Daniel (@dmalmros) header
Daniel (@dmalmros) profile picture

Unhinged! I do not smoke.. building @impakta_io - AI for climate & finance. Part time investor and all that shit..

Aarhus, Denmark
Joined November 2010
Photo by Daniel (@dmalmros)Photo by Daniel (@dmalmros)Photo by Daniel (@dmalmros)Photo by Daniel (@dmalmros)Photo by Daniel (@dmalmros)Photo by Daniel (@dmalmros)Photo by Daniel (@dmalmros)Photo by Daniel (@dmalmros)Photo by Daniel (@dmalmros)Photo by Daniel (@dmalmros)
Every AI agent demo ends right before the part where it has to say "I don't know." #aiagents
7
SOC 2 was never a threat detector. It's a receipt for the boring basics, and most breaches, agents or not, still start with a skipped basic.
These security certifications are less than useless in this new AI agent world of security threats. What’s the certification checking that you’re obsessed with monitoring realtime; run agents analyzing all your realtime metrics; and your posture is “paranoid” on things like latency increases if services, attempts to access systems that have no business of accessing etc?
12
every agent ui should answer 4 things at a glance: - what is it doing right now - what does it know about me - what will it do next without asking - how do i stop it most agent apps answer one. usually the first, with a spinner.
1
104
This is awesome! 👏🏼
Day 5/ Couldn't pick, so we shipped both Full width, split view, or switch between them right in the list with "\" Works in Mail, Support and the Inbox
1
2
27
Your AI agent asks "Allow this action?" so often that users click yes on autopilot. That's not safety. That's a cookie banner. 3 fixes so people actually read the prompt: #aiagents #ux
1
15
2. Only ask when it can't be undone. Reversible? Just do it and show an undo button. Save the scary prompt for delete, send and pay.
1
3
3. Batch the boring ones. 10 file edits = 1 review screen, not 10 popups. Bookmark this for your next agent build. What's the worst permission prompt you've clicked through?
4
Saturday CTO ritual: coffee, then reading the bug cards my AI QA bot filed this week. Never says "looks good to me". Zero feelings about my code. Best hire I never interviewed. #founderlife #buildinpublic
1
12
1/3 Text chat is where agentic UX goes to die. When your agent outputs 400 words of markdown instead of an interactive component, users stop trusting it. Agentic UI cannot just be a streaming text box anymore. – at Guadalajara, Jalisco
3
1
1
121
in 24hrs i made a collaborative, virtual operating system. "ink os - a social computer" it's written in a programming language that i wrote (ink) and i can play nocturne (an infinite 3d, ai native mmo) inside of it. it has permissions like google docs, it's ai steerable via api / cli. (so you can use your local claude / codex subscriptions to vibe code onto it). each app is sandboxed, so you don't need to worry about what your friends are publishing on the computer. it uses object storage for files & has a shared database layer that all of the apps can talk to (with reactive subscriptions). this means all your apps can be interoperable with each other. think of each "desktop" as an opinionated workspace. pin separate apps to the task bar, surface different files and apps. i've vibe coded the following apps onto it: - preview - finder - little gods (game) - palette analysis - bookmarking - retro diffusion - spreadsheets - video calls - nocturne (game) - pathweaver (game) - rabble rouser (game) - a collaborative moodboard - a collaborative text editor - a collaborative movie list manager - multiplayer polls - a music app - rigamaroll (game) - a chatroom - color picker - ink programming environment - tic tac toe. one thing i really love is how you can *duplicate* apps and then it treats them as separate deployments. so you can *really easily* fork an app or an mmo, vibe code some changes and then delete the one you don't like? (or keep both?) i think the *permissions* model being at the top layer, enables some really fun ux for apps, such as... a video call app where you don't need to share a link with anyone cos it's just part of the space? (or a chatroom, private mmo server, etc). if there's one thing i've learnt *again and again*... it's... scale up your ambition. if i can do this in *24-hrs* with ai, what can a team do in a year?
ok so... there was a 2 day hackathon at work last week... i built an infinite, 3D, ai native mmo called nocturne... it's set in the world of inkwell. the server capacity is... pretty good..? i tested it with 1000 connections in the cloud. it's written in a programming language i wrote (called ink). it uses polygons & gaussian splat *frostings* for the graphics. it has an adaptive music system that changes intensity and mood based on the gameplay. the combat is kind of realtime dnd-like? all of the npcs are powered by llms, you can talk to them, trade, fight them... they remember you..? they have little neural nets inside them and they optimise for survival and happiness. there's *trillions* of combinations of characters... *hundreds of millions* of spell combinations. all of the creatures have a genome, they reproduce and have mutations creating new creature types... you can catch them like in pokemon... there's semantic crafting and alchemy... you can be turned into a vampire and burn in the sunlight..? there's a day & night cycle... seasons... fires spread, rain puts them out, ice freezes over lakes... you can become a werewolf and infect others? or a weredragon? even a wererat. you can ride on goats, sheep, horses, eagles and dragons... aliens can abduct you or the farm animals... and when you do... you can discover and explore their home planets with different physics. there's giant colossal beasts to fight, demigods with trials that give you world changing powers... you can get portals in a bag that take you to home's you can customise like in tiny glade... oh and there's an api... so people can connect their local agents to it and build their own worlds... rift's open up and invasions happen. villages learn traditions and will fear you if you treat them badly... there's open pvp everywhere and you drop all of your gear if you die. if you try to do pvp in the main cities, then mages will spawn in and try to kill you. oh... there's also semantic scrying.. you can get any item and cast a spell and it opens a portal to the closest thing that is semantically similar... got a bone? maybe it'll take you to a graveyard... a log? a forest, etc. i feel like i haven't even *scratched the surface* with how deep this game is, but this post is pretty long... so... *dream bigger*.
24
7
4
135
6,867
CGI all over the place…
20
If your agent needs a 2,000-word system prompt to behave, you didn't build an agent. You built a hostage negotiation. #aiagents
18
Free SaaS, paid agents, paid agency. Congrats, we reinvented the consultancy with a login page. Software was the escape from services margins, not the free sample for them. #saas
This is the future of SaaS in 1 image 1) Give away SaaS for free (or close to it) 2) Upsell AI agents 3) Upsell agency services
37
K here it is y'all, the agent interface I made to suite my workflow (many projects with many concurrent tasks). stetta.app 👈🏼
4
4
21
1,178
Daniel retweeted
Generative UI is no longer a skill issue👇 1. Import standardUI from @CopilotKit 2. Pass it to your CopilotKitProvider You get a FULL catalog of 70+ components that can render in the chat. Add one wrapper and put them anywhere on your page. Works with ANY AG-UI agent.
4
3
1
44
2,723
Every SaaS shipped an AI feature this year. Almost none can tell you its CO2e per 1,000 requests. Carbon is the next observability metric and nobody's on call. #ai #climatetech
1
2
27
Unslopping a B2B SaaS Before / After
4
6
1
144
6,647