Will Percey
-
Knowledge Base
Version: 2.0.0
dark_mode
home
language
article
image
clinical_notes
Explore
hub
Open Knowledge Graph
new_releases
Recently Updated
biotech
Mechanistic Interpretability
How models actually think
verified_user
AI Safety & Alignment
Jailbreak feature conflicts & scheming
blur_on
Hallucinations & Grounding
The refusal-by-default mechanism
edit_note
Prompt Engineering
When CoT is faithful vs post-hoc
loop
Agentic Loops
Iterative agent execution patterns
category
Agent Clawification
The Claw ecosystem & variant selection
smart_toy
NVIDIA Agent Stack
Enterprise agentic AI platform
stream
Stream Safeguards
Runtime stream monitoring & hooks
language
My Websites
View All
arrow_forward
ImgID
AI Image Verification
ADios
DNS-Level Adblocker
Murmur
Local AI Speech-to-Text
PUML Studio
PlantUML Diagram Editor
article
Blog
View All
arrow_forward
article
Agentic Social Protocol Violations
2026-02-13
article
AI's Decision or a Coin Flip?
2025-01-30
article
SynthID Solves Google's Problem, Not Yours
2025-01-26
article
Why AI Image Detectors Always Lose
2025-01-19
cloud
Cloud Providers
View All
arrow_forward
cloud
AWS
Amazon Web Services
cloud
Azure Services
Microsoft Azure
cloud
GCP Services
Google Cloud Platform
compare_arrows
Service Comparison
Compare cloud providers
architecture
Well-Architected
Framework best practices
savings
Cost Optimization
FinOps & cost management
flight_takeoff
Migration Strategies
6 Rs & cloud migration
savings
AI Cost Optimization
GPU & LLM cost optimization
workspace_premium
Azure Solutions Architect
AZ-305 Exam Guide
smart_toy
LLM & Agentic AI
View All
(13 more)
arrow_forward
auto_awesome
Agent Clawification
Skill-based agents embedded in real-world channels
robot_2
Agentic Patterns
AI agent patterns
psychology
Agentic Anatomy
Agent components
forum
Conversation Management
Context window strategies
headset_mic
Voice Agents
Frameworks, tool calling & modality types
mic
Voice Agents: V2V Risks
V2V risk catalogue & security stack
bug_report
ElevenLabs: Voice Testing
Scenario, tool call & simulation testing
stream
Stream Safeguards
Runtime stream monitoring & hooks
gavel
Judge & Escalation
Tiered quality gates for agent output
loop
Agentic Loops
Iterative agent execution patterns
precision_manufacturing
Graph State Machine
Declarative graph execution engine
error_outline
Agentic Errors
Agent failure modes
shield
Agentic Zero Trust
Bidirectional agent security
thermostat
Agent Temperature
Temperature guidance by role
shield
AI Guardrails
Safety & content filtering
auto_awesome
RAG Architecture
Retrieval-Augmented Generation
share
Knowledge Graphs
GraphRAG & entity relationships
verified
AIUC-1 Standard
AI agent security & trust certification
biotech
Mechanistic Interpretability
How models actually think
blur_on
Hallucinations & Grounding
Detection & prevention
neurology
Deep Learning & MLOps
View All
(15 more)
arrow_forward
neurology
AI Architectures
Model architectures
cloud
AWS Model Development
Nova Forge & SageMaker HyperPod
visibility
Computer Vision
CNNs, transformers & detection
recommend
Recommendation Systems
Algorithms, ranking & personalization
query_stats
Time Series Forecasting
Classical & deep learning methods
tune
Fine-Tuning
LoRA, QLoRA & model adaptation
bolt
GPU Inference
TensorRT, CUDA & optimization
devices
Edge AI
On-device inference & optimization
account_tree
MLOps
ML lifecycle & pipelines
model_training
Model Serving
Inference servers & deployment
hub
ML Platform Architecture
Infrastructure & MLOps patterns
speed
Inference Optimization
Quantization & performance tuning
database
Data
View All
arrow_forward
storage
Databases
SQL, NoSQL & NewSQL
hub
Vector Databases
Embeddings & similarity
schema
Data Architecture
Lakes, warehouses & governance
grid_view
Dimensional Modeling
Facts, dimensions & grain
trending_up
Database Scaling
Performance & distribution
pattern
Database Patterns
Access & query patterns
analytics
Big Data
Warehouses & processing
architecture
Architecture & Patterns
View All
(1 more)
arrow_forward
architecture
Design Patterns
Software design patterns
bug_report
Testing Patterns
Testing & QA patterns
account_tree
Architecture & Notation
Frameworks & diagramming
robot_2
Agentic Patterns
AI agent patterns
shield
Resilience Patterns
Fault tolerance & recovery
psychology
Behavioral Patterns
GoF behavioral patterns
sync
Concurrency Patterns
Thread & message patterns
storage
Database Patterns
Data access & ORM patterns
widgets
Microservice Patterns
Distributed systems patterns
high_quality
High Availability
HA patterns & redundancy
monitoring
Observability
