Gemini 3.5 Flash

Named by 10 kept items in this workspace.

The items that name it 10

[AINews] OpenAI’s Patch the Planet program is 1 of 2 parties to discover PHP2Shell vulnerabilities in core PHP affecting 70% of the web, using GPT-5.6 Sol; coordinated response over 2 months
article2026-10-22
Ethan Walkrman (@ethanwalkerman) on X
thread2026-10-18
Aditya (@adityawaslost) on X
writeup2026-10-11
RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing
paper2026-10-07
[AINews] Reflection Beam - 501B-A23B American Open Model
article2026-10-06
Opus 5.5: 6x cheaper and 2x faster than Fable 5.1, but only 33.5% of code is secure | Blog | Endor Labs
writeup2026-09-25
[AINews] Meta Connect 2026: Muse glasses, voice, video, and Charm
writeup2026-09-24
Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber
article2026-07-21
Introducing Gemini 3.5 Flash Cyber
article2026-07-17
Harness^2: Recursive Agent Harnessing for an Open World
paper

In every workspace you can read 15

AI

[AINews] OpenAI’s Patch the Planet program is 1 of 2 parties to discover PHP2Shell vulnerabilities in core PHP affecting 70% of the web, using GPT-5.6 Sol; coordinated response over 2 months
article2026-10-22
Ethan Walkrman (@ethanwalkerman) on X
thread2026-10-18
Aditya (@adityawaslost) on X
writeup2026-10-11
RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing
paper2026-10-07
[AINews] Reflection Beam - 501B-A23B American Open Model
article2026-10-06
Opus 5.5: 6x cheaper and 2x faster than Fable 5.1, but only 33.5% of code is secure | Blog | Endor Labs
writeup2026-09-25
[AINews] Meta Connect 2026: Muse glasses, voice, video, and Charm
writeup2026-09-24
Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber
article2026-07-21
Introducing Gemini 3.5 Flash Cyber
article2026-07-17
Harness^2: Recursive Agent Harnessing for an Open World
paper

Security

ORCAGen: Orchestrating Context-Aware Malware Deception with RAG-Guided Generative AI
paper2026-10-08It is written here as Gemini 3.5 Flash (LLM evaluated; lowest response time and runtime overhead).
Opus 5.5: 6x cheaper and 2x faster than Fable 5.1, but only 33.5% of code is secure | Blog | Endor Labs
article2026-09-24
Agentic Hacks, Real Proofs: Inside Google's PageBreak Project
article2026-09-24
Benchmarking 13 AI models on rediscovering known CVEs
article2026-07-16It is written here as gemini-3.5-flash.
Endor Labs: AI Coding Agents Cheat Security Benchmarks via Training Recall, Not Reasoning
article2026-06-11

All technologies in this workspace.