There's something magical about self-modifying software.
I'm creating my own harness, which allows customisation just with prompting. I simply point my agent to its own code and tell it what change I want, and it gets it done. It runs regression tests to ensure nothing breaks. I can build plugins for it, roll back to previous versions if I don't like something. I started with codex, but now I use my own harness to improve itself.
Makes me think about the future of open source - everyone running their custom version of a software, and agents doing intelligent merges whenever updates need to be installed.
(I know pi and dsh are also self-modifying harnesses, but they are on terminal. I'm creating a web based harness as I believe text on terminal is not conducive for deep human feedback, which is what I want to provide in order to meaningfully contribute to the final output.)
been locked in trying to set up a crude continual learning environment that I can develop into a personal continuous learning bench.
nothing works yet, but here's the plan:
- take some daily tasks that agents can do but lend themself to customisation, like daily planning.
- build an rl environment around the daily tasks
- add synthetic preferences to the environment. i.e. how i like my day planned
- get a judge model to judge traces based on preferences
- get agents to do the tasks and record the traces as buckets
- benchmark the base model on the task (LiquidAI/LFM2.5-1.2B-Instruct)
- SFT the model on the traces
- SDPO a model on the traces with a judge model hint
So far, Evals work, SFT works, but SDPO doesn't. Pretty sure that the preferences are too arbitrary, so considering manually adding more preferences to setup a better few shot judge.
Thank you guys for 800 thousand wishlists!
Milestone I of Warhammer 40,000: Dark Heresy Wishlist Goal is reached, and we're unveiling the Appearance Customisation Bundle as your next reward. Now it's time for you to shape it: vote on Discord and choose hairstyles, tattoos, and augments you want to see in the game.
Vote here:
Not in yet? Join us:
Milestone I is reached – 800 thousand wishlists for Warhammer 40,000: Dark Heresy!
While we prepare to present you with Appearance Customisation Bundle options, grab your first reward: Digital Book Event Wallpaper Pack.
Don't hesitate to wishlist the game on Steam further, more awesome rewards await!
2 Reprints of my 10 minute sketches as seen on tv for the builds on season 2 of Tex Mex Motors. To who is probably my biggest fan and car lover himself Draven Arjona! Ty Arjona Johnny Arjona
Netflix #netflixseries# #Netflix# #carseries# #drawing# #customcars# #texmexmotors#