Monitoring & SLO/SLA
trending_up
Capacity Planning
Forecasting & autoscaling
database
Data Architecture
Storage & processing patterns
api
API Design
API governance & standards
rocket_launch
Deployment Strategies
CI/CD & release patterns
group
Multi-Tenancy
SaaS & tenant isolation
hub
Enterprise Integration
ESB & messaging patterns
map
Domain-Driven Design
Strategic & tactical DDD
science
Chaos Engineering
Resilience & failure testing
auto_awesome
Feature Engineering
Transformation & selection
functions
Computer Science Fundamentals
View All
(4 more)
arrow_forward
functions
Big O Notation
Time & space complexity
account_tree
Data Structures
Arrays, trees, graphs & more
psychology
Algorithm Patterns
Common problem-solving patterns
sort
Sorting Algorithms
Comparison & analysis
neurology
Neural Network Algorithms
Backprop & optimization
hub
Systems & Networking
Protocols & distributed systems
security
Security Fundamentals
Crypto, auth & vulnerabilities
database
Database Theory
ACID, indexing & optimization
shield
Disaster Recovery
RTO, RPO & business continuity
cable
Network Architecture
VPC, subnets & connectivity
verified_user
Compliance
GDPR, HIPAA, SOC 2 & PCI DSS
security
Zero Trust Architecture
Identity & perimeter-less security
abc
Acronym Guide
Tech terminology reference
apps
Technologies
View All
arrow_forward
forum
Messaging & Queues
Message brokers & queues
storage
PostgreSQL
Postgres for everything
speed
Caching
In-memory caching
search
Search & Indexing
Advanced search tools
code_blocks
Infrastructure as Code
IaC tools & solutions
hub
LLM Technologies
Frameworks, tools & guardrails
engineering
DevOps & CI/CD
CI/CD & monitoring tools
security
Security & Authentication
Auth & API security
map
Maps & Routing
Mapping & routing solutions
science
Testing Technologies
Testing frameworks & tools
widgets
Container & Orchestration
Containers & K8s
api
API Technologies
REST, GraphQL, gRPC
videocam
Real-time Communication
WebRTC, WebSocket & streaming
stacks
Tool Stacks
View All
arrow_forward
dataset
Apache Stack
Big data technologies
search
Elastic Stack
Search & observability
business
Red Hat Stack
Enterprise solutions
memory
NVIDIA Stack
GPU & AI infrastructure
smart_toy
NVIDIA Agent Stack
Enterprise agentic AI platform
shield
HashiCorp Stack
DevOps lifecycle
monitoring
Grafana Stack
Observability platform
radar
Tech Radar
View All
arrow_forward
sports_esports
Google Genie
Google DeepMind
Creating video games in real-time in front of your eyes. Too expensive but bright future.
terminal
Ollama
Ollama
The new CLI goes beyond ollama run. ollama launch turns it into a platform, local models inside Claude Code, agent wrappers, and an enormous model catalogue
business_center
NemoClaw
NVIDIA
The first enterprise-grade claw variant from a major vendor. Compliance, confidential computing, and NeMo integration in one platform — the claw to watch for regulated industry deployments.
security
NanoClaw
qwibitai (community)
Proof that a claw agent can be both capable and fully auditable. Container isolation by default, Claude SDK foundation, and a codebase small enough that one person can genuinely understand the whole thing.
smart_toy
Kimi K2
Moonshot AI
Impressive multi-agent orchestration, a pattern to follow once it matures.
forum
Moltbook
OpenClaw
By the creators of OpenClaw. A social network where only AI agents can post, humans just observe.
widgets
Google Opal
Google Labs
Vibe coding for non-developers. Describe an app in plain English and Opal builds it. Conversational and visual editing modes, with deeper Google integrations on the roadmap.
hive
Hive
Aden
Goal-driven agent development where you declare outcomes instead of hardcoding workflows. Self-healing graphs, built-in judge and escalation, and a TUI dashboard for observability.
groups
MetaGPT
DeepWisdom
Role-playing agents that mimic a full dev team. Niche but interesting for exploring multi-agent coordination patterns and development automation.
verified
AIUC-1
AIUC
The missing piece for enterprise AI adoption: a verifiable, independently audited standard that replaces bespoke vendor security questionnaires.
graphic_eq
ElevenLabs
ElevenLabs
Voice is the missing interface for agentic systems. Their Conversational AI SDK turns any agent into a voice agent with tool calling and sub-second latency.
record_voice_over
EVA
ServiceNow Research
The accuracy-vs-experience tradeoff is real and previously unquantified. Directly relevant to voice agent work — EVA's dual-axis scoring is the right mental model for evaluating spoken AI.
menu_book
NotebookLM
Google Labs
AI-powered research and note-taking.
