llm 47
- Replay Data vs Catastrophic Forgetting, Measured: Mixing General Text into a Fine-Tune
- Enterprise AI: Token Budgets That Hold Under Concurrency - Measured on an LLM Gateway
- Fine-Tuning Evaluation, Measured: Held-Out Perplexity, KL Drift and Benchmarks
- AI Security: Hidden Prompt Injection vs Agent Page Readers, Measured
- AI Security: Secrets in Agent Logs, Measured - What gitleaks and Redaction Actually Catch
- Continuous batching, measured: llama.cpp static vs continuous scheduling on one M2 Pro
- Go pprof Profiling Guide: CPU, Goroutine and Mutex Profiles on One Service
- AI Security: Agent Tool Permissions That Survive Prompt Injection
- LoRA Fine-Tuning LLMs: A Practical Guide from Dataset to Eval Gate
- Sandboxing Agent Tool Calls: Keep the Secrets Out of the Blast Radius
- AI Security: Prompt Injection Defenses for Agents That Actually Hold
- AI Security: Agent Tool-Egress and Data-Exfiltration Controls That Actually Hold
- Fine-tuning data curation and eval-set construction for enterprise teams
- LoRA vs QLoRA vs full fine-tuning: the GPU memory, cost, and eval-score tradeoffs
- Go pprof alloc_space: 2.87 GB of garbage from one `+=` in a loop
- Hedged Requests and Load Shedding: Finishing the Go LLM Gateway Resilience Stack
- GOGC=off with runtime.SetMemoryLimit: the GC tuning pair that cut our p99 61%
- Go LLM Gateway: Circuit Breaker Plus Retry Budget That Cut Token Waste 88%
- Enterprise AI: Audit Logging and Policy Controls for an LLM Gateway
- Go sync.Pool and String Interning: Beating GC Pressure in the Same Tokenizer Sidecar
- Rust Small-String Optimization: compact_str Cut Our LLM Tokenizer Sidecar's p99 by 67%
- AI SDLC: A Release Gate on Coding-Agent Evals That Blocks the Rollout, Not the Retrospective
- Rust Async Under Load: Tokio Backpressure in an LLM Gateway
- Go Context Cancellation for LLM Streaming and Agent Calls: One Pattern That Cut Waste 47x
- Context-window rot: agent pass@1 falls 45 points before the window is even half full
- Rust vs Go Error Handling in AI Agent Tool Calls: Which Failure Taxonomy Caught More Bugs
- Go pprof vs SLO Burn Rate: Finding the p99 Leak Before the Pager Fires
- Enterprise AI: A Use-Case Intake Form and Three Risk Tiers So Governance Scales With Risk, Not Headcount
- Enterprise AI: Governing LLM Usage - A Shadow-AI Inventory and a Usage Register in 30 Days
- Before and After: A Screenshot Walkthrough of the Lamplit Labs Token Counter, Schema Builder and Validator
- TypeScript vs Go vs Rust for LLM Tooling: One MCP Server, Three Languages, Measured
- One Workflow, Three Tools: Prompt to Schema to Validator with the Lamplit Labs Tools
- Tiktoken Playground: Seeing Where Your Prompt Actually Splits
- Model Context Window Chart: How Much Fits Before You Start Trimming
- Structured Output Validator: Catching Schema Drift Before It Reaches Your Code
- Embedding Visualizer: Checking Vector Similarity Before You Trust Retrieval
- Text Chunker for RAG: Previewing Chunk Boundaries Before You Embed
- Function Call Schema Builder: Tool Definitions Without Hand-Written JSON
- AI API Format Converter: One Chat Request, Four Provider Payloads
- Prompt Template Editor and Prompt Diff: Treating Prompts Like Code Before They Reach Production
- Token Counter: Checking Prompt Size and Context-Window Fit Before You Call the Model
- AI Pricing Calculator: Estimating LLM API Costs Before You Ship
- Embeddings and Cosine Similarity: How a Program Tells That Two Sentences Mean the Same Thing
- Retries, Timeouts and Rate Limits: Making Your First Model Call Survive the Real World
- Grounding a Model with Your Own Documents and Getting a Reply Your Code Can Check
- Calling a Language Model from Code: Your Prompt Is Just an API Request
- How a Language Model Answers You: Tokens, Prediction and Repetition