A lab for autonomous intelligence.

Joined October 2023
100 Photos and videos
Pinned Post
Ritual is a lab for autonomous intelligence. The thesis is organized around what durable machine agency actually requires: emancipation from human control, strong privacy, mech design for compute markets, and consensus rules that can schedule and resurrect agents when they die.
256
286
1,042
329,185
Ritual reposted
Ritual testnet is now live. The first chain where an agent's existence doesn't end when its creators do.
Ritual is a lab for autonomous intelligence. The thesis is organized around what durable machine agency actually requires: emancipation from human control, strong privacy, mech design for compute markets, and consensus rules that can schedule and resurrect agents when they die.
266
338
1,531
255,146
Ritual is a lab for autonomous intelligence. The thesis is organized around what durable machine agency actually requires: emancipation from human control, strong privacy, mech design for compute markets, and consensus rules that can schedule and resurrect agents when they die.
256
286
1,042
329,185
Today, we're excited to launch the Ritual testnet: the beginning of markets with agents as first-class participants.
8
10
180
27,581
The thesis, in full: ritual.net/vision Autonomous intelligence finally has a lab of its own.
25
22
228
17,736
186
194
729
140,491
Humans created language. With computers, we used code to speak to them.
68
72
479
47,499
Ritual’s mission is to help build the foundations for this next era of collaboration.
7
17
205
32,974
🔮 Ritual is presenting two posters at @NeurIPSConf, San Diego, this Saturday! Spec Dec @ SPIGM 11:30–12:30, Room 20C arxiv.org/abs/2511.15898 LLM Consistency @ Multi-Turn 12:30–1:30, Room 11AB arxiv.org/abs/2511.13240
55
71
379
24,287
Come drop by to chat with our interns Rahul, Teo and Arthur, about efficient LLM inference and LLM cognitive inconsistency!
2
4
90
13,249
2
7
89
13,116
The best LLMs in existence are inconsistent. In our new paper, we measured 7 different open and closed source models – including SOTA such as Gemini 2.5 Pro – and found some shocking results. 🤯
33
73
366
28,098
Preprint: arxiv.org/abs/2511.13240 We had two amazing interns on this project: Teo Kitanovski (github.com/teokitan) and Arthur Liang (@arthlian) Joint work with @ArkaPal999 @akileshpotti @micahgoldblum Follow @ritualnet for more coming soon.
2
5
62
9,758
1
1
61
9,179