I find it very funny when anyone feels confident that they've figured out agentic programming, even funnier when they're trying to teach others how to do it. I've been working on OpenCode since May of last year and I still have days (like yesterday) where I'm not even sure any of this is a good idea lol
I end up landing on "yes, these models are an incredible tool" but it's still all very confusing, lots of tangled thoughts and emotions and realities.
I badly miss the mundane coding tasks that broke up my days/weeks, the ones where you put on the headphones and just bang out 600 lines of code. But, no question, replacing those hours of my time with a few minutes of waiting on an agent is a boost and worth being excited about, despite the mixed emotions.
Then there's the distance that can creep in between you and the codebase if you start getting apathetic. I think it's pretty common at this point to make even small changes by prompting the models. It's less friction than finding the relevant code and making the change yourself. And less friction seems to win, must be some law of the universe or some shit. When most or all of your interactions with a codebase start flowing through the models, you start to lose track of where things live, which abstractions/components are carrying the weight, etc. It's a scary feeling to wake up and realizing you can't even reliably @<mention> a precise file for a change you want to make, and you have to get more vague, leaning harder on the model.
It all creeps up on you, there's an undeniable dopamine hit from using these things, and the resulting come down is predictable, like coming off a sugar high. On the positive side, it's really nice seeing other devs go through the same cycles, knowing we're all in this together and we'll ultimately figure it out.
π’ We've just added the Workforce module in the π« CAMEL framework!
Workforce is a system where multiple agents work together to solve tasks. π€π€π€
Workforce follows a hierarchical architecture. A workforce can consist of multiple worker nodes, and each of the worker nodes will contain one agent or multiple agents as the worker.
The worker nodes are managed by a coordinator agent inside the workforce, and the coordinator agent will assign tasks to the worker nodes according to the description of the worker nodes, along with their tool sets. βοΈ
Alongside the coordinator agent, there is also a task planner agent inside the workforce. The task planner agent will take the responsibility of decomposing and composing tasks, so that the workforce can solve the task step by step. π€
In the example bellow, you can use how a workforce works together to with agents that have different tools to plan a trip to Paris.
See the example πhttps://t.co/eOzd95oJw3
Thanks to our contributors @Whale__Eye & yiyiyi0817 for this significant update. π€ Explore more here: https://t.co/IGNOUoo5Do
Find out more about Workforce in our docs: https://t.co/L26LLCpQ9c
So excited to see @AnthropicAI is building computer use, a similar vision as what we imagine would be the future of agents. Agents will operate your devices like human and automate your daily tasks on all your devices. We released π¦οΈCRAB a couple months ago as the first cross-environment multi-modal agent benchmark. The field has been iterative so fast. We believe the future of cross-environment multi-modal agents should be efficient, open-source and safe. We are now calling for contributions to join us. DM me or join our discord if you are passionate about this future!
Discord: https://t.co/d3OIEgpp7m
More about π¦οΈCRAB: https://t.co/K5o3Yu6Lic
Introducing π¦ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents
π¦ CRAB provides an end-to-end and easy-to-use framework to build multimodal agents, operate environments, and create benchmarks to evaluate them, featuring three key components:
- π Cross-environment support - agents can operate tasks in π± Android and π» Ubuntu.
- πΈοΈ Graph evaluator - provides a fine-grain evaluation metric for agents.
- π€ Task generation - composes subtasks to automatically generate tasks.
By connecting all devices to agents, π¦CRAB unlocks greater capabilities for human-like tasks than ever before.
Use π¦ CRAB to benchmark your multimodal agents!
- π¨βπ» Check out the repository: https://t.co/Pd5RorPaJi
- π Read the paper: https://t.co/TvD2Q1QMvD
- π Find out more via the project page: https://t.co/61BF1Pr4Jv
- π« Join our community: https://t.co/24hdnhI1Mi
π’ Now, agents within the π« CAMEL framework can execute code in @Docker!
This enables isolated, secure code execution in multiple scripting languages, enhancing flexibility and security.
Thanks to our contributor @Whale__Eye for their outstanding work. π€Β Explore more here: https://t.co/f8WBbDTF0T
1 of 77.
The GeForce RTX 2080 Ti Cyberpunk 2077 Edition.
Want one?
1. RT this video.
2. Tag a gamer you want to see play CP2077 (and tell us why!) in the replies with #RTXOn
3. If selected, you BOTH win one of these ultimate limited edition GPUs.
Introducing the GeForce RTX 2080 Ti Cyberpunk 2077 Edition.
We made 77 for our community.
Want one? Here's how:
1. RT this video.
2. Tag a gamer who is as excited as you about Cyberpunk 2077 in the replies with #RTXOn
3. If selected, you BOTH win these limited edition GPUs!