ZeroSlop — August 4, 2026
Today: Google Workspace’s continuous approach to mitigating…; Nous Research's NousCoder-14B is an open-source coding…; Architecting Security for Agentic Capabilities in…
12 stories worth knowing about today — AI breakthroughs, launches, and innovations making a difference.
1. Google Workspace’s continuous approach to mitigating indirect prompt injections
Google Security Blog
Posted by Adam Gavish, Google GenAI Security Team Indirect prompt injection (IPI) is an evolving threat vector targeting users of complex AI applications with multiple data sources, such as Workspace with Gemini. This technique enables the attacker to influence the behavior of an LLM by injecting ma…
2. Nous Research’s NousCoder-14B is an open-source coding model landing right in the Claude Code moment
VentureBeat AI
Nous Research , the open-source artificial intelligence startup backed by crypto venture firm Paradigm , released a new competitive programming model on Monday that it says matches or exceeds several larger proprietary systems — trained in just four days using 48 of Nvidia’s latest B200 graphics pro…
3. Architecting Security for Agentic Capabilities in Chrome
Google Security Blog
Posted by Nathan Parker, Chrome security team Chrome has been advancing the web’s security for well over 15 years, and we’re committed to meeting new challenges and opportunities with AI. Billions of people trust Chrome to keep them safe by default, and this is a responsibility we take seriously. Fo…
4. Anthropic launches Cowork, a Claude Desktop agent that works in your files — no coding required
VentureBeat AI
Anthropic released Cowork on Monday, a new AI agent capability that extends the power of its wildly successful Claude Code tool to non-technical users — and according to company insiders, the team built the entire feature in approximately a week and a half, largely using Claude Code itself. The laun…
5. Onton Releases Ontology 1: A Neurosymbolic Search Model That is 2.7x More Accurate than the World’s Best E-commerce Search Engines
MarkTechPost
Onton, a San Francisco-based search and discovery company, has released Ontology 1, a neurosymbolic model for complex, conversational, multimodal product search. On a 90-query benchmark scored by three independent LLM judges, Ontology 1 reached a mean precision@10 of 0.630, against 0.543 for Google …
6. Understanding Alignment in Multimodal LLMs: A Comprehensive Study
Apple ML Journal
Preference alignment has become a crucial component in enhancing the performance of Large Language Models (LLMs), yet its impact in Multimodal Large Language Models (MLLMs) remains comparatively underexplored. Similar to language models, MLLMs for image understanding tasks encounter challenges like …
7. Mitigating prompt injection attacks with a layered defense strategy
Google Security Blog
Posted by Adam Gavish, Google GenAI Security Team With the rapid adoption of generative AI, a new wave of threats is emerging across the industry with the aim of manipulating the AI systems themselves. One such emerging attack vector is indirect prompt injections. Unlike direct prompt injections, wh…
8. Listen Labs raises $69M after viral billboard hiring stunt to scale AI customer interviews
VentureBeat AI
Alfred Wahlforss was running out of options. His startup, Listen Labs , needed to hire over 100 engineers, but competing against Mark Zuckerberg’s $100 million offers seemed impossible. So he spent $5,000 — a fifth of his marketing budget — on a billboard in San Francisco displaying what looked like…
9. Reflex Open Sources XY: A Rust-Backed Super-Fast Python Charting Library That Keeps 100 Million Point Charts Interactive
MarkTechPost
Reflex has released XY, an Apache-2.0 Python charting library that moves rendering work into a native Rust core and a WebGL2 client. It holds roughly 0.08 seconds render time from 10,000 to 100 million points, exports a 10-million-point interactive scatter at 258 KiB, and keeps exact f64 columns in …
10. How to Secure AI Agents, MCP Servers, and LLM Apps in Production
MarkTechPost
AI agents, MCP servers, and LLM apps break the core AppSec assumption that applications do what their code says. This guide walks through a practical see-fix-protect framework: a five-layer agentic AI attack surface map, a 12-point misconfiguration checklist, an evidence-based triage matrix, runtime…
11. Revisiting Classic Thought Experiments to Measure Consciousness for Artificial Intelligence Safety
arXiv CS.AI
arXiv:2608.00001v1 Announce Type: new Abstract: This research note revisits Leibniz’s mill, Turing’s imitation game, and Searle’s Chinese Room through the Conservation-Congruent Encoding (CCE) framework. It formalises a toy symbolic setting in which successful behaviour is measured by task performa…
12. SIRIN: A Unified Toolkit for Detecting Contextual Hallucinations in Retrieval-Augmented and Memory-Grounded LLM Systems
arXiv CS.AI
arXiv:2608.00033v1 Announce Type: new Abstract: SIRIN (Semantic Inconsistency Recognition and Inspection Nexus) is a unified toolkit and interactive web UI for detecting contextual hallucinations (fluent, plausible responses unsupported by the provided evidence) in retrieval-augmented, agentic, and…