GPT-4o

Named by 13 kept items in this workspace.

12 items name it under models and 1 under classification.key entities.

The items that name it 13

LFM2.5-24B-A2B: Built for fast on-device agents
articleas classification.key entities2026-10-14
Character.AI Files for Bankruptcy as Disney Bids $20 Million—And Users Get Grief Resources
articleas models2026-10-13
AI models may be capable of self-replicating without access to a datacenter
writeupas models2026-10-12
Qwen3.8 27B addition in words
writeupas models2026-10-04
Aleph Alpha Kolibri: How the sovereign German LLM works
articleas models2026-10-03
ShadowSafin/Synapass
repoas models2026-10-01
Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI
talkas models2026-09-21It is written here as GPT4o.
ChatGPT Images 2.5 System Card
advisoryas models2026-09-08
headroomlabs-ai/headroom
repoas models2026-09-07
ThorOdinson246/whatisit-nl2sh
repoas models2026-07-29
Harness Engineering for Self-Improvement
articleas models2026-07-04
Qwen3.8-27B (Apache-2.0, multimodal dense, 262k ctx)
repoas models
Distributed Attacks in Persistent-State AI Control
paperas models

In every workspace you can read 21

Security

Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol
paper2026-10-26
ORCAGen: Orchestrating Context-Aware Malware Deception with RAG-Guided Generative AI
paper2026-10-08It is written here as GPT-4o (LLM evaluated).
Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks
paper2026-10-02
Static Defenses vs. Dynamic Exploits: Why A2AS Fails at the Runtime
writeup2026-09-23
GhostSplice: Malicious MCP Servers Split Exfiltration to Bypass Guardrails
article2026-08-19
Microsoft Agent Governance Toolkit
repo2026-05-06
Distributed Attacks in Persistent-State AI Control
paper
Sockpuppeting: How a Single Line Can Bypass LLM Safety Guardrails | TrendAI (US)
writeup

AI

LFM2.5-24B-A2B: Built for fast on-device agents
article2026-10-14
Character.AI Files for Bankruptcy as Disney Bids $20 Million—And Users Get Grief Resources
article2026-10-13
AI models may be capable of self-replicating without access to a datacenter
writeup2026-10-12
Qwen3.8 27B addition in words
writeup2026-10-04
Aleph Alpha Kolibri: How the sovereign German LLM works
article2026-10-03
ShadowSafin/Synapass
repo2026-10-01
Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI
talk2026-09-21It is written here as GPT4o.
ChatGPT Images 2.5 System Card
advisory2026-09-08
headroomlabs-ai/headroom
repo2026-09-07
ThorOdinson246/whatisit-nl2sh
repo2026-07-29
Harness Engineering for Self-Improvement
article2026-07-04
Qwen3.8-27B (Apache-2.0, multimodal dense, 262k ctx)
repo
Distributed Attacks in Persistent-State AI Control
paper

All technologies in this workspace.