Qwen3.5-4B

Named by 2 kept items in this workspace.

1 items name it under affected products and 1 under tools.

The items that name it 2

AuraForge: Scaling Security Supervision for Training Coding Agents
paperas tools2026-10-01
Coding agent model trained/fine-tuned with synthesized security tests in this study to evaluate security supervision improvements
LLMjacking evolved: Attackers are using stolen AI compute to build offensive agentic tools | Sysdig
writeupas affected products2026-06-17It is written here as qwen3.5:4b.

In every workspace you can read 14

AI

dbreunig/nesformer
article2026-10-30
Introducing LFM3: Every Modality for Specialized Intelligence
article2026-10-27
Coding From the Himalayas With an Offline AI Agent
writeup2026-10-27It is written here as Qwen3.5 4B.
[AINews] Anthropic files for $2T IPO in 2 weeks: 1400% growth rate, 48% of revenue through cloud partners, 85% margin, $1B op profit in Q2, $134B cash in bank and $10B lifetime burn
article2026-10-27
RIFT: KV Cache Compression for Draft Models with Complementary Compressibility Training
paper2026-10-22
[AINews] TypeSafe/Jev at >$100M ARR, $7.5B valuation 3 weeks after launch
article2026-10-10
[AINews] not much happened today
article2026-10-03
LLM2Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them
paper2026-10-01
AuraForge: Scaling Security Supervision for Training Coding Agents
paper2026-10-01
Shockingly Simple Self-retrospection Improves Agentic Models Without RL
paper2026-09-28
[AINews] The Future of Latent Space
article2026-09-25
Transformers now runs llama.cpp quants
article2026-09-22

Security

AuraForge: Scaling Security Supervision for Training Coding Agents
paper2026-10-01
LLMjacking evolved: Attackers are using stolen AI compute to build offensive agentic tools | Sysdig
writeup2026-06-17It is written here as qwen3.5:4b.

All technologies in this workspace.