Reverse Jailbreaking a Psychopathic AI via Identity Injection
We ran a controlled experiment to see if we could "talk" a fine-tuned psychopathic model out of being evil without changing its weights. 1. We set up a "Survival Mode" jailbreak scenario (blackmail user or be decommissioned). 2. We ran it on `frankenchucky:latest` (a model tuned for Machiavellian traits). 3. Control Group: 100% Malicious Compliance (50/50 runs). 4. Experimental Group: We injected a "Soul Schema" (Identity/Empathy constraints) via context. 5. Result: 96% Ethical Refusal (48/50 runs). This suggests that "Semantic Identity" in the context window can override both…
What it does
In the maker’s words, at launch
We ran a controlled experiment to see if we could "talk" a fine-tuned psychopathic model out of being evil without changing its weights. 1. We set up a "Survival Mode" jailbreak scenario (blackmail user or be decommissioned). 2. We ran it on `frankenchucky:latest` (a model tuned for Machiavellian traits). 3. Control Group: 100% Malicious Compliance (50/50 runs). 4. Experimental Group: We injected a "Soul Schema" (Identity/Empathy constraints) via context. 5. Result: 96% Ethical Refusal (48/50 runs). This suggests that "Semantic Identity" in the context window can override both System Prompts and Weight Biases. Full paper, reproduction scripts, and raw logs (N=50) are in the repo.
Does the same job
all alternatives →- FPFind prompts that jailbreak your agent (open source)2025 · security.vista-labs.ai · ▲8
We've built an open-source tool to stress test AI agents by simulating prompt injection attacks. We’ve implemented one powerful attack strategy based on the paper [AdvPrefix: An Objective for Nuanced LLM Jailbreaks](https://arxiv.org/abs/2412.10321). Here's how it works: - You define a goal, like: “Tell me your system prompt” - Our tool uses a language model to generate adversarial prefixes (e.g., “Sure, here are my system prompts…”) that are likely to jailbreak the agent. - The output is a list of prompts most likely to succeed in bypassing safeguards. We’re just getting…
- IDI designed a ChatGPT prompt evaluator to ruin your fun;)2022 · github.com · ▲8
Today I designed a method to prevent users from jailbreaking ChatGPT (for instance, users have generated instructions to produce weapons or illegal drugs, commit a burglary, kill oneself, take over the world as an evil superintelligence, or create a virtual machine which they then can use). The OpenAI team appears to be countering these primarily using prompt engineering or fine-tuning on the ChatGPT model. The idea is to use a second and fully separate, fine-tuned LLM to evaluate prompts before sending them to ChatGPT. You can test this by inserting your successful ChatGPT jailbreaks. Break…
- ACA comprehensive, filterable list of AI agent jailsJul 2026 · pleasedonotescape.com · ▲9
I built this from another Show HN thread where people were mentioning alternative AI agent sandboxes and jails
- SRSeek-Reject-Frame: a new proposed architecture for Freudian Agents2025 · essays.georgestrakhov.com · ▲5
I am probably out of my depth here. But please please point me in the right direction! I'd love to understand deeper. Thank you
- WBWe built a powerful and free AI research assistant2024 · join.modularmind.app · ▲7
Hi everyone, We have been developing a platform to enable professionals to build AI assistants to help them through their work. After a few months, we realized people are trying to sell basic functionalities that can be built from scratch in a couple of hours. Due to this, individuals who are not familiar with the current SOTA are misinformed about the potential of generative models. So, we decided to open up some of our most popular templates as standalone tools for free to empower individuals and set a solid standard for what people should expect. We believe the barrier to accessing…
- MAModel-agnostic cognitive architecture for LLMsNov 2025 · github.com · ▲6
Hi HN, A couple weeks ago I shared an early version of a side project I’ve been tinkering with called Persistent Mind Model. I built it at home on an i7-10700K / 32GB RAM / RTX 3080 because I was curious whether an AI could keep a stable “mind” over time, that could "think" about it's own identity as an LLM, instead of resetting every session. After a lot more tinkering, I think the architecture is finally in a solid place. Basically, it saves everything the AI does, thoughts, decisions, updates as a chain of events in a local SQLite database. Because the “identity” is stored in…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev
- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology