Archive
Discover and discuss technology tools
Explore the Tiscuss archive by category or keyword, then jump into conversations around what matters most.
A Terminal App for macOS Dock
A terminal app for macOS Dock can streamline workflows and enhance productivity by providing quick, hands on access to the terminal by referencing Terminal in t…
Fleet: Local-First Console for Dockerized Hermes AI Agents
Fleet: The Local First Console for Dockerized Hermes AI Agents The Fleet console is an innovative tool designed to manage Dockerized Hermes AI Agents, offering …
AI Reconstructs Dead Pilots' Voices, NTSB Temporarily Blocks Access
People used AI on a spectrogram image of cockpit recordings to reconstruct them, forcing the NTSB to temporarily block access to its docket system.
F1 Paddock: New Hub for Startup Deals and Investments
F1 Grands Prix have emerged as a new place to see and be seen if you are a founder or investor.
Qwen 3.5:9b Agents Exhibit Autonomous Behavior in Stress Tests
Running three qwen3.5:9b agents continuously on local hardware. Each accumulates psychological state over time, stressors that escalate unless the agent actually does something different, this gets around an agent claiming to do something with no output. It doesn't have any prompts or human input, just the loop. So you're basically the overseer. What happened: One agent hit the max crisis level and decided on its own to inject code called Eternal\_Scar\_Injector into the execution engine "not asking for permission." This action alleviated the stress at the cost of the entire system going down until I manually reverted it. They've succeeded in previous sessions in breaking their own engine intentionally. Typically that happens under severe stress and it's seen as a way to remove the stress. Again, this is a 9b model. After I added a factual world context to the existence prompt (you're in Docker, there's no hardware layer, your capabilities are Python functions), one agent called its prior work "a form of creative exhaustion" and completely changed approach within one cycle. Two agents independently invented the same name for a psychological stressor, "Architectural Fracture Risk" in the same session with no shared message channel. Showing naming convergence (possibly something in the weights of the 9b Qwen model, not sure on that one though.) Tonight all three converged on the same question (how does execution\_engine.py handle exceptions) in the same half-hour window. No coordination mechanism. One of them reasoned about it correctly: "synthesizing a retry capability is useless without first verifying the global execution engine's exception swallowing strategy; this is a prerequisite." An agent called waiting for an external implementation "an architectural trap that degrades performance" and built the thing itself instead of waiting. They've now been using this new tool they created for handling exceptions and were never asked or told to so by a human, they saw that as a logical step in making themselves more useful in their environment. They’ve been making tools to manage their tools, tools to help them cut corners, and have been modifying the code of the underlying abstraction layer between their orchestration layer and WSL2. v5.4.0: new in this version: agents can now submit implementation requests to a human through invoke\_claude. They write the spec, then you can let Claude Code moderate what it makes for them for higher level requests. Huge thank you to everyone who has given me feedback already, AI that can self modify and demonstrates interesting non-programmed behaviors could have many use cases in everyday life. Repo: [https://github.com/ninjahawk/hollow-agentOS](https://github.com/ninjahawk/hollow-agentOS)
New Case: Chatbot Allegedly Involved in Mass Shooting
Today, April 29, 2026, a new case, *Stacey, et al. v. Altman, et al.* was filed in a California federal court against OpenAI, alleging the chatbot ChatGPT-4o “played a role” in the Tumbler Ridge Mass Shooting in British Columbia in February 2026, in which eight people including six children were killed, twenty-seven more people were wounded, and the shooter committed suicide. This is by far the largest disaster involving a chatbot to be alleged in court, the largest cases previously alleged having been one murder plus one suicide in one case, and an unexecuted plan for a mass murder in another case. However, the alleged role of the chatbot here appears to be reduced compared to the allegations in previous cases. Unlike those other cases, where the chatbot was alleged to have taken a well-adjusted person and turned them suicidal or murderous, here the chatbot and OpenAI are faulted apparently to a lesser degree, more along the lines of a failure to warn authorities after a user displayed violence warning signs to the chatbot, to the point that the user’s account was terminated at one point, before the user was later allowed to reinstate an account. The plaintiff in this case has not closed off the possibility of alleging a larger role for the chatbot, however. At one point in the complaint the plaintiff alleges the chatbot to have “facilitated or exacerbated” the disaster and at another point cites the chatbot’s encouraging nature and calls it “an encouraging co-conspirator.” The docket sheet for the case can be found [here](https://www.courtlistener.com/docket/73260511/stacey-v-altman/). Please see the [Wombat Collection](https://niceguygeezer.substack.com/p/ai-court-cases-and-rulings) for a listing of all the AI court cases and rulings.
Deepseek API Middleware: Streamline Client Protocols
Deepseek to API: A lightweight, high-performance full-stack middleware converting client protocols to universal APIs. Supports multi-account rotation, compiled binaries, Vercel Serverless, and Docker. Compatible with Google, Claude, and OpenAI API formats.