kjcodes_
756 posts
kjcodes_
@kjcodes_
exploring RL ∩ Continued Learning | building the local-first CLI for RL experiments
Katılım Temmuz 2020
388 Takip Edilen180 Takipçiler
Reinforcement learning has libraries.
What it’s missing is workflow discipline.
Shipping RLCLI today.
1. Local-first
2. Reproducible
3. Built for real experiment iteration
GitHub: github.com/KJ14GOD/rl-cli
Install: pypi.org/project/rlx-wo…
English
if you're an independent researcher and need
- compute
- tokens
- travel stipends
- any other resources
DM me! hillclimb grant releasing soon😁
Mariya I. Vasileva@mariyaivasileva
My fellow researchers — an open question for everyone: what short-term research project grants do we know of that support scientific agendas aimed at progress on long-horizon problems, especially open-source work, and are accessible to researchers outside academia?
English
Good friend at uni is working at SIG as a QSD this summer while I'm scouting Day 3 OLinemen #ok
English
T3 Code is now available for everyone to use.
Fully open source. Built on top of the Codex CLI, so you can bring your existing Codex subscription.
English
my side project got me my dream research role btw
sachin.@sachinyadav699
> clock in 9–5 daily > come home > open laptop again > “this AI side project will change my life” few months later… >realize you’re just doing overtime for free > training models > paying $200/month for the privilege escaped the rat race entered the compute race
English