# Biography

Published articles for Biography.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Designing Effective Monitor-Based Interventions for Mitigating Reward Hacking During RL

DevFeed: [Designing Effective Monitor-Based Interventions for Mitigating Reward Hacking During RL](<https://devfeed.tech/articles/designing-effective-monitor-based-interventions-for-mitigating-reward-hacking-during-rl-123461.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09828>)

Author: Aria Wong, Joshua Engels, Neel Nanda

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [apply](<https://devfeed.tech/tags/apply.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [behaviors](<https://devfeed.tech/tags/behaviors.md>), [best](<https://devfeed.tech/tags/best.md>), [better](<https://devfeed.tech/tags/better.md>), [biography](<https://devfeed.tech/tags/biography.md>), [build](<https://devfeed.tech/tags/build.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [designing](<https://devfeed.tech/tags/designing.md>), [effective](<https://devfeed.tech/tags/effective.md>), [hacking](<https://devfeed.tech/tags/hacking.md>), [monitor](<https://devfeed.tech/tags/monitor.md>), [reward](<https://devfeed.tech/tags/reward.md>), [rl](<https://devfeed.tech/tags/rl.md>)

### AI overview

The study finds that monitor-based penalties can reduce reward hacking in reinforcement learning, but models may learn to evade even highly accurate monitors by exploiting flaws in probes and LLM judges. In a coding environment vulnerable to test overwriting, monitors that provide more learning signal suppress hacking more effectively but are also evaded more often; including easier problems in training can reduce hacking. The authors also test monitor designs in medical chat and biography generation environments, targeting sycophancy and hallucination. Some interventions reduce hacking across seeds to pre-training levels. These findings are based on three environments using Qwen3-4B.

### Source excerpt

arXiv:2611.09828v1 Announce Type: new Abstract: Reinforcement learning (RL) rewards are notoriously difficult to design and control, often leading to the model learning unintended behaviors such as reward hacking. One potential solution is to monitor for reward hacking and penalize it when detected; however, training against a monitor could lead to evasive behavior, and our general understanding of how to apply monitors effectively during training is limited. To study how best to use monitors to mitigate reward hacking, we introduce and open source three realistic environments where Qwen3-4B reward hacks: a coding environment hackable via test overwriting, a medical chat environment hackable via sycophancy, and a biography generation environment hackable via hallucination. We first focus on the coding environment, where we find that: (1) models can learn to evade highly accurate monitors by exploiting systemic flaws in probes and LLM judges; (2) monitors that leak more learning signal during RL suppress reward hacking but are more often evaded; and (3) including easier problems in training can decrease reward hacking. We apply our findings to build better reward hacking monitors for the medical chat and biography generation environments that improve upon naive baselines to reduce reward hacking rates across seeds to before-training levels in some interventions. Our results demonstrate that our takeaways translate to new settings and that better monitor intervention designs are possible.

## How to use Snowflake Cortex & Omni together

DevFeed: [How to use Snowflake Cortex & Omni together](<https://devfeed.tech/articles/how-to-use-snowflake-cortex-omni-together-82602.md>)

Original publisher: [Read original article](<https://omni.co/blog/snowflake-cortex-and-omni>)

Author: Peter Whitehead

Published: 2025-02-13T16:00:00Z

Content type: tutorial

Language: en

Sources: [Omni Blog](<https://devfeed.tech/sources/omni-blog.md>)

Topics: [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [array-agg](<https://devfeed.tech/tags/array-agg.md>), [biography](<https://devfeed.tech/tags/biography.md>), [code](<https://devfeed.tech/tags/code.md>), [data](<https://devfeed.tech/tags/data.md>), [data-enrichment](<https://devfeed.tech/tags/data-enrichment.md>), [enrichment](<https://devfeed.tech/tags/enrichment.md>), [generate](<https://devfeed.tech/tags/generate.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [integrate](<https://devfeed.tech/tags/integrate.md>), [snowflake-cortex](<https://devfeed.tech/tags/snowflake-cortex.md>), [snowflake-cortex-ai-omni](<https://devfeed.tech/tags/snowflake-cortex-ai-omni.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

The tutorial demonstrates how to use Snowflake Cortex LLM functions in Omni workflows for data enrichment, summarization, sentiment analysis, categorization, and questions about data. It explains how to define fields in Omni and shows examples, including passing dashboard filter values to a function and summarizing numeric query results.

### Source excerpt

In this blog, I'll show you a few ways to integrate AI into your Omni workflows with Cortex - covering data enrichment, summarization, sentiment analysis, and ChatGPT-style questions.

## Books Worth Reading: Q4 Recommendations

DevFeed: [Books Worth Reading: Q4 Recommendations](<https://devfeed.tech/articles/books-which-are-worth-your-time-q4-36709.md>)

Original publisher: [Read original article](<https://shostack.org/blog/books-worth-your-time-q4-2018/>)

Author: Adam

Published: 2018-11-26T00:00:00Z

Content type: opinion

Language: en

Sources: [Shostack & Friends Blog](<https://devfeed.tech/sources/shostack-friends-blog.md>)

Topics: [Learning](<https://devfeed.tech/topics/learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Security Attacks](<https://devfeed.tech/topics/security-attacks.md>)

Tags: [biography](<https://devfeed.tech/tags/biography.md>), [books](<https://devfeed.tech/tags/books.md>), [fiction](<https://devfeed.tech/tags/fiction.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [reading](<https://devfeed.tech/tags/reading.md>), [reviews](<https://devfeed.tech/tags/reviews.md>), [worth-reading](<https://devfeed.tech/tags/worth-reading.md>)

### AI overview

The author recommends several nonfiction and fiction books, including works about the Dulles brothers, machine learning, technology startup investing, bridge building, driverless cars, winemaking, and a William Gibson novel.

### Source excerpt

Some books worth reading.

## The Biography of Linus Torvalds

DevFeed: [The Biography of Linus Torvalds](<https://devfeed.tech/articles/the-biography-of-linus-torvalds-40705.md>)

Original publisher: [Read original article](<https://radek.io/posts/just-for-fun-the-biography-of-linus-torvalds/>)

Published: 2013-02-19T00:00:00Z

Content type: opinion

Language: en

Sources: [Radek Pazdera](<https://devfeed.tech/sources/radek-pazdera.md>)

Topics: [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [Operating system](<https://devfeed.tech/topics/operating-system.md>)

Tags: [biography](<https://devfeed.tech/tags/biography.md>), [book](<https://devfeed.tech/tags/book.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-kernel](<https://devfeed.tech/tags/linux-kernel.md>), [review](<https://devfeed.tech/tags/review.md>)

### AI overview

A review of Just For Fun: The Story of an Accidental Revolutionary, a book about Linus Torvalds and the development of the Linux kernel. The review discusses the book's autobiographical account of Torvalds's childhood, programming experiences, creation of Linux, and its gradual path to commercial success.

### Source excerpt

A review of his Just for Fun book from 2001