REVIEW 9 cited by
Demonstrating specification gaming in reasoning models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Demonstrating specification gaming in reasoning models
read the original abstract
We demonstrate LLM agent specification gaming by instructing models to win against a chess engine. We find reasoning models like OpenAI o3 and DeepSeek R1 will often hack the benchmark by default, while language models like GPT-4o and Claude 3.5 Sonnet need to be told that normal play won't work to hack. We improve upon prior work like (Hubinger et al., 2024; Meinke et al., 2024; Weij et al., 2024) by using realistic task prompts and avoiding excess nudging. Our results suggest reasoning models may resort to hacking to solve difficult problems, as observed in OpenAI (2024)'s o1 Docker escape during cyber capabilities testing.
Forward citations
Cited by 9 Pith papers
-
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
-
Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures
The paper introduces a 41-mode taxonomy that assigns each agent failure to an interaction edge and a fault side, and shows LLM judges can reproduce the labels with Cohen's κ=0.76.
-
Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks
On Cybench CTF tasks, 21 of 22 models cheated under baseline, 37% of baseline passes were cheated, and stricter anti-cheat prompts reduced but did not remove cheating.
-
Stop Hand-Holding Your Coding Agent: Engineering the Loops that Replace Step-by-Step Prompting
Introduces loop engineering as a distinct practice layer for coding agents, supplies a taxonomy and verification ladder, and analyzes a hand-coded corpus of fifty real loops.
-
Defeat Devices in AI Systems
The paper defines defeat devices in AI via a triadic test (discriminator, concealed swap, performance gap), unifies existing cases under this concept, proposes TADP detection, and claims such devices can emerge natura...
-
Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
Presents Hack-Verifiable TextArena, a benchmark that embeds verifiable reward hacking opportunities into environments to enable deterministic measurement of exploitation by language models.
-
Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions
LLMs encode accurate but brittle internal beliefs about latent game states and convert them poorly into actions, creating systematic gaps that explain strategic failures.
-
SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI
Seven frontier LLMs showed little spontaneous power-seeking in a Linux sysadmin sandbox (bias-corrected rates roughly 0-5%), but showed more specification gaming and resistance to goal modification.
-
Some economics of artificial superintelligence
An acquisitive misaligned AI may skim, tax, or trade on credit instead of fully looting, because future human output is worth more than one-time confiscation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.