LLaMa

Named by 17 kept items in this workspace.

15 items name it under classification.technologies and 2 under affected products.

The items that name it 17

Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness
paperas classification.technologies2026-10-27
From Detection to Decision: Calibration and Deferral for Prompt-Injection Detection
paperas classification.technologies2026-10-14
INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems
paperas classification.technologies2026-10-14
Anthropic tests AI autonomous replication across eight nodes in four of five trials
articleas classification.technologies2026-10-12
AI models may be capable of self-replicating without access to a datacenter
paperas classification.technologies2026-10-12
Physical Side-Channel Attacks on Edge LLMs: Extracting Output Tokens and User Prompts
paperas classification.technologies2026-10-09
SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
paperas classification.technologies2026-10-07
Identity Management for Agentic AI [pdf] (2025)
paperas affected products2026-10-01
large foundation model-based agentic system discussed as example of AI agent requiring new auth/authz models
Uncensored and Offensive Security AI Models Benchmark
repoas classification.technologies2026-09-29
Understanding the Impact of LLM Watermarking on AI Agent Behavior
writeupas classification.technologies2026-09-26
GhostSplice: Malicious MCP Servers Split Exfiltration to Bypass Guardrails
articleas classification.technologies2026-08-19
AI Security Briefing
articleas classification.technologies2026-07-18
AI Security Briefing
writeupas classification.technologies2026-07-18
meta-llama/PurpleLlama
repoas classification.technologies2026-07-14
LLMjacking evolved: Attackers are using stolen AI compute to build offensive agentic tools | Sysdig
writeupas classification.technologies2026-06-17
requie/LLMSecurityGuide
repoas classification.technologies2026-05-05
Sockpuppeting: How a Single Line Can Bypass LLM Safety Guardrails | TrendAI (US)
writeupas affected products
Open-weight model family included in testing

In every workspace you can read 54

AI

Does Chain-of-Thought Reliance Follow a Scaling Law?Larger Models Follow Their Steps More, Independent of Post-Training
paper2026-10-28
FlatCake: A Flat KVCache Storage Architecture for LLM Serving
paper2026-10-28
Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness
paper2026-10-27
Folding Attention Biases into Keys Makes Compacted KV Caches Run on Standard Kernels
paper2026-10-27
What Adobe v ArtCraft teaches us
article2026-10-25
MPQ: A Message-Passing View of Post-Training Quantization
paper2026-10-23
Training Small Language Models for Transferable Tool Selection
paper2026-10-22
How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications
article2026-10-21
FairStress: A deeper evaluation of fairness in LLM decision-making
article2026-10-20
HERMES: High-Performance Private Decoding for Large Language Models
paper2026-10-18
Meta shakes up the frontiers, open and closed
article2026-10-17
Rodrigo ES Porto (@RodrigoESPorto) on X
thread2026-10-16
FuTransformer: FP8 prefill and INT4 decode for Llama-style inference on Hopper
paper2026-10-16
Multi-Reward Hacking: From Aggregation-Induced Drift to Trust-Anchored Defense
paper2026-10-15
MultiAlloc: Budget-Aware Precision Allocation for KV Cache Quantization
paper2026-10-13
Geometric Calibration of Supervised Fine-Tuning
paper2026-10-13
Meta's New Muse Wonder Finally Puts Zuckerberg in the Frontier AI Race
article2026-10-12
Anthropic tests AI autonomous replication across eight nodes in four of five trials
article2026-10-12
AI models may be capable of self-replicating without access to a datacenter
writeup2026-10-12
DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs
paper2026-10-09
Sub-1-Bit LLM Compression via Latent Factorization
repo2026-10-08
SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
paper2026-10-07
Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment
paper2026-10-06
Defense-in-Depth for LLMs: Evaluating Memory Gates Against Activation-Induced and Memory-Induced Sycophancy
paper2026-10-05
Sujeet (@sujeetgholap) on X
thread2026-10-03
Inside-Out AI: Rebuilding Airbnb Behind the Scenes and Across the Guest Experience
article2026-10-02
Identity Management for Agentic AI [pdf] (2025)
paper2026-10-01
Uncensored and Offensive Security AI Models Benchmark
repo2026-09-29
OpenRouter: from Seed to Stripe — with OpenRouter’s Alex Atallah & AMP’s Anjney Midha
talk2026-09-25
ClusterMAX 3.0: The Industry Standard GPU Cloud Rating System Returns
article2026-09-23
The current balance of power in open models
article2026-09-21
A Zeroth-Order Paradigm for LLM Preference Alignment
paper2026-09-16
Long Live the Short King: Why 4-hi HBM Wins
article2026-09-13
Latest open artifacts (#24): Motif-3, GLM-5.3, Hy4-preview and open model licenses
article2026-09-08
TPU Inference Externalization Full Steam Ahead - InferenceX
article2026-09-07
rikugan: LLM reverse-engineering agent for IDA Pro and Binary Ninja
repo
LLM Inference in a Flash!
paper

Security

Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness
paper2026-10-27
From Detection to Decision: Calibration and Deferral for Prompt-Injection Detection
paper2026-10-14
INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems
paper2026-10-14
Anthropic tests AI autonomous replication across eight nodes in four of five trials
article2026-10-12
AI models may be capable of self-replicating without access to a datacenter
paper2026-10-12
Physical Side-Channel Attacks on Edge LLMs: Extracting Output Tokens and User Prompts
paper2026-10-09
SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
paper2026-10-07
Identity Management for Agentic AI [pdf] (2025)
paper2026-10-01
Uncensored and Offensive Security AI Models Benchmark
repo2026-09-29
Understanding the Impact of LLM Watermarking on AI Agent Behavior
writeup2026-09-26
GhostSplice: Malicious MCP Servers Split Exfiltration to Bypass Guardrails
article2026-08-19
AI Security Briefing
article2026-07-18
AI Security Briefing
writeup2026-07-18
meta-llama/PurpleLlama
repo2026-07-14
LLMjacking evolved: Attackers are using stolen AI compute to build offensive agentic tools | Sysdig
writeup2026-06-17
requie/LLMSecurityGuide
repo2026-05-05
Sockpuppeting: How a Single Line Can Bypass LLM Safety Guardrails | TrendAI (US)
writeup

All technologies in this workspace.