Really curious to see what the community thinks about this. Basically all it’s doing is giving you access to run your own agent. So you might as well run your own ICM in Claude code, right? According to their terms, the user takes all of the risk for the platform making errors and hallucinations. What do you think, are you in? Note: this isn’t financial advice and I don’t work for Robinhood

Had a call today with researchers from Stanford's Autonomous Agents Lab. They're studying AI adoption at marketing agencies. Found me via Google. I asked them how much research they did on me first, none; they were embarrassed to say they just filled out my contact form. I warned them it might not be the conversation they expect. At the end, they said I was the most advanced agency owner they'd spoken with. They'd never heard of ICM. These are smart people doing real research. They've talked to a lot of agencies. And the most common thing they see is: people using ChatGPT chat, maybe dabbling with agents, struggling to get them to do things reliably end-to-end. You all know what I've been running for the past 2 months and I showed them. Then the researchers showed me their own tool — an autonomous browser agent that can log into Google Ads and act. I told them: I don't write to external platforms without a human reviewing it first. That's a policy, not a technical limitation. My clients' $20K/month runs through my judgment, not an AI's. Human in the LOOP! Their reaction: "that makes sense." But they were clearly used to hearing "I'm trying to get the AI to do more." I'm not. I'm trying to get the AI to help me reason better. That's a different goal. My takeaway: if you're in this group and you're here honestly learning, you're way ahead, don't stop! Keep building! Ronnie Coleman once said: "Everybody wants to be a bodybuilder, but nobody wants to lift no heavy-ass weights."

Just curious, does everyone write your md files from scratch? Or do you ask claude to help you write, by giving it information? And can I say that the recommendation is to have md files lesser than 150 lines?

I was curious what people do when they are using the web chat side of Chatgpt/gemini/Claude. Do you keep all your chats, keep everything in projects/gems/whatever or do you delete them all? I do the project/gem thing where if I have topic or something I want to contain and give rules too I will keep those chats. But if its not a chat in a project, I delete it. I was running into issues were a chat from 6 months ago, would get referenced then I would spend like 5 prompts trying to get it to let go/forget something. So I got to the point where I turned off memory and deleted chats. Now I can explore a topic and not have to worry about past topics polluting it. What all do you do?

I wrote this essay because of my coworkers, my relatives, the influencers online who poke fun at AI because of the slop they see. I don’t blame them. As we all know even if you want to adopt the technology there is endless slop in the form of the same tools and wrappers that will be replaced by the next Claude update. It so easy to be jaded about this movement and it’s easy for us to miss that being a part of this community. The reality is every other person I speak with rolls their eyes when I talk about what I see here. Please if you find this useful share with the people in your life who feel the same. https://donsbookshelf.com/blog/dont-let-ai-slop-fool-you/