The Ledger
Every statement that passed quotation and attribution checks. Mix any filter with any other: certainty 1/5, debate potential 5/5, or both at once.
why aren't all 40 resolved? a statement only gets an assessment when the public record can support or contradict it. opinions and what-ifs never can, and 0 checkable ones are still open, waiting for their date. predictions held up or didn't; assertions are supported or contradicted. on every card: ▮▮▮▮▮ certainty · ▮▮▮▮▮ debate potential. speakers are clickable
Finn: A computer science degree is the most useless degree today
“I have a computer science degree, which is probably the most useless degree you can possibly get at this point in time.”
Finn: Hardware bottlenecks and soaring memory costs will persist long-term
“My, kind of thesis, which I think is playing out in front of us right now is we're going to have hardware bottlenecks for a very long time now because the AI build out's happening. And so memory sky, I just bought a memory card for my Nintendo switch to cost m…”
Finn: Local multi-agent pipelines will automate video production in 45 seconds
“Now five different models locally on my computer are going to basically process this video and in 45 seconds The entire production process is over, and it's going to be uploaded on YouTube, right? That's where this is going.”
Finn: Lead gen returns for interactive AI apps will vanish in three years
“Like we're in that beginning moments of this strategy where people who attack it and use it are going to see unbelievable returns. And then in three years when everyone's doing it, the returns won't be there.”
Alex Finn: Hermes Overtook OpenClaw with Desktop Release
“I believe this is like the moment that Hermes overtook OpenClaw, to be quite honest”
Finn: Claude Opus 4.8 is the smartest AI model available
“I think Opus for eight is the smartest AI model out there.”
Finn: ChatGPT-5.5 is better than Claude Opus 4.8 for coding
“Coding, I actually think ChadGPT-Five-Five is better than Opus-Four-Eight for coding.”
Finn: Multi-agent role hierarchies create severe token and cost inefficiencies
“The challenge is, I think there's inefficiencies there when it comes to cost. Like, if I have to go to my CEO and say, hey, build me you know, a thumbnail for my latest YouTube video, and then they go to, like, the product manager, who then goes to the graphic…”
Finn: Hermes produces polished updates while OpenClaw updates are rough and untested
“The Hermes updates have been very focused, polished, tested, and tied to really nice narratives that are focused on making life easier for the user. While I feel like the OpenClaw updates Have been more kind of shotgun, put everything in it, don't test it quit…”
Finn: OpenClaw hardcodes models and requires framework updates for new releases
“OpenClaw, like every model is like hard coded in to OpenClaw. So you have to like ask them to switch models. And when new models come out, you have to wait for OpenClaw to update with that newest model.”
Alex Finn: AI employees can track trends, build products, and run businesses
“You are going to have an AI employee that's tracking trends for you, building you product, delivering you news, creating you content, running your whole business. This isn't your one-on-one. It's going to be checking your email, letting you know when you get a…”
Finn: Claudebot Autonomously Built and Submitted Features for Creator Buddy
“It actually found, you know, that this story, articles are popping on X. Elon's giving away a million dollars, and it actually built out article functionality for me in my SaaS creator buddy, right? So I have this app creator buddy. It's all about X content. A…”
Finn refuses to hire humans, using Claudebot as his only employee
“And I'm just a one person business. I'm not hiring people. This is my employee. And it was able to get this done, which is really incredible.”
Alex Finn recommends beginners run AI agents on cheap local computers
“I think the best path for the average person, honestly, is a Mac mini. Actually, I take that back, like, if you just have, like, a computer laying around using a computer. Basically, my recommendation is the cheapest computer you can find, use that. A local de…”
Finn: X thread-to-newsletter funnels are oversaturated and watered down
“And the way people really have been driving clicks to their newsletter over the last couple of years is they build like a really good thread and then they have a follow post that says, here's my newsletter, sign up for it. And that's kind of been drowned out a…”
Finn: DeepSeek forced rival AI models to expose chain-of-thought reasoning
“If Deep Seek did anything well, it kind of set the tone for like, okay, now all the other AI models have to put the chain of thought in, because this is what people expect now. I really think Deep Seek had like huge influence on how all this works.”
Finn: Developers should avoid using reasoning models like o1 for coding
“I would assume based on my experiences, you probably don't want to use the thinking model to do coding. You know, cause I've tried oh one and it was just a pain to use. You lose a lot of speed.”
Finn: Developers no longer need to break AI coding into micro-steps
“Before this, everyone who was in AI, hey, if you're doing something recursive, you're doing something, make sure you break it down into micro steps. Make sure you break it down step by step by step to make sure it's accurate. I don't think that's the case anym…”
Finn: X and YouTube have the best indie hacking communities
“If you're an indie hacker, if you're an entrepreneur, I, in my opinion, I think X and YouTube are the only two places on planet earth that have the best indie hacking communities on the internet. I think if you're an indie hacker, you've got to be on both. You…”
Alex Finn: Hermes Desktop Is the Best Interface for Hermes Agent
“I think this is the single best way To use Hermes Agent now. I think, I don't use Telegram on desktop anymore. I don't use any other experience. This is clearly the best way to be using Hermes Agent.”
