Louis Morgner

The best thing to figure out is to figure out that you can figure everything out.

@zwiebelhelm u guys are cooking, keep the spirit up

What does it mean to bring SF to Berlin?

@darylginn deadline

I'm a designer, scare me with one word.

@jmwind is this an internal tool or what are you guys using?

Joined a new AI-native company this week and it’s kind of wild how different it feels already. The laptop arrived, I logged in, and an agent basically took over from there. It set up my dev env, pulled repos, fixed dependency issues, got permissions approved, pointed me at the backlog, linked the architecture docs, and surfaced the Slack debates I actually needed to read before touching production. When I needed context on something, I asked the agent and it found the exact thread from months ago explaining why a decision was made, who owned it, the related Linear issues, and the PRs connected to it. I’ve only been here 3 days but it honestly feels like I’ve worked here for a year because the usual friction and scavenger hunt for context just isn’t there anymore. We should probably stop calling this “onboarding” and rename it to “mounting” because this feels a lot more like mounting a distributed filesystem called “institutional memory” than slowly getting drip-fed context over 6 months.

@benedictk__ i'm in

Germany / Switzerland - who wants to be on this?

feeling down? just listen to actual life 2 from fred again in order. stop the thinking, start the feeling. one of the best pieces of music every created.

@MitcheIl the most sad business model i ever heard about

Met a guy making $5.2 million a year With a super simple business He finds a small town, buys a plot of land for cheap, and announces that he's building a data center there Residents whip up a frenzy and start pushing back He negotiates and has the city buy back the land for double what he paid Most of these net him $100k or so Does one a week Takes only a few hours of work Inspiring

a big question i keep coming back to is what the best context representation is. ultimately, it's text. but arranged how? md? html? something else? the answer may be a mix of data set representation, density, structure, and taste.

back in berlin with the boys. heads down building. first yt video hit 20k - @chrislimbergg is a goat.

@simpletox26 @karina_repko @fdotinc @useopencompany @actadotso out now on youtube

@karina_repko @fdotinc @louismorgner @useopencompany @actadotso can't wait for the full episode

recorded something cool at @fdotinc with the berlin boys @louismorgner @useopencompany @actadotso

@karina_repko @fdotinc @useopencompany @actadotso this was so fun to shoot

@LumoraAI_25 excited to onboard you soon

@louismorgner Already joined brother ☺️

you need to build the thing to figure out what you should've been building. each iteration teaches me so much. and more powerful ideas emerge. so instead of overthinking, just get to building and learning through the real rep in the product gym. action produces information.

@robj3d3 would love to bring this use case to @useopencompany - wanna share more details on your dream workflow?

You cannot convince me we don't already have AGI. Claude Code + ahrefs API is automating my SEO research in 10 minutes when it used to take months.

@fin465 NO NEED TO SCREAM BRO

SOMEONE VIBE CODED A PRODUCT THAT SCRAPES BUSINESSES AND SENDS COLD EMAILS AROUND WHAT THEIR CUSTOMERS ARE COMPLAINING ABOUT this is wild. you type in any niche and choose a city. it pulls every matching business off Google Maps with 50+ data points. then it actually crawls their websites and grabs verified emails, phone numbers, and every social profile attached to them pulled in real time, not recycled from some stale database like the other tools out there then the AI digs through up to 100s of their Google reviews and surfaces their exact pain points "customers say photos don't reflect the actual size of properties" or "homes sit on the market too long" then you describe what YOUR business offers. it matches your service against their specific problems and writes a fully personalized cold email per business. fire it off in 2 clicks. one at a time, never bulk, so it actually hits the primary inbox runs in 100+ countries across any vertical. if they're on Google Maps, you can pull them easily the most complete lead gen tool out there AND this entire feature was vibe coded with Claude Code in 1 week

started working on some orchestration/brain adjacent topics ~5 months ago. yc just put out a request for it, and "overnight" hundreds of people are shipping the same idea. it's all about execution in the end. ideas are not valuable. just the craft and end product is.

new website just landed. i want to be your new operating system for running your company with ai. yes, that's what everyone is building in sf these days but i think we are coming closer to the best ux out there. @useopencompany

@ndrewpignanelli yep, we spent so much time engineering fancy ontologies and rag pipelines but honestly not needed at all these days for most use cases. only if you have >10k docs, but even then just some fuzzy search can do the job.

people don’t understand this take cause they don’t understand what’s happening in AI memory. Everything is moving to git backed files accessible via grep-type-systems or semantic plus grep which isn’t very defensible to offer as a service. In other words… the SOTA approaches to memory are now just agent plus terminal. And all the fancy approaches like knowledge graphs are getting rekt by an agent plus a terminal. Your fancy agent structure is getting rekt by a model that can keep track of anything over 1000+ terminal calls.

#recursive-language-models" target="_blank" rel="nofollow noopener">github.com/useopencompany…

new on the radar: recursive language models don’t put the long prompt in the context window. load it into a python repl as a variable. The llm writes code to inspect/slice and calls sub-llms over chunks as functions. +114% over GPT-5 on OOLONG-132k.

@sama on it @useopencompany

feels like a good time to seriously rethink how operating systems and user interfaces are designed (also the internet; there should be a protocol that is equally usable by people and agents)