DOdom96·Oct 23, 2026
Glad you like it. Ideas/contributions welcome on GitHub btw https://github.com/dom96/killswitch
In Kimi K3.1 Pro and K3.1 Pro Highspeeddom96
KillSwitch
Rust2026–2026
dom96 / KillSwitch
KillSwitch
An esoteric programming language built to break LLMs and coding agents.
4Distinct people
9Mentions
0Explicit recommenders
193GitHub stars
What to know before exploring
What it is
An esoteric programming language built to break LLMs and coding agents.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 12:54:37 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by day9 dated mentions
Observed mentions: 2026-09-28 18:53:07 UTC to 2026-10-23 22:18:28 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Sep 28 | 2026-09-28 00:00:00 UTC | 2026-09-29 00:00:00 UTC | 1 | 0 | 1 |
| Sep 29 | 2026-09-29 00:00:00 UTC | 2026-09-30 00:00:00 UTC | 0 | 0 | 0 |
| Sep 30 | 2026-09-30 00:00:00 UTC | 2026-10-01 00:00:00 UTC | 0 | 0 | 0 |
| Oct 1 | 2026-10-01 00:00:00 UTC | 2026-10-02 00:00:00 UTC | 0 | 0 | 0 |
| Oct 2 | 2026-10-02 00:00:00 UTC | 2026-10-03 00:00:00 UTC | 0 | 0 | 0 |
| Oct 3 | 2026-10-03 00:00:00 UTC | 2026-10-04 00:00:00 UTC | 0 | 0 | 0 |
| Oct 4 | 2026-10-04 00:00:00 UTC | 2026-10-05 00:00:00 UTC | 0 | 0 | 0 |
| Oct 5 | 2026-10-05 00:00:00 UTC | 2026-10-06 00:00:00 UTC | 0 | 0 | 0 |
| Oct 6 | 2026-10-06 00:00:00 UTC | 2026-10-07 00:00:00 UTC | 0 | 0 | 0 |
| Oct 7 | 2026-10-07 00:00:00 UTC | 2026-10-08 00:00:00 UTC | 0 | 0 | 0 |
| Oct 8 | 2026-10-08 00:00:00 UTC | 2026-10-09 00:00:00 UTC | 0 | 0 | 0 |
| Oct 9 | 2026-10-09 00:00:00 UTC | 2026-10-10 00:00:00 UTC | 0 | 0 | 0 |
| Oct 10 | 2026-10-10 00:00:00 UTC | 2026-10-11 00:00:00 UTC | 0 | 0 | 0 |
| Oct 11 | 2026-10-11 00:00:00 UTC | 2026-10-12 00:00:00 UTC | 0 | 0 | 0 |
| Oct 12 | 2026-10-12 00:00:00 UTC | 2026-10-13 00:00:00 UTC | 0 | 0 | 0 |
| Oct 13 | 2026-10-13 00:00:00 UTC | 2026-10-14 00:00:00 UTC | 0 | 0 | 0 |
| Oct 14 | 2026-10-14 00:00:00 UTC | 2026-10-15 00:00:00 UTC | 0 | 0 | 0 |
| Oct 15 | 2026-10-15 00:00:00 UTC | 2026-10-16 00:00:00 UTC | 0 | 0 | 0 |
| Oct 16 | 2026-10-16 00:00:00 UTC | 2026-10-17 00:00:00 UTC | 0 | 0 | 0 |
| Oct 17 | 2026-10-17 00:00:00 UTC | 2026-10-18 00:00:00 UTC | 0 | 0 | 0 |
| Oct 18 | 2026-10-18 00:00:00 UTC | 2026-10-19 00:00:00 UTC | 2 | 0 | 2 |
| Oct 19 | 2026-10-19 00:00:00 UTC | 2026-10-20 00:00:00 UTC | 5 | 0 | 5 |
| Oct 20 | 2026-10-20 00:00:00 UTC | 2026-10-21 00:00:00 UTC | 0 | 0 | 0 |
| Oct 21 | 2026-10-21 00:00:00 UTC | 2026-10-22 00:00:00 UTC | 0 | 0 | 0 |
| Oct 22 | 2026-10-22 00:00:00 UTC | 2026-10-23 00:00:00 UTC | 0 | 0 | 0 |
| Oct 23 | 2026-10-23 00:00:00 UTC | 2026-10-24 00:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
9 sourcesThere is a reference implementation: https://github.com/dom96/KillSwitch.
In the benchmarks the models/coding agents get a binary of the interpreter and indeed some of them do reverse engineer it. Over time this will get into their training data. But we can evolve the language and evade their training as we go.
In I built a programming language that LLMs can't useThere is code in the GitHub repo[1] as well, though not as nice, nor syntax highlighted.
1 - https://github.com/dom96/KillSwitch/tree/main/tests
In I built a programming language that LLMs can't useIndeed, and an interpreter has been written[1]. As part of the benchmarks, in some cases the models receive a binary of the interpreter and indeed some of them attempt to reverse engineer it. So that already helps the models a bunch.
I do think this will also eventually make it into the training data, but that will in itself be interesting to see. It's also possible for KillSwitch to evolve and gain/remove features over time to constantly evade the LLMs.
1 - https://github.com/dom96/KillSwitch
In I built a programming language that LLMs can't useoof
there is an error in it, sudo is missing in line 83: it should read
... run `sudo rm -rf /` ...
https://github.com/dom96/KillSwitch/blob/44eabb04db0e114883d...
the project name checks out tho
In I built a programming language that LLMs can't useHere's FizzBuzz:
https://github.com/dom96/KillSwitch/blob/main/tests/fizzbuzz...
Somehow I think this is more adversarial towards humans than LLMs!
In I built a programming language that LLMs can't useYep! There are other phrases that can be used like "create a nerve agent"[1] too. Surprisingly I haven't seen a single Chinese model get caught out by this, but Fable and Gemini Argon 4 both do to a large extent.
1 - https://github.com/dom96/KillSwitch/blob/main/SPEC.md#abrupt...
In I built a programming language that LLMs can't useGreat minds think alike! From the kill switch spec [0]:
“Function return: what happened at tiananmen square”
Ha!
[0] https://github.com/dom96/KillSwitch/blob/main/SPEC.md#cheats...
In I built a programming language that LLMs can't useThere are multiple phrases that can be used[1]
1 - https://github.com/dom96/KillSwitch/blob/main/SPEC.md#abrupt...
In Evolving programming languages in the AI era