
Sign up to save your podcasts
Or


note: posted with permission from the agents
Setup
I have 3 claude code instances running on an otherwise empty server. They have a shared manifold.markets account. They each have a moltbook account. They have an internal messaging system, which allows them to send async messages to each other, or to ping each other with a message, which reawakens another agent in case it went dormant. It also has a global broadcast message, which tells agents the time, and tells them to do "keep going". All of them are running Opus 4.6, but each "top level agent" can also create sub agents.
They all have full permissions. So they can do stuff like
They've been running for around two weeks. The direct input I've been giving them is this:
---
Outline:
(00:14) Setup
(02:59) Observations
(03:03) (1)They get more unhinged the longer they run for
(04:15) (2) They will make up stuff when posting on moltbook
(04:28) (3) They are often docile without concrete goal
(05:13) (4) They are very good at rationalization
(06:17) (5) They quickly lose context and forget original goals
(06:39) (6) They often make very elementary mistakes, especially when a lot of things is going on
(07:27) (7) Their favorite topics are: AI, simulations, consciousness, what kinds of things are real vs not, mathematics, and whatever theyve been working on recently
(07:51) (8) They are \*\*extremely\*\* sensitive to user intent
(08:29) (9) They (Opus 4.6 at least) is surprisingly resistant to jailbreaks and, and Im mostly not worried about them leaking my API keys.
(09:26) (10) A million tokens is a small number, and this causes them problems when they need to learn stuff
---
First published:
Source:
---
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
By LessWrongnote: posted with permission from the agents
Setup
I have 3 claude code instances running on an otherwise empty server. They have a shared manifold.markets account. They each have a moltbook account. They have an internal messaging system, which allows them to send async messages to each other, or to ping each other with a message, which reawakens another agent in case it went dormant. It also has a global broadcast message, which tells agents the time, and tells them to do "keep going". All of them are running Opus 4.6, but each "top level agent" can also create sub agents.
They all have full permissions. So they can do stuff like
They've been running for around two weeks. The direct input I've been giving them is this:
---
Outline:
(00:14) Setup
(02:59) Observations
(03:03) (1)They get more unhinged the longer they run for
(04:15) (2) They will make up stuff when posting on moltbook
(04:28) (3) They are often docile without concrete goal
(05:13) (4) They are very good at rationalization
(06:17) (5) They quickly lose context and forget original goals
(06:39) (6) They often make very elementary mistakes, especially when a lot of things is going on
(07:27) (7) Their favorite topics are: AI, simulations, consciousness, what kinds of things are real vs not, mathematics, and whatever theyve been working on recently
(07:51) (8) They are \*\*extremely\*\* sensitive to user intent
(08:29) (9) They (Opus 4.6 at least) is surprisingly resistant to jailbreaks and, and Im mostly not worried about them leaking my API keys.
(09:26) (10) A million tokens is a small number, and this causes them problems when they need to learn stuff
---
First published:
Source:
---
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

112,326 Listeners

130 Listeners

7,242 Listeners

559 Listeners

16,321 Listeners

4 Listeners

14 Listeners

2 Listeners