kay retweeted
You can now comment on posts at empero.org.
Sign in with your Empero account, the one you use for Abacus, to reply, vote on comments, like posts and save them for later. Replies to you and your saved posts are collected at empero.org/community
kay retweeted
idk how they built that, but it works surprisingly well. This time, my favorite neuroanatomy with brain pathologies as a service (125 tool calls and 200k tokens later) ;) -> @EmperoAI kojo in @zorai_agent
kay retweeted
Use kojo @ kojo.sh
We are planning on a secondary release concerning cybersecurity-oriented models, which might pique some of your interests.
gif made by kojo in ~3 minutes and 21 seconds.
kay retweeted
Proud to finally share what we’ve been working on at Empero: Kojo. 🚀
The model performed extremely well on the completed SWE-bench Verified test suite (461/500 bugs fixed = 92.2%). Claude Opus 4.8 achieved 88.6% in the published leaderboard; Sonnet 5 85.2%; and Mythos Preview achieved 93.9%. We achieved better performance than Opus 4.8 and Sonnet 5 and is within 1.7% of Mythos Preview.
The API prices are as follows:
$0.175 per million input tokens
$1.00 per million output tokens.
$0.02 per million cached input tokens.
It is also super exciting to be part of the team launching this product so we can get more people using Kojo!
Below is something that Kojo made in one-shot:
(Do know there are better things made with this model so definitely check out the others within EmperoAI!!)
Kojo, our latest model, is out.
Chat with it for free, or build on it through an OpenAI-compatible API.
kojo.sh
kay retweeted
Kojo, our latest model, is out.
Chat with it for free, or build on it through an OpenAI-compatible API.
kojo.sh
kay retweeted
Our website just got an all new and fresh look!
empero.org/
kay retweeted
What a terrible day to release a new model, but at least we @EmperoAI can claim to be a reaaaal lab now.
Android app incoming, maybe.
More models, maybe, incoming.
Pricing will be reasonable come monday, as we are still completely self-bootstrapped. We're available, ask us :D
kay retweeted
I am proud to announce that I am currently an active contributer at @EmperoAI. I will be helping with training the models and providing datasets. Even though I am still a novice I am curious to see where my experience with AI will lead me!
kay retweeted
You can now get an api key for the beta! (Requires an account)
kojo.empero.org
Say "Hi!" to our newest beta model!
kojo.empero.org/chat
kay retweeted
Kojo is our next model in beta currently.
Take a gander for yourself @ kojo.empero.org
We're pleased with ourselves. I am, at least. Requests for access via a payed API will be handled.
P.S, try asking it to make a 3D model of a rocket engine :)
Logo by me.
kay retweeted
Say "Hi!" to our newest beta model!
kojo.empero.org/chat
kay retweeted
🚀 Abacus Desktop 0.1.0 is out.
The abacus coding agent, now in a window: your projects and sessions, the agent's work as it streams, the diff, a terminal, and a browser it can use.
Open source. macOS, Windows, Linux. Any model.
abacus.empero.org
kay retweeted
New from Empero: PageGram: Multi-Head N-gram Memory at the Read Cost of a Flat Table.
Engram-style n-gram tables cost 16 random flash reads per token. PageGram reads 2, and matches or beats both flat and Engram-style tables in loss.
📄 alphaxiv.org/pdf/2610.pagegr…
🧵 1/7
kay retweeted
New from Empero: Identity on Demand: Multi-head Gated Value Residuals (MGVR).
A drop-in change to attention that reaches the same loss in 16–22% fewer steps: 1.15–1.23× effective compute for +0.2% parameters.
📄 alphaxiv.org/abs/2610.multi-…
🧵
