cd/sources/allen-institute-ai2· home› sources› Allen Institute (AI2)
cat /sources/allen-institute-ai2.feed | wc -l → 91

Allen Institute (AI2)

articles 91 domain medium.com → page 3/5 feed RSS
20:34
2026-07-12
medium.com
large-language-models

Why prompt injection works: a Transformer-level view

A developer explains prompt injection in large language models from a Transformer architecture perspective, detailing how attention mechanisms and token embeddings enable adversarial inputs to overrid…

21:23
2026-07-11
medium.com
ai-agents

Agentic Memory Transparency

Vektor Slipstream, an AI agent platform, now displays exactly what it remembers about users, aiming to increase transparency and trust. The feature shows users the stored memories and allows them to d…

08:36
2026-07-09
medium.com
artificial-intelligence

Databricks Data and AI Summit 2026 as it was

A developer recounts their experience at the Databricks Data and AI Summit 2026, highlighting key announcements and trends in data engineering and artificial intelligence. The event showcased new feat…

15:24
2026-07-08
medium.com
ai-agents

The Governance Gap Is a Boundary Problem

A developer building open-refinery, a control plane for AI-driven work, discovered that audit trails alone cannot prevent unwanted actions—governance must gate actions before they occur. The tool enfo…

14:49
2026-07-04
medium.com
artificial-intelligence

Why AI Gurus Are Building Toys While the World Needs Architects

A developer argues that the AI industry is focused on building small-scale models and toys rather than the large-scale architectures needed to solve real-world problems. The piece criticizes the lack …

03:18
2026-07-04
medium.com
artificial-intelligence

A Conflict-Free Multi-Agent Ensemble for Claude and Codex

A developer built a conflict-free multi-agent ensemble that orchestrates Claude and Codex to collaborate on coding tasks without stepping on each other's changes. The system uses a shared context and …

23:47
2026-06-30
medium.com
ai-agents

Charter and Harness: What Each One Is

A developer introduces the concepts of 'charter' and 'harness' to clarify how agentic coding systems are governed. The charter is defined as all authored material specifying agent behavior, including …

21:35
2026-06-29
medium.com
artificial-intelligence

Rethinking Software Engineering in the Age of AI

A developer argues that AI is reshaping software engineering, requiring teams to adapt their workflows and skill sets. The post emphasizes that AI tools can automate routine tasks, allowing engineers …

20:55
2026-06-29
medium.com
autonomous-vehicles

AEB: A Case Study Using Comma.ai Dataset (2019)

A developer used Comma.ai's open dataset to build a case study on Automatic Emergency Braking (AEB) systems, demonstrating how the data can be leveraged for safety-critical automotive applications. Th…

09:23
2026-06-29
medium.com
ai-agents

A practical guide to defending your agent memory from attacks

A developer from Vektor Memory published a practical guide on defending agent memory from attacks, detailing common vulnerabilities and mitigation strategies for AI agent systems. The guide covers mem…

10:54
2026-06-28
medium.com
artificial-intelligence

YC AI Investment Trends 2026: Where the US AI Market Is Heading

Y Combinator's 2026 AI investment trends reveal a shift toward applied AI startups in healthcare, defense, and enterprise automation, with a focus on reducing reliance on large language models. The an…

← prev page 3 / 5 next →