Alex Finn: Managing context stops Hermes Agent costs from hitting $1,000 monthly
“You, if you manage your context and your sessions well, you are not paying thousand dollars a month. You're not paying anything close to it.”
Finn: Average users do not want to use command-line terminal interfaces
“The average person does not want to use a CLI, right? Like I guess, I think there was this huge Trend the last few months. CLIs, we're going back to CLI. CLI is the future. Everyone will be working the CLI. That doesn't change the fact average people do not wa…”
Finn: Use distinct profiles for differing skills and sub-agents for parallel tasks
“Different skill sets needed. Use different profiles. One skill set, but just on multiple strands at once. Use sub agents.”
Finn: AI expenses are value-generating investments, not entertainment subscriptions
“I think people have this weird framing around costs when it comes to AI. Like they see the cost of Claude and they see it's, oh, 200 dollars a month. That's really expensive. It's very, they're comparing it to like the cost of like Netflix and like Xbox live a…”
Finn: Maximizing AI agents requires full personal context and clear expectations
“What you need to do, because its memory is so strong, is you need to go in and you need to make sure it knows as much about you as humanly possible, right? You need to make sure if you have a YouTube channel, you put the link to your YouTube channel, you talk …”
Finn: Users underutilize AI by failing to hunt 'unknown unknowns'
“I think the issue most people have when they use Not only Claudebot, but any AI tool at all is they don't hunt the unknown unknowns, and what I mean by that is these AIs have unbelievable power, can do unbelievable things, but we only ever ask it to do things …”
Alex Finn uses Claude Opus for reasoning and Codex for coding
“You want to use the right muscles, and what I mean by that is I think of Opus as the brain. You want to use other models as the muscles. Codex is a really good muscle for coding for this, and so set up Codex inside your CloudBot.”
Finn: Design AI agent workflows around human actions, not AI capabilities
“You need to think of it from the lens of what would a human being do? If I had a human being right here, they had a computer, they had our e-commerce site up on it. What would they do? Not what would an AI do? What would a human being with a computer do?”
Finn: AI hardware costs should be compared to employee salaries, not Netflix
“The mental framework you need to have is, Most people are comparing these costs to like Netflix. Oh, I paid 20 dollars a month from Netflix. I'm not going to pay 200 dollars for ChatGPT. The thing is, is Netflix, Xbox Live, all those are money sinks. Those are…”
Finn: Anti-prompt-injection skills will launch within two weeks
“I'm sure I'm very positive in the next week or two, there'll be official skills out there that like handle prompt injection from email, prompt injection from tweets and replies.”
Finn: An Elon Musk retweet on X yields about 10 million impressions
“You get an Elon retweet that's getting 10, ten million impressions, right?”
Finn: Interactive micro-experiences outperform text threads for email collection
“Yo, I built this really cool online experience, right? Go play it. And now you get an email a lot cooler way. I think then kind of a thread. So I think this is the cutting edge of how to get emails and all of that.”
Finn: Converting viral memes into AI micro-apps is an untapped growth frontier
“So I think there truly is something to taking viral moments in time, turning them into experiences with AI and like garnering attention that way. There's something truly there. And I don't think a lot of business owners and entrepreneurs and indie hackers are …”
Finn: Hermes agent comes preloaded with 150+ skills that increase costs
“Out of the box, your Hermes agent has, like, over a 150 skills installed, and each one of those actually adds context to your agent, and so that's increasing your cost.”
Alex Finn: Combine a personal context brain dump with reverse prompting
“You brain dump in everything about yourself, interests, goals, ambitions, skill sets, things like that. So your agent has context around who you are, and then you reverse prompt based on what you know about me. What's the best way to do this?”
Finn Scans for Business Opportunities Every 20 Minutes Using Local Qwen
“Every 20 minutes, I have my agent going and using the Quen three seven model locally.”
Finn: High-memory Mac Studios are virtually sold out
“Mac Studios pretty much sold out on any, basically every level. You can get it right now, but it's small amounts of memory. It's not like the big the big boys that allow you to run really good models.”
Finn: Claudebot has zero access to my personal Twitter account
“So it has zero access to my Twitter account. And so you want it only access to things where can't really mess things up and it's not susceptible to trickery.”
Finn: A simple Cursor-built mini-game drove 500 newsletter signups on X
“And so I experimented with this about eight months ago where I said, Hey, I built my first video game through cursor. I have no game building experience. Play the game below. Whoever has the highest score in the next 24 hours, I'm sending you a hundred dollars…”