BestHub
Sign in
Old Zhang's AI Learning
Author

Old Zhang's AI Learning

AI practitioner specializing in large-model evaluation and on-premise deployment, agents, AI programming, Vibe Coding, general AI, and broader tech trends, with daily original technical articles.

344
Articles
2
Likes
5.8k
Views
0
Comments
Recent Articles

Latest from Old Zhang's AI Learning

100 recent articles max
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 26, 2026 · Artificial Intelligence

Anthropic S-1 Reveals $16.3B Revenue, Mythos Model, 900% NRR, and Unique Governance

Anthropic's 421-page S-1 filing shows H1 2026 revenue of $16.3B, a $80.7B GAAP loss driven by non-cash fair-value adjustments, positive operating cash flow of $3.9B, a new flagship Mythos model, 900% net revenue retention, and a governance structure giving a Long-Term Benefit Trust veto power over the board.

AI governanceAnthropicIPO
0 likes · 19 min read
Anthropic S-1 Reveals $16.3B Revenue, Mythos Model, 900% NRR, and Unique Governance
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 26, 2026 · Artificial Intelligence

Nanbeige4.3-33B vs Qwen3.8-27B: Benchmark Claims Meet Hardware Reality

The author benchmarks Nanbeige4.3-33B against Qwen3.8-27B on an A100-80GB GPU, finding Nanbeige wins select benchmarks but fails to deliver its claimed 512K context on a single card due to high KV cache overhead from its Llama architecture, suffers from excessive chain-of-thought tokens that break coding tasks, and lacks vision capabilities, while Qwen's linear attention enables longer context and multimodal support.

LLM benchmarkingNanbeige4.3-33BQwen3.8-27B
0 likes · 12 min read
Nanbeige4.3-33B vs Qwen3.8-27B: Benchmark Claims Meet Hardware Reality
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 25, 2026 · Artificial Intelligence

vLLM & SGLang Surpass DeepSeek's DeepInfer: General Engines Prevail

vLLM and SGLang matched or exceeded DeepSeek's custom DeepInfer engine on DeepSeek-V4.1-Flash within days by adopting its open-sourced operators and optimizing for model-specific traits, proving general-purpose inference engines remain dominant due to full production-grade systems.

DeepInferDeepSeekKV cache
0 likes · 15 min read
vLLM & SGLang Surpass DeepSeek's DeepInfer: General Engines Prevail
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 24, 2026 · Artificial Intelligence

Claude, Gemini, Grok & ChatGPT: My AI Subscription Stack Analyzed

The author reviews their subscriptions to Claude Pro, Gemini Pro, Grok, and ChatGPT Plus, comparing model capabilities, pricing value, and productivity gains for coding, writing, and image generation, while questioning if the costs can be recouped through side projects.

AI subscriptionsChatGPTClaude
0 likes · 5 min read
Claude, Gemini, Grok & ChatGPT: My AI Subscription Stack Analyzed
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 23, 2026 · Artificial Intelligence

Anthropic Warns: Ditch Subagents for a Single Loop with Skills

Anthropic argues that multi-subagent architectures often mirror organizational charts rather than technical needs, showing single-loop agents with progressive skill disclosure outperform complex pipelines in quality, latency, and cost, and provides a migration framework.

AI agentsAgent EvaluationAnthropic
0 likes · 22 min read
Anthropic Warns: Ditch Subagents for a Single Loop with Skills
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 22, 2026 · Artificial Intelligence

Automated Pipeline Turns Long Videos into Interactive Knowledge Bases with 3 AI Skills

The author builds an open-source pipeline using three skills — z-web-pack, z-video-downloader, and z-video-study-webpage-qwen — to download videos, extract subtitles, and generate static web pages with bilingual subtitles, timestamped key points, frame-matched knowledge cards, and quotes, enabling efficient learning from long-form content like Dan Koe's videos.

Qwenautomation pipelineknowledge management
0 likes · 9 min read
Automated Pipeline Turns Long Videos into Interactive Knowledge Bases with 3 AI Skills
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 20, 2026 · Backend Development

Free DeepSeek V4.1 Flash 1017 via Magpie Gateway: One-Click Setup for Any Coding Agent

This tutorial shows how to use the open-source Magpie gateway to aggregate free DeepSeek V4.1 Flash 1017 quotas from OpenCode Zen Free, Tencent Cloud WorkBuddy, and ByteDance Trae CN, enabling zero-cost integration with coding agents like Claude Code, Codex, and DeepSeek Harness via automatic protocol translation and multi-account failover.

API AggregationClaude CodeCoding Agents
0 likes · 9 min read
Free DeepSeek V4.1 Flash 1017 via Magpie Gateway: One-Click Setup for Any Coding Agent
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 20, 2026 · Artificial Intelligence

Deploying 552B DeepSeek-V4.1-Flash on Dual DGX Sparks: 130 tok/s, 2.9 bpw Quantization

MiaAI-Lab demonstrates running the 552B-parameter DeepSeek-V4.1-Flash-1017 model on two NVIDIA DGX Spark workstations (256GB unified memory) using a Zig-based runtime, ConnectX-7 200 Gb/s interconnect, EXL3 2.9 bpw quantization, and local NVMe storage with memory guards, achieving 75 tok/s single-stream and 130 tok/s 4-stream decode throughput with 512K context.

ConnectX-7DGX SparkDeepSeek-V4.1-Flash-1017
0 likes · 14 min read
Deploying 552B DeepSeek-V4.1-Flash on Dual DGX Sparks: 130 tok/s, 2.9 bpw Quantization
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 19, 2026 · Artificial Intelligence

DeepSeek Harness Outperforms Claude Code on Bug Hunt Bench with V4.1 Flash 1017

Third-party Bug Hunt Bench results show DeepSeek Harness (DSH) with DeepSeek-V4.1-Flash-1017 surpasses Claude Code by 2-3 points across reasoning tiers, but consumes 82% more tokens and costs 82% more per task while fixing twice as many non-scored defects; the author recommends DSH for complex debugging and Claude Code for routine coding.

Bug Hunt BenchClaude CodeDeepSeek
0 likes · 9 min read
DeepSeek Harness Outperforms Claude Code on Bug Hunt Bench with V4.1 Flash 1017