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.

345
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 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
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 19, 2026 · Artificial Intelligence

vLLM 0.32.0 Adds System 1 Decision Engine for Millisecond Structured Decisions

vLLM 0.32.0 introduces a built-in /v1/systemone endpoint that delivers millisecond-level structured decisions (choice, boolean, scoring) using models like LiquidAI/d1-3B, achieving 23ms median latency and 44 decisions per second, alongside KV cache quantization improvements, universal HF parsers, and breaking changes.

HF tool parserKV cache quantizationLLM inference
0 likes · 11 min read
vLLM 0.32.0 Adds System 1 Decision Engine for Millisecond Structured Decisions
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 17, 2026 · Artificial Intelligence

DeepSeek-V4.1-Flash-1017: Flash Model Matches Flagships on Agent Benchmarks, Cuts KV Cache 4x

DeepSeek releases V4.1-Flash-1017, a flash-tier model that outperforms flagship competitors on key agent benchmarks like DeepSWE and Automation-Bench while reducing KV cache to 1/4 of its predecessor via CSA2 sparse attention and FP4 quantization, and adds native multimodal support, adjustable reasoning intensity, and a new Search & Fetch API for real-time web access.

Agent benchmarksCSA2 sparse attentionDeepSeek
0 likes · 6 min read
DeepSeek-V4.1-Flash-1017: Flash Model Matches Flagships on Agent Benchmarks, Cuts KV Cache 4x
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 15, 2026 · Artificial Intelligence

Anthropic Engineer's Framework for Ambitious AI Usage: Altitude, Depth, Range

Anthropic engineering lead Felix Rieseberg argues that most users barely scratch the surface of LLM capabilities, proposing a three-dimensional framework — Altitude (outcome-focused abstraction), Depth (expert-level tooling and verification), and Range (cross-disciplinary agent teams) — to transform AI from a speed tool into a strategic partner, with concrete prompts and case studies.

AI AgentsAI promptingAnthropic
0 likes · 17 min read
Anthropic Engineer's Framework for Ambitious AI Usage: Altitude, Depth, Range
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 15, 2026 · Artificial Intelligence

Grok Bot Deep Dive: Cloud VMs, Teach-by-Demo, and Bot Team Collaboration

The article dissects Grok Bot's architecture, revealing how per-bot cloud VMs, role-based bot teams, screen-recording skill teaching, human-bot group chat, auto-review approvals, persistent S3 memory, and one-click cloning shift AI agents from single-turn chat tools to persistent digital coworkers.

AI AgentsGrok Botauto-review
0 likes · 13 min read
Grok Bot Deep Dive: Cloud VMs, Teach-by-Demo, and Bot Team Collaboration
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 15, 2026 · Industry Insights

Doubao Work's Canvas: All-in-One AI Creative Workspace for Solo Creators

The author tests Doubao Work's new Canvas feature, which integrates image generation (Seedream 5.0 Flash), video creation (Seedance), HTML coding, and local editing into an infinite canvas, enabling end-to-end production of brand assets like posters, menus, videos, and landing pages in one interface, while also noting recent fixes to previous usability issues.

AI CanvasAI Image GenerationAI video generation
0 likes · 9 min read
Doubao Work's Canvas: All-in-One AI Creative Workspace for Solo Creators
Old Zhang's AI Learning
Old Zhang's AI Learning
Oct 11, 2026 · Artificial Intelligence

Qwen4-Max & Qwen4-27B Coming: Open-Source Plans & Qwen3.8-27B Deployment Insights

The author covers Alibaba Qwen team's upcoming Qwen4 family with open-source plans, surveys recent global AI model releases, notes a slowdown in Chinese model updates, shares hands-on testing of Qwen3.8-27B quantization variants on A100 and 4090 GPUs, and recommends FP8 for dual-4090 and GGUF UD-Q4+ for single-4090 setups.

FP8GGUFLLM deployment
0 likes · 4 min read
Qwen4-Max & Qwen4-27B Coming: Open-Source Plans & Qwen3.8-27B Deployment Insights