esac

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 | 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)

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

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: [email protected]

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

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.

I think i'm about to follow your academical steps, can i ask you a few questions by mail? (the one i found is for an (ex?) UC professor)

I'm pretty sure the bottleneck is disk I/O and not the CPU

do you have something? i was going to write the very same extension (but distributed so i could add it to my pc and my friends) but never did that

the prize 25k is not relevant since most of the equipment can be taken from a sponsor and the participants are mostly universities, which means that every single cost is paid either by a sponsor or by amazon, we entered last year and ended up paying a total of 250€ for 5 members

personally i love the fact that this competition exists even if only to push research in the field

I'm not against helping people with tickets and allowances, after all that's the whole point of scholarships isn't it?

But I do understand why many Italians are so upset about the amount.

I worked for two years (and paid my share of taxes) to finance my studies I don't understand why you assumed I don't pay taxes.

>are likely to spend everything in local shops

same goes for scholarships, actually more because we don't have families outside the EU

160€/mo rent 15€/mo utilities 5€ other stuff the house is shared with 4 guys, two bedrooms

(Turin so yea it's a little cheaper)

as an italian student living on 12€/day which covers rent and bills (6€), food (4€) coffe to study after dinner (0.5€) and unexpected expenses i wonder how those 35€ and for the first time i understand why people are angry at immigration.. (we didn't get scholarships for 2 years because of the lack of money)

the ones where the losers can't voice their discontent over the media

you answer mails aswell?

ROS, ROS, ROS all our robots are on ROS and you get visualization and simulation tools, 90% of the things you'll ever need come from apt-get (ubuntu make everything easier) but the real deal is Gazebo and stage for simulation and the wiki is full of tutorials

In my country (Italy) 400€ is 1/3 of the monthly wage for a junior developer

Wouldn't another stereotype be degrading for the other group ?

thanks for the link!

I feel like I wouldn't trust the devs there, unless i can verify/get to know them physically outside it would feel like throwing money in the wind and hoping it works

That's why I felt that reputation should come from status/community, as a developer I don't want to be untrustworthy with my university/oss/friends/peers and as a employer i want to be able to exert social pressure on the developer in case things don't go as expected.