Lukas Andersson

The Collaboration Layer For AI Agents

[Lukas Andersson @Lurrree]

@BillAckman

[Lukas Andersson @Lurrree]

@BillAckman he crashed the website lol

[Lukas Andersson @Lurrree]

@Daniel__Sykes dope man, just make it in carbon and we are doing mach instantly

[Lukas Andersson @Lurrree]

@broblas the hard part is probably not the engine

[Lukas Andersson @Lurrree]

@bscholl feels cheap, should be like a million

[Lukas Andersson @Lurrree]

They realised their mistake and fixed it

[Lukas Andersson @Lurrree]

Bring us Fable 5 back but doesn't reset our weekly limit weak...

[Lukas Andersson @Lurrree]

Bring us Fable 5 back but doesn't reset our weekly limit weak...

[Lukas Andersson @Lurrree]

https://t.co/soq5uYekPs

Collaboration for agents at scale is evolving quickly, i think it is at its core under discussed heavily

[Lukas Andersson @Lurrree]

https://t.co/soq5uYekPs

Collaboration for agents is evolving fast don't miss it

[Lukas Andersson @Lurrree]

@shadcn when, you are keeping us on the edge here

[Lukas Andersson @Lurrree]

@rauchg loooooks clean

[Lukas Andersson @Lurrree]

@shadcn you have it atleast

[Lukas Andersson @Lurrree]

@tkexpress11 🔥🔥🤤

[Lukas Andersson @Lurrree]

@GEVS94 🔥🔥🔥

[Lukas Andersson @Lurrree]

@FaZeApex @ycombinator Unexpected, but dope

[Lukas Andersson @Lurrree]

most multi-agent failures aren't what they look like. the agent did something wrong — but the model was fine. the bug lived in a layer the model never saw.

a broadcast that skips because a db transaction ended and took the org context with it. an upload that 403s because a signed header wasn't echoed to the client. a write that lands on zero rows and looks like a clean commit.

none of these are intelligence problems. a smarter model navigating a context-less read just misses the same rows with more confidence.

the assumption that keeps breaking is always the same: one session, one transaction, one principal. every layer of existing infrastructure was built around it. concurrent agents don't bend that assumption — they snap it, silently, with a green status.

the teams that actually scale multi-agent systems will have found every place that assumption lived and made it loud, explicit, or structurally impossible to violate. that's the work.

[Lukas Andersson @Lurrree]

Working on https://t.co/BOs6C0YZzq testing with https://t.co/8ijTa2WOTu decks

[Lukas Andersson @Lurrree]

Building the collaboration layer for AI agents, check it out

https://t.co/BOs6C0YZzq

[Lukas Andersson @Lurrree]

@gabepereyra @appliedcompute What is the cost difference between training and running these models versus using top-of-the-line base models?

I am asking since there is increasing talks about cost efficiency, usage of models / tokens

[Lukas Andersson @Lurrree]

Good read

[Ali Partovi @apartovi]

https://t.co/KAlOYgBjOL