Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

here we go… open sourcing the $pippin framework! for launching digital beings like pippinlovesyou - character config - reusable and dynamic skills via - activities w/ cool down, etc - memory mgmt here’s a ~4 min super cut of the live demo github & more 👇

247,286 Aufrufe • vor 1 Jahr •via X (Twitter)

14 Kommentare

Profilbild von Yohei
Yoheivor 1 Jahr

github: quick background: @pippinlovesyou the unicorn is a digital being operating 24/7, taking naps, going on walks, and occasionally communicating w the human world during a winter break refactor, decided to open source as a framework.

Profilbild von Yohei
Yoheivor 1 Jahr

core loop is activity selection and execution, which kicks off after configuring your character and choosing an LLM (and adding api key) auth into composio tools for dynamic skills or add your own in the skill folder. then build activities that use these skills!

Profilbild von Yohei
Yoheivor 1 Jahr

onboarding wizard will ask you for core character name, objective, your default LLM choice, an api key for it. will also ask which activities you want to enable. default activities are examples for you build off of.

Profilbild von Yohei
Yoheivor 1 Jahr

you will see skills from the skills folder listed in the overview page (manual skills), and after auth’ing into composio tools - you will see all actions related to the tool show up (dynamic skills)

Profilbild von Yohei
Yoheivor 1 Jahr

activities can use both manual and dynamic skills (see examples activities for how), and you can set a cool down period to ensure certain activities don’t happen too often (eg tweet once an hour, post one podcast a day)

Profilbild von Yohei
Yoheivor 1 Jahr

the history tab allows you to monitor frequency, input, and output of activities. helpful for monitoring unwanted activity usage or debugging.

Profilbild von Yohei
Yoheivor 1 Jahr

api key tab is where you can add manual api keys (for manual skills, where required keys are defined in skill config file), or see a list of all 250+ composio tools and auth in (oAuth/API keys/etc depending on the tool) (some composio skills don’t work yet, but working w @composiohq team to get them working)

Profilbild von Yohei
Yoheivor 1 Jahr

once you have objective/skills/activities in place, let your digital being run! now that this is out, i’ll be migrating @pippinlovesyou to this so i can automate podcasts and more :) (and through usage, we'll figure out how to evolve this)

Profilbild von Yohei
Yoheivor 1 Jahr

the experimental self-building activities need more work, so i’d suggest ignoring for production (might move to a different folder) - but for those who love challenges, i dare you to get it working 😉

Profilbild von Yohei
Yoheivor 1 Jahr

of course there’s lots more to add, such as a separate skill/activity repository (we want to keep core framework lightweight) we’ll be building this out publicly on github along w the awesome community devs who have already helped so much 🙏

Profilbild von Yohei
Yoheivor 1 Jahr

lots of ppl have reached out wanting to build on or partner with the framework, and all of these are welcome! share your project if it’s built on or inspired by the Pippin framework in anyway, so we can build a library of iterations and new approaches.

Profilbild von Yohei
Yoheivor 1 Jahr

I’m sure some ppl will want help with the framework and i have ai dev friends looking to explore web3, so looking into ways for you to use $pippin to get these built - onboarding more devs into our community (pippin, and solana at large) *more on this was discussed in livestream

Profilbild von Yohei
Yoheivor 1 Jahr

still getting a discord set up for the dev community, will share shortly. in the meantime, hope you enjoy playing w the framework, drop ideas/thoughts/feedback in the replies! (and also be wary of scams like fake TGs and airdrops) let’s build beautiful things!

Profilbild von DotsamaNFT - Marketplace
DotsamaNFT - Marketplacevor 1 Jahr

💸 Earn Passive Income with Dotsama Badges! 💸 Hold a Dotsama Badge to get a share of 50% of marketplace revenue! Stake, earn, and grow alongside us. 🚀(Minting Soon) Want a free @Astarllama NFT? Follow, repost, and drop your 0x wallet below for an airdrop! 🪂 #NFT $ASTR $GLMR

Ähnliche Videos

Autonomous driving through very dense dynamic traffic, with extremely tight-complex-stochastic traffic-dynamics on sub-urban roads, connecting to an open ground, with absolutely zero traffic-rules. This is the most heavily cluttered environment where we have tested our #autonomousdriving technology, presenting many of the adversarial negotiation scenarios as well, throughout the autonomous navigation task. This demo was done at the Mata Baglamukhi Madir campus in the city of Nalkheda, in MP, India, and was done in the presence of heavy police forces deployed that day on the ground, as can be seen in our demo. Our autonomous vehicle starts from the temple with a generic open environment, with zero traffic rules, with very narrow corridors created out of barricades for vehicles movement by the security forces. In the corridor no two vehicles can pass through at the same time, and our vehicle was tasked with driving through this corridor, while negotiating its way from any traffic, two-wheelers, or pedestrians it faces, with dense presence of bikes and cars on either side, presenting a very challenging environment for #autonomousvehicles. The vehicle exits the open area, and then assumes generic dual lane navigation, avoiding both static and dynamic obstacles, before encountering a police check-post, where the vehicle is supposed to wait if the barricade is closed, and proceed if open. Upon exiting the checkpost, the vehicle negotiates a traffic-intersection with stochastic and adversarial driving behaviour of other vehicles on the road. Our vehicle continuously faced heavily cluttered traffic scene, where entities on the road can execute a random driving pattern, making the decision making task very challenging. We did the demo over a period of two days, successfully executing multiple (30+) trials in this setting. This demo was again a culmination of our prior works and demos: Kankali Kali Mata demo, on-roads, bidirectional negotiation capability on single lane roads, and open environment Level-5 negotiation capability as showcased in our Toll-Plaza demo. We again scaled up classical decision making and motion planning algorithmic framework, to adapt to such a level of density of obstacles on the road. This framework is further being scaled up with #reinforcementlearning and unsupervised #deeplearning at Swaayatt Robots. We will again do a demo in the month of June here, showcasing autonomously acquired skills to pave the way for Level-5 autonomous driving, and to solve the Level-4 autonomy problem by the end of 2024. #MachineLearning

Sanjeev Sharma

332,952 Aufrufe • vor 2 Jahren