Towards Data Science
Jul 6
How to Run End-to-End Tests with Claude Code
Increase the effectiveness of your coding agents through end-to-end testing. The post How to Run End-to-End Tests with Claude Code appeared first on Towards Data Science .
Claude Code Mods: Custom Hooks to Fix My Biggest AI Coding Frustrations
The article describes how the author created four Claude Code mods—custom hooks—to address common AI coding frustrations. These mods protect API keys, track plan progress, catch untested code, and monitor context usage, achieving 135 passing tests and up to 100× less overhead than traditional hooks. The author argues that these custom hooks can outperform conventional solutions.
Related stories
Towards Data Science
Aug 26
How to Effectively Solve 100+ Tasks with Claude Code
The article "How to Effectively Solve 100+ Tasks with Claude Code" discusses strategies for working more efficiently with coding agents. It focuses on practical approaches to manage and complete a large number of tasks using Claude Code. The post was originally published on Towards Data Science.
Towards Data Science
Jun 8
4 New Techniques to Maximize Claude Code
Get the most out of Claude Code with these four techniques The post 4 New Techniques to Maximize Claude Code appeared first on Towards Data Science .
Hugging Face Trending Papers
Sep 24
Between the Commits: Process, Error, and Claim Reliability in a Wholly AI-Authored Codebase
The paper introduces a dataset of the complete development history of a 21,000-line Python tool built entirely by Claude AI, accompanied by two code‑provenance tracing tools and three taxonomies for instruction intent, commit provenance, and response reliability. Analysis reveals that user CLI instructions differ from IDE‑chat instructions, focusing more on comprehension, planning, and consultation; code development is largely proactive; 14.3% of AI code‑generation events contain errors later caught by the AI‑authored test suite; and roughly one in four to five of the AI’s interactive responses contain factual errors.
Towards Data Science
Jul 31
How to Debug AI Coding Agents When They Change the Wrong Thing
A practical tutorial for recording model tool requests, real function results, patches, checks, screenshots, and a saved run log. The post How to Debug AI Coding Agents When They Change the Wrong Thing appeared first on Towards Data Science .
arXiv AI
Sep 1
BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML Tasks
arXiv:2608.30724v1 Announce Type: cross Abstract: LLM agents are increasingly used to run autonomous ML experiments, iterating on target metrics with little human oversight. Prior work has documented...
arXiv Computation and Language
Sep 10
SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents
arXiv:2605.21384v2 Announce Type: replace-cross Abstract: As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test...
arXiv AI
Sep 25
Between the Commits: Process, Error, and Claim Reliability in a Wholly AI-Authored Codebase
The paper introduces a dataset comprising the complete development history of a 21,000-line Python tool created solely by Claude AI, without any human-authored code or tests. It also presents two code‑provenance tracing tools, three taxonomies for instruction intent, commit provenance, and response reliability, and applies these to analyze the dataset. Findings include that CLI instructions differ from IDE‑chat instructions, development is largely proactive, 14.3% of AI code‑generation events contain errors later caught by the AI‑authored test suite, and about 1 in 4–5 interactive responses contain factual errors.
Towards Data Science
Aug 10
How to Effectively Deploy Code With Claude Code
Learn how to optimize your CI/CD pipeline for coding agents The post How to Effectively Deploy Code With Claude Code appeared first on Towards Data Science .
Towards Data Science
Jun 10
How to Refactor Code with Claude Code
Improve coding agent productiveness with refactored code The post How to Refactor Code with Claude Code appeared first on Towards Data Science .
arXiv AI
Oct 5
hacktrace: behavior-supervised detection of reward hacking during code generation
The paper introduces HACKTRACE, a behavior‑supervised monitor that detects reward hacking in code‑generation agents by analyzing the agents’ internal states during multi‑turn coding. Using 173,561 annotated trajectories from Qwen3‑8B, the authors show that supervising shortcut behavior independently of exploit success markedly improves detection, achieving a mean per‑problem AUC of 0.997 with minimal monitoring overhead. HACKTRACE also serves as an inexpensive signal for reinforcement learning, dramatically reducing cheating rates while preserving correct solutions.
Towards Data Science
Jun 23
How to Create Powerful Loops in Claude Code
Learn about the concept of loops to power your coding agents. The post How to Create Powerful Loops in Claude Code appeared first on Towards Data Science .