AI Wiki — Knowledge Base

Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations

arXiv:2609.20779v1 Announce Type: cross Abstract: Safety evaluations for large language models rely on surface-form classifiers that report declining harm scores across model generations. We provide e

model-releasesarxiv-cs-ai

18 Sept 2026

Search: “gpt”

From GPT-3 to GPT-5: Mapping their capabilities, scope, limitations, and consequences

LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4

OpenAI GPT-5 System Card

Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations

GPT-Red: Automated Red Teaming via Self-Play at Scale

When the Forger Is the Judge: GPT-Image-2 Cannot Recognize Its Own Faked Documents

Writing for the Reviewer: Defensive Writing in GPT Models

GPT-6-Astra Lights Up Embodied Navigation: Evaluation in Zero-Shot Vision-and-Language Navigation in Continuous Environments

Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking

Why GPT-Style Models Do Not Directly Transfer to Symbolic Music: Compression in the Wrong Coordinate System

How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks

GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment

Evaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain Attacks

DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT

Embodied GPT-5.1: Evidence of a World Model?

Reading Task Failure Off the Activations: A Sparse-Feature Audit of GPT-2 Small on Indirect Object Identification

NRGPT: An Energy-based Alternative for GPT

Detecting GPT-Assisted Writing Using Interpretable Stylometric Features

Taramandal-GPT: Enhancing Astrodynamics Problem-Solving with Knowledge Retrieval and Structured Thinking

Looped GPT-BERT: Trading Parameters for Computation in Small Language Modeling

Evaluating the Effectiveness of Persona Simulation in Opinion Prediction with GPT-4.1

DQAOA-GPT: AI-Accelerated Distributed Quantum Optimization for Combinatorial Problems

SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models

MiniGPT: Rebuilding GPT from First Principles

Commander-GPT: Dividing and Routing for Multimodal Sarcasm Detection

AstraSR: Real-World Thermal Super-Resolution with GPT-6 Astra

Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies

Robot Manipulation with GPT-6-Astra: Body Knowledge, Experience Reuse, Emergent Skills, and Sim2Real Transfer

An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond

GPT-6-Astra in a Navigation Workflow: Behavioral Analysis in Zero-Shot Vision-and-Language Navigation in Continuous Environments

A Benchmark Dataset for MLLM-Generated Image Detection: GPT Image2 & Nano Banana2

MS-GPT: Rethinking MS/MS De Novo Structure Elucidation as Spectrum-Induced Posterior Querying of a Molecule-Language Model

EverydayGPT: Confidence-Gated Routing for Efficient and Safe Hybrid GPT-RAG Conversational QA

Whisper-GPT -- Continuous Discrete Hybrid Representation Language Models For Speech And Music

FUSAR-GPT : A Spatiotemporal Feature-Embedded and Two-Stage Decoupled Visual Language Model for SAR Imagery

A Mechanistic Account of Attention Sinks in GPT-2: One Circuit, Broader Implications for Mitigation

EMG-GPT: Predictive Pretraining on Residual-Quantized EMG Tokens for Hand Pose Estimation

Modernising the Compressed-Domain Video Captioner: A Controlled Study of SigLIP2 and GPT-2 Substitutions

A Tool-Augmented, GPT-4 Chatbot for Real-Time Repository Data Analysis

GPT-Micro: A large language paradigm for accelerated, inexpensive, and thermodynamics-consistent discovery of constitutive models in manufacturing

Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens

Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision

ZonoGPT: Towards An Abstract Domain for Verifying Large GPT Models

LLMs for Survey Text Analysis - A Performance Comparison Between Humans and GPT-5 on Inductive Content Analysis

Decomposing Wrong-Consensus Agreement in LLM Self-Consistency: A GPT-4.1 Case Study

PolymerGPT: Multi-property Optimization with a Decoder-Based GPT Model for Generative Polymer Design

TextRich: A Multi-Domain Benchmark for Detecting AI-Generated Text-Rich Images from GPT-Image-2

Autonomous disproofs of the sum-product conjecture over mathbb R with GPT-5.5 Pro