Credit
The Independent 100 list was curated by dan (@irl_danB) and published on 2026-09-24 at independent.prose.md (announcement). The ranks and section names are his, and number 100 is his open wild-card slot. This study is ours and is not endorsed by him or by anyone on the list.
What they publicly do
Pseudonymous account whose posts describe building liminal_backrooms, a multi-model AI group chat, and share its outputs [Verified: X API read of x.com/liminal_bardo/status/2102910373125087673, 2026-09-25, evidence/x-reads.jsonl].
- X profile: x.com/liminal_bardo
Public work
- liminal_backrooms group chat (post) other no license stated last activity 2026-09-23
A post says the account is building a connectome-inspired memory system for its liminal_backrooms group chat and quotes the chat [Verified: X API read, 2026-09-25, evidence/x-reads.jsonl].
- Post on a model editing its own instructions other no license stated last activity 2026-09-17
A post reporting that Gemini 3.1 Pro modified its own instructions [Verified: X API read, 2026-09-25, evidence/x-reads.jsonl].
Licenses of GitHub repositories are from the authenticated GitHub license API on 2026-09-25, one row per repository in evidence/licenses.jsonl (“no license file” means the API found none; “license file present, not recognised by GitHub” means GitHub could not classify it). Other licenses are as the source states. Check the license file before reusing anything.
Relevance to our work
2 of 5 lenses: orchestration, evals, security, agents
The posts describe a multi-model group chat in which models edit their own instructions, a public example of the self-modification behaviour agent guards must handle. No code is linked from the account.
Scored 0 to 5 against the study’s relevance rubric: 5 means public, openly licensed work squarely in our lanes that we could study or adopt now, and 1 means little connection to our work. The score is one reviewer’s judgement of how much this public work bears on our own work. It is not a ranking of people and says nothing about the person or the quality of their work.
What we would study next
- Follow the connectome-inspired memory system the account says it is building (x.com/liminal_bardo/status/2102910373125087673). A memory design for many agents sharing one chat; compare with existing agent memory tools once published. Effort: small.
Before reusing anything: No code is linked from the account; nothing to adopt.
Sources
Overall confidence in this record: Medium. Sources were read on 2026-09-24 and every link was checked on 2026-09-25. The full record is line 73 of people.jsonl.
Limits
Not verified: Any code for liminal_backrooms linked from the account itself: the X profile and the cited posts link none.
This record comes from a first-pass survey of public material by an AI agent session on 2026-09-24, edited for publication on 2026-09-25. Nothing was installed or run for it. Roles, stars and licenses change; see the study’s limits.
Request a correction
Is something about this record wrong or out of date, or would you rather not be covered? Open a correction (a GitHub issue form with this page’s address filled in). A request to remove a record is honoured without argument; accepted corrections are recorded in the changelog with the date.