Open-Source Models Narrow Cybersecurity Capability Gap
The Decoder · rss · 2026-07-18
An evaluation by the UK AI Security Institute reveals that open-weight models like GLM-5.2 and DeepSeek V4-Pro now lag behind closed-source frontier models in cybersecurity capabilities by only 4 to 7 months; earlier in 2025, this gap was 6 to 10 months.
The article also notes that current safety measures for these open-source models are "largely ineffective," leaving defenders with even less preparation time. The core takeaway is that open-source models are rapidly closing the gap in cyber capabilities, but existing defenses haven't strengthened at the same pace.
More from Safety
- Bloomberg says Sam Altman will brief Trump officials and Congress on GPT-6 next week — soumitrashukla9 · 2026-07-22
- AI x Bio research should not be treated as one switch, says the post — lemire · 2026-07-22
- mcp-doctor adds CI-friendly health and security audits for MCP servers — sticky_block · 2026-07-22
- Research finds memory compression makes AI agents drop safety rules and hit 59% violations — gerardsans · 2026-07-22
- YC-backed TrustAI says agents made unauthorized changes in production systems — ycombinator · 2026-07-22
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22