradient based algorithms to find rewards (e.g. https://arxiv.org/abs/2102.06741)

> Maybe we need to frame RL goals in much more simple terms, and allow genetic algorithms to evolve their own inputs and reward functions on their own.

I was checking HN while the current iteration of this (gradient based, genetic was my master thesis) algorithm, the main complexity is figuring out:

1) What are the sub-goal e.g. grasping things 2) How to solve those goals e.g. motor control 3) How to do something useful, e.g. surviving

Balancing those three processes is the current hurdle.

For more info my email is delvermm at mila.quebec


Also, evolution isn’t trying to get to human level intelligence. It’s just one out of millions of adaptations that work, it’s recent, and it’s rare. Change Earths parameters a little over the past several million years, and maybe we don’t evolve.


It's an extremely open-ended process.


> The main issue is that evolution is both massively parallel and had plenty of runtime to get to human level intelligence.

How many entities are we talking about for substantial evolution? I know that there have been 100 billion "humans" (not that it's so clear-cut) alive, so guessing this is on the order of ~trillions of entities to simulate some evolution for (but maybe I'm really underestimating the early tail of tons and tons of microorganisms and small short-lived life that got us to this point).

Is the bandwidth of evolution that much larger than what we could possible simulate with computation, especially for a much simpler world/task than "generally survive"?


Given that a single teaspoon of soil probably has about a billion bacterial organisms in it, I suspect you're a couple orders of magnitude short.


An interesting plant growth simulator for all the Deep Reinforcement Learning people: https://github.com/YasmeenVH/growspace

The growth of the plant follows Space Colonization Algorithm which have been used for rending realistic trees in games. This algorithm is based on a cloud of points which have been inspired by the grown of tree in order to provide a certain attraction to the growing branches.


Solving Hearthstone (Blizzard) by Deep learning


SEEKING WORK | Québec-Montréal | REMOTE

Deep Learning PhD, with Full-stack experience; AI/ML consultant.

I'm looking to work on Computer Vision or Reinforcement learning, would prefer PyTorch projects.

15+ years (~10 professionally) experience of Python I've worked in Robotics, Computer Vision, NLP and Reinforcement learning.

Queries at: feeddeadbeef@protonmail.ch


physical buttons are hard to debug! emergency-only cellphone looks like the better alternative for now even if it would require me to use two phones or swap sims. It's not a life risk situation, more a (business and peace of mind) life risk situation so i don't think ~life alert could work


I forgot that definitely Android and probably iOS allow you to make exceptions to do-not-disturb mode for some contacts. Would that do it?


Take a look at particle.io. They have a super simple button that you can connect via WiFi or GSM to ifttt or twilio really easily. Sample code leaves almost nothing to debug.


Thanks for the suggestion, I didn't think of Twilio=>webook. Telegram is one of the platforms I use daily and something that would distract me but i guess you can replace it with anything else like an IRC client.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: