David Hoos

At the core of effective agency biz-dev is building trust. But there are a variety of ways to build trust so you have to make a choice. That's one reason why I appreciated this story from Bram van de Ven about how he has taken a month-long business trip to a city 7-hours away. Is a podcast the right play for your agency? Maybe. Do you need to go to an industry conference? Maybe. Or maybe a month-long business trip is what it will take. It depends. It's all about identifying what you can do, what your audience needs for you to build trust with them, and identifying the activities where those two overlap.

@RobertJBye For example: “It seems like our conversation is going in a new direction. Would you like to start a new threat to minimize your usage?”

@RobertJBye Since we seem to be able to use up credits at different levels for different tasks, having something that gives us better visibility into what work led to what usage and maybe even a toggle we can turn on that will prompt us to work differently to save credits.

What features are missing from Claude on web? Boring simple things to crazy wild ideas. What do you want to see!?

@bcherny @itsolelehmann It think it needs to be tied to more structured goals, similar to what Paperclip is doing.

@itsolelehmann We’re always experimenting with new ideas. 90% don’t ship because we don’t think they’re good enough experiences. Still on the fence about this one — should we ship it?

i can't believe more people aren't talking about this part of the claude code leak there's a hidden feature in the source code called KAIROS, and it basically shows you anthropic's endgame KAIROS is an always-on, *proactive* Claude that does things without you asking it to. it runs in the background 24/7 while you work (or sleep) anthropic hasn't turned it on to the public yet, but the code is fully built here's how it works: every few seconds, KAIROS gets a heartbeat. basically a prompt that says "anything worth doing right now?" it looks at what's happening and makes a call: do something, or stay quiet if it acts, it can fix errors in your code, respond to messages, update files, run tasks... basically anything claude code can already do, just without you telling it to but here's what makes KAIROS different from regular claude code: it has (at least) 3 exclusive tools that regular claude code doesn't get: 1. push notifications, so it can reach you on your phone or desktop even when you're not in the terminal 2. file delivery, so it can send you things it created without you asking for them 3. pull request subscriptions, so it can watch your github and react to code changes on its own regular claude code can only talk to you when you talk to it. KAIROS can tap you on the shoulder and it keeps daily logs of everything. > what it noticed > what it decided > what it did append-only, meaning it can't erase its own history (you can read everything) at night it runs something the code literally calls "autoDream." where it consolidates what it learned during the day and reorganizes its memory while you sleep and it persists across sessions. close your laptop friday, open it monday, it's been working the whole time think about what this means in practice: > you're asleep and your website goes down. KAIROS detects it, restarts the server, and sends you a notification. by the time you see it, it's already back up > you get a customer complaint email at 2am. KAIROS reads it, sends the reply, and logs what it did. you wake up and it's already resolved > your stripe subscription page has a typo that's been live for 3 days. KAIROS spots it, fixes it, and logs the change endless use-cases, it's essentially a co-founder who never sleeps the codebase has this fully built and gated behind internal feature flags called PROACTIVE and KAIROS i think this is probably the clearest signal yet for where all ai tools are going. we are heading into the "post-prompting" era where the ai just works for you in the background like an all-knowing teammate who notices and handles everything, before you even think to ask

@lydiahallie Any word this morning?

Update: still working on this. It's the top priority for the team, I know this is blocking a lot of you. More as soon as we have it.

We're aware people are hitting usage limits in Claude Code way faster than expected. Actively investigating, will share more when we have an update!

@lydiahallie We don't just need it fixed, we need to get our usage back. I used 15% across Friday and Saturday and then woke up to 75% this morning.

@Salmaaboukarr I'm locked out till Friday. 😒

are claude usage rates going insane rn or is it just me?

@claudeai But what good is it if you hit your usage limits in 20 minuntes?

Computer use is now in Claude Code. Claude can open your apps, click through your UI, and test what it built, right from the CLI. Now in research preview on Pro and Max plans.

@trq212 At the very least it would be helpful to be able to see more itemized usage data so we can discern how to optimize our usage. It’s getting frustrating to use it a bunch and clocking modest usage and then just doing a few things and it clocks a ton of usage.

To manage growing demand for Claude we're adjusting our 5 hour session limits for free/Pro/Max subs during peak hours. Your weekly limits remain unchanged. During weekdays between 5am–11am PT / 1pm–7pm GMT, you'll move through your 5-hour session limits faster than before.

I’d really like some way to itemize what is driving my @claudeai Max20x usage. I was using it pretty heavily on Friday and Saturday and barely hit 16% of my usage for the week and then spent 45 minutes doing work with it this morning and now it says I’ve had 60% of usage!?!?!?!

@evielync Sounds like a blend of Paperclip, Obsidian, and Claude Code maybe? Either way, looks cool!

WHAT?!? 🤯 I asked Claude to build me an all in one AI Operating System for working with Claude Code. An hour later here we are... → Full ability to chat with Claude Code → Markdown file browser/editor built right in I've been using VS Code but there is a lot that I just don't need. I'm a knowledge worker, not a developer. So I guess I just built an IDE for knowledge workers? Now we're building: → Voice Mode (ability to switch to voice conversations) → Cron Job Management - so I can manage all the automated processes we have running → Ability to switch to different agents (currently I just have one... my AI Cos, Chad)

@gregisenberg How do you interface with it on mobile?

I met the guy behind Paperclip. he won't show his face, but he just built one of the FASTEST growing open-source projects in AI. how to use Paperclip to hire AI agents to ACTUALLY run a startup with 0 employees: 1. with paperclip, you hire a team of AI agents like CEO, engineer, QA, video editor, content strategist and manage them from one dashboard. it works with Claude Code, Codex, OpenCode, or any model on OpenRouter. you're not locked into one provider. 2. your AI agents wake up capable but with zero memory. they don't know who they are, where they are, or what they're supposed to be doing. kinda like that movie memento from back in the day you need to leave them Polaroids like heartbeat checklists, persona prompts, written context. that's how you keep them on track. 3. when an agent makes a mistake, you don't rewrite everything. you add one rule to their persona prompt. "always define a success condition for every task." "always pass work to QA before closing." you're training them like you'd train a junior hire. one correction at a time. 4. skills extend what your agents can do. want a video editor who can produce animated content? install the Remotion skill. want security reviews? there's a skill for that. 5. the biggest lever for quality is encoding your own taste. AI can do everything except know your values. design sensibility, brand voice, success criteria but you have to write it down. 6. don't one-shot your startup. agentic design patterns matter. the simplest one: after the engineer builds something, QA reviews it. structure prevents compounding errors. one-shotting an entire app is fun for 30 minutes, then it falls apart. 7. Paperclip tracks every token spent and every task completed. you can use your existing subscriptions (Claude, Codex) so spend shows as $0, or hook into API credits for real dollar tracking. 8. importable companies are coming. Gary Tan's G-Stack, a full game studio, 300+ agent repos... you can "acqui-hire" a proven agent team into your Paperclip instance instead of building from scratch. the future is downloading a tested org that actually works. 9. routines let you automate recurring work. "every day at 10am, read what was merged into the main branch and write a Discord update celebrating community contributors." it runs, you review, you improve. every task is traceable. 10. maximizer mode is next. you tell the CEO "build this game" and it does whatever it takes and hires who it needs, keeps pressing until it's done. no token anxiety. just outcomes. use @ideabrowser for startup ideas/trends to get started thank you for @dotta for doing this podcast and breaking down exactly how people can hire ai agent teams with paperclip you won't find an episode like this anywhere else episode is live on @startupideaspod on your fav platforms (follow for more) is this not the greatest time in history to be building? im rooting for you now go watch my frien

What movie is 10/10, yet hardly anyone has heard of it?

Overall, I was pretty pleased with the Stranger Things finale. The one thing I told my wife I felt was missing was a strong song that captured the emotional vibe. That said, I think they nailed it so well in season 1 and 4 that they had set a very high bar for themselves.

Co-sign

@dancintilldead I think Vecna gets a Darth Vader-style redemption arc. He makes the right choice at the very end, but dies in the process. Remember, the Duffer's said the most violent death is in this season. I could very easily see it being Vecna.

so do we think vecna is getting killed or he is getting some redemption arc and being freed from the mind flayer

Welp. Once again my @Spotify wrapped is all the Soundtracks we play for our 5 year old. Can we please get a profiles feature like every video streaming service has?

@SantiagoPliego He should talk to @smpldocs. I don’t think they’ve built it yet, but they’re well on their way.

@BrandLongo KW

SEO Starts with Keyword Research I've made my clients MILLIONS by understanding this. Get it for Free for 24 hours only. Comment "KW" + Like this post (must be following)

Pretty proud of my family member who is one of the folks behind this. Not sure if he'd want to be called out so I'll leave him anonymous, but well done.

I’m old enough to remember when cord cutters switched to streaming to AVOID commercials. *sigh*