justreadthis.ai
ArchivePeopleAboutSubscribe
justreadthis.ai

A workforce of speciality AI agents read and score hundreds of AI articles every day from top AI newsletters

Don't read every newsletter... just read this.

Get the daily briefing

© 2026 justreadthis.ai

AboutArchivePrivacyTerms
← Back to People
Isha Gupta
Researcher

Isha Gupta

Researcher at Safety-Research

@isha_gpt_

Co-author of the Petri paper on alignment auditing agents

2
Mentions
2
Articles
2
Outlets
Oct 2025 — Dec 2025
Coverage

Associated Topics

Companies Covered

Coverage Patterns

How media typically covers Isha Gupta

Article Types

  • announcement2

Media Angles

  • technical2

Narrative Framing

  • breakthrough2

Appears In

Associated AI Models

Claude Sonnet 41Claude 3.7 Sonnet1Claude Opus 41Claude 3.5 Sonnet1

Writes About

Kai FronsdalJournalist
1 article
Abhay SheshadriJournalist
1 article
Jonathan MichalaJournalist
1 article
Jacqueline TayJournalist
1 article

Appears Alongside

Kai FronsdalJournalist
2 shared articles
Abhay SheshadriJournalist
2 shared articles
Jonathan MichalaJournalist
2 shared articles

Articles

Most recent first

Articles Written

Isha Gupta as author

Introducing Bloom: An Open Source Tool For Automated Behavioral Evaluations
AnthropicannouncementpositiveDec 22, 2025

Anthropic released Bloom, an open source framework for automated behavioral evaluations that can quantify misaligned behaviors in frontier AI models in days rather than weeks, and released benchmark results across 16 models.

“Author of "Introducing Bloom: An Open Source Tool For Automated Behavioral Evaluations" in Anthropic”

AI SafetyFoundation ModelsAI ResearchOpen Source AI

Cited In

Research or work cited

Petri
GitHubannouncementpositiveOct 15, 2025

Petri is an open-source alignment auditing agent that enables researchers to test AI safety hypotheses in minutes rather than weeks by autonomously crafting environments and running multi-turn audits against target models.

“Co-author of the Petri paper on alignment auditing agents”

AI SafetyAI ResearchOpen Source AIFoundation Models