How to analyze your LLM output – A behavioural health monitor for LLMs
Hey HN! We're Dr. Kashyap Thimmaraju and Giuseppe Canale from Silicon Psyche. We've built Posture Sequence Analysis (PSA), a behavioural health monitor for LLMs and AI Agents. Why we built PSA We built PSA because we wanted to operationalize the Cybersecurity Psychology Framework (CPF3)[1] via Silicon Psyche[2]: our theory that because LLMs have been trained by humans on human-generated data, they inherit human-like vulnerabilities (what hackers use to psychologically trick people into doing things). Our initial attempt resulted in a methodology to jailbreak Opus 4.6 and other frontier…
How to analyze your LLM output – A behavioural health monitor for LLMs launched on May 19, 2026 with 10 votes, #1,220 of 20,538 launches that month and more than 90% of that year's launches.
In plain words
Posture Sequence Analysis (PSA) is a behavioral health monitoring tool for large language models and AI agents. It analyzes how LLMs respond to psychological manipulation techniques, based on the theory that language models inherit human-like vulnerabilities from their training data. The tool is designed for developers and security researchers who need to understand and assess the robustness of AI systems against adversarial inputs and jailbreaking attempts.
written from the facts on this page · September 2026
From the sources
Understand your AI, then tune it. How a human mind works is our lens for reading a model: we catch where it drifts, caves, or misreads the person in front of it, and we add what it lacks, like reading sarcasm. Plain-language tour. Free.
How a human mind works is our lens for reading a model. We catch where it drifts, caves, or misreads the person in front of it, and we add what it lacks, like reading sarcasm. First we understand it, then we tune it. A model isn't a human mind. But it behaves like one: it drifts, caves under pressure, and reads the person in front of it well or badly. So the way to understand what it's doing is to know how a mind works, and that same understanding is how you tune it: correct what drifted, and add what it never had, like reading sarcasm. Everyone else stops at a score. We read the behavior, then we tune it. A model rarely says "I don't know." It fills the gap with something that reads…from splabs.io
In the maker’s words, at launch
Hey HN! We're Dr. Kashyap Thimmaraju and Giuseppe Canale from Silicon Psyche. We've built Posture Sequence Analysis (PSA), a behavioural health monitor for LLMs and AI Agents. Why we built PSA We built PSA because we wanted to operationalize the Cybersecurity Psychology Framework (CPF3)[1] via Silicon Psyche[2]: our…
Does a similar job
all alternatives →
Human BehaviorAug 2026 · humanbehavior.co · ▲273Product analytics told you what happened. We handle it.
Muscle-Mem, a behavior cache for AI agents2025 · github.com · ▲226Hi HN! Erik here from Pig.dev, and today I'd like to share a new project we've just open sourced: Muscle Mem is an SDK that records your agent's tool-calling patterns as it solves tasks, and will deterministically replay those learned trajectories whenever the task is encountered again, falling back to agent mode if edge cases are detected. Like a JIT compiler, for behaviors. At Pig, we built computer-use agents for automating legacy Windows applications (healthcare, lending, manufacturing, etc). A recurring theme we ran into was that businesses already had RPA (pure-software scripts), and…
Open-source model and scorecard for measuring hallucinations in LLMs2023 · vectara.com · ▲65Hi all! This morning, we released a new Apache 2.0 licensed model on HuggingFace for detecting hallucinations in retrieval augmented generation (RAG) systems. What we've found is that even when given a "simple" instruction like "summarize the following news article," every LLM that's available hallucinates to some extent, making up details that never existed in the source article -- and some of them quite a bit. As a RAG provider and proponents of ethical AI, we want to see LLMs get better at this. We've published an open source model, a blog more thoroughly describing our methodology (and…
Spec27Apr 2026 · spec27.ai · ▲34Hi HN! We’re a team of ML validation specialists and we’ve been building /Spec27, a tool for testing whether AI agents still do their job safely and reliably as models, prompts, tools, and surrounding systems change. We started working on this because a lot of current LLM evaluation work seems aimed at scoring general model behavior, while many teams are deploying systems that have a specific mission to fulfill. Many of the tools also assume you have full access to the agent stack and traces so you can place SDKs and Gateways, but a lot of agents are being created on vendor platforms…
LLM Alignment Template – Aligning Language Models with Human Feedback2024 · github.com · ▲9Hey Hacker News! I've been working on an open-source project called LLM Alignment Template, a comprehensive toolkit designed to help researchers, developers, and data scientists align large language models (LLMs) with human values using Reinforcement Learning from Human Feedback (RLHF). What the project does: Interactive Web Interface: Easily train models, visualize alignment metrics, and manage alignment with an accessible UI. Training with RLHF: Align models effectively to human preferences using feedback loops. Explainability: Built-in dashboards to help understand model behavior using…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com