June 25, 2026 · AI
Speeding up LLM inference with MTP and diffusion
MTP and diffusion inference on Gemma 4 and Qwen 3.6, fp8 on one H100
#LLM
#vLLM
#MTP
#Speculative Decoding
AI
한국어May 27, 2026 · AI
Requirements as Latent State
Why spec-driven development is a requirements-inference architecture
#AI
#Agent
#Requirements
#Spec-Driven
May 27, 2026 · AI
Skill and Harness
Why skills and harnesses overlap in implementation
#AI
#Agent
#Harness
#Skills
May 26, 2026 · AI
Harness as Environment
How harness design determines whether agents actually adapt.
#AI
#Agent
#Harness
#Memory
May 22, 2026 · AI
Memory as Adaptation
Why agent memory moved from RAG storage to the foundation of policy adaptation
#AI
#Agent
#Memory
#RAG
May 22, 2026 · AI
Weights, Prompts, Codes as Parameters
Weights, prompts, and code as parameters at different layers of a learnable policy space
#AI
#Agent
#LLM
#POMDP
May 21, 2026 · AI
GraphDB Benchmark (2/2) — Workload Matrix and Final Recommendations
Eight graph engines measured across OLTP, memory, analytics, and differentiation queries
#GraphDB
#PostgreSQL
#RCTE
#Neo4j
May 21, 2026 · AI
Comparing Four LightRAG Variants — Same Root, Different Production Strategies
Source-level comparison of RAG-Anything, ApeRAG, and EdgeQuake as LightRAG derivatives
#LightRAG
#RAG-Anything
#ApeRAG
#EdgeQuake
May 20, 2026 · AI
PDF to Markdown — Five Tools Compared
Five PDF-to-Markdown converters (markitdown, pdftotext, pymupdf, mineru, opendataloader-pdf) scored against a seven-criterion 100-point rubric
#PDF
#Markdown
#RAG
#Ingestion
May 20, 2026 · AI
Sharing Claude Code Sessions via Symlinked .jsonl
Resume the same Claude Code session across accounts by pointing every projects directory at one shared physical path
#Claude Code
#Multi-account
#Session Sharing
#Symlink
May 20, 2026 · AI
Apple Silicon LLM Inference — Five Backends Compared
Benchmarking Qwen3.5-9B on Apple Silicon across MLX, llama.cpp, Ollama, omlx, and vLLM Metal — single-request throughput, prefill scaling, decode vs input length, and concurrency response
#LLM
#Apple Silicon
#MLX
#llama.cpp
May 20, 2026 · AI
LightRAG Without Apache AGE — Graph Storage in Recursive CTE
Implementing LightRAG's BaseGraphStorage on plain PostgreSQL with RCTE — why a 1-hop-dominant retrieval pattern fits flat SQL
#LightRAG
#PostgreSQL
#RAG
#GraphRAG
May 20, 2026 · AI
Codex App Server Python SDK — JSON-RPC v2 over stdio
A Python SDK over the codex app-server stdio interface — install, first call, thread model, main methods
#Codex
#OpenAI
#Python SDK
#JSON-RPC
May 20, 2026 · AI
Running Multiple Claude Code Accounts on One Machine
Run isolated Claude Code accounts on the same Mac with one env var and a small zsh function
#Claude Code
#Multi-account
#zsh
#Dotfiles
May 20, 2026 · AI
Long-Context Evaluation — NIAH and Lost in the Middle
NIAH limits, the Lost in the Middle effect, alternative benchmarks, and measured recall across four reasoning-effort modes
#LLM
#Long-context
#NIAH
#Benchmark
May 20, 2026 · AI
NVIDIA NIM API — Free Inference for GLM, Kimi, Nemotron, and Gemma 4
NVIDIA's build.nvidia.com offers 100+ models on H100 infrastructure for free. Plug it directly into Claude Code, Cursor, or any OpenAI-compatible coding agent.
#NVIDIA
#NIM
#AI
#API
May 20, 2026 · AI
Claude Code Settings Sync and Troubleshooting
Sync matrix, migration steps, common failures, and diagnostic commands for running multiple Claude Code accounts on one machine
#Claude Code
#Multi-account
#Settings Sync
#Troubleshooting
May 20, 2026 · AI
GraphDB Benchmark, Eight Engines (Part 1) — Decomposing the RCTE 290x Gap
On a 1.14M-edge knowledge-graph workload, PostgreSQL RCTE beats Apache AGE by 290x — tracing the cypher() wrapper's 13ms cost and PG plan generation accumulation
#GraphDB
#PostgreSQL
#RCTE
#Apache AGE
May 15, 2026 · AI
10 OpenAI Models Through Quick Benchmarks — The Model Isn't as Smart as You Pay
I ran 30 trials per configuration across GPT-4, GPT-5, and o-series models using three reasoning problems. gpt-5-nano on minimal scored 4.4%. o1 scored lower than gpt-4o.
#OpenAI
#GPT
#model comparison
#AI
May 15, 2026 · AI
GitHub Models Inference API — Free Model Access Tested
How to easily call modern AI models such as GPT-4.1 and DeepSeek R1 through GitHub's free model inference API
#GitHub
#Inference API
#AI
#API
May 15, 2026 · AI
Experimenting with the GPT-5 Responses API Web Search Tool
An experimental record of implementing web search with OpenAI's GPT-5 Responses API, focused on tool-support differences between models and how parameters shape responses. The analysis centers on web search tool compatibility between gpt-5 and gpt-5-chat-latest.
#AI
#GPT-5
#API
#web search
