BestHub
Sign in
Baobao Algorithm Notes
Author

Baobao Algorithm Notes

Author of the BaiMian large model, offering technology and industry insights.

302
Articles
0
Likes
1.4k
Views
0
Comments
Recent Articles

Latest from Baobao Algorithm Notes

100 recent articles max
Baobao Algorithm Notes
Baobao Algorithm Notes
Sep 5, 2026 · Artificial Intelligence

GPT-6 Astra Scores 99.9% on ARC-AGI-3: Model Leap or Harness Win?

OpenAI's GPT-6 Astra achieves 99.9% on the ARC-AGI-3 benchmark using its native Provider Adapter harness, demonstrating novel behaviors like inventing algebraic shorthand, surpassing human action efficiency, and writing its own tools, though the official standard harness yields 62.7%, raising questions about whether this constitutes AGI.

AGIAI benchmarksAI safety
0 likes · 17 min read
GPT-6 Astra Scores 99.9% on ARC-AGI-3: Model Leap or Harness Win?
Baobao Algorithm Notes
Baobao Algorithm Notes
Aug 31, 2026 · Industry Insights

2027 LLM Campus Hiring: Base Roles Hit 3M RMB, Application Layer Commoditizes

The article analyzes 2027 campus recruitment for large model roles, revealing a bifurcated market: elite base-model positions offer 3M+ RMB packages but require proven pedigree (base internships or high-impact papers), while application-layer roles commoditize into prompt engineering with lower pay; infra/algorithm/data roles converge, Agent development shifts to engineering, and students are advised to target base internships early or accept application roles as entry points.

Agent EngineeringApplication LayerBase Model Training
0 likes · 18 min read
2027 LLM Campus Hiring: Base Roles Hit 3M RMB, Application Layer Commoditizes
Baobao Algorithm Notes
Baobao Algorithm Notes
Aug 4, 2026 · Artificial Intelligence

Agentic RL: Cutting‑Edge Techniques from GLM‑5.2 and Qwen

The article dissects recent Agentic RL breakthroughs—including GLM‑5.2’s shift from GRPO to critic‑based PPO, Qwen’s multi‑dimensional verification system, the generative‑critic GenAC, and the on‑policy skill‑distillation method OPID—showing how each tackles long‑trajectory credit assignment, reward hacking, and scalable evaluation across software‑engineering, front‑end, and real‑world tasks.

Agentic RLGLM-5.2Generative Critic
0 likes · 36 min read
Agentic RL: Cutting‑Edge Techniques from GLM‑5.2 and Qwen
Baobao Algorithm Notes
Baobao Algorithm Notes
Jul 20, 2026 · Artificial Intelligence

Kimi K3 Unleashed: 2.8 Trillion‑Parameter Model Tackles 3D Simulations, Games, and Kaggle

The author evaluates the newly released 2.8‑trillion‑parameter open‑source Kimi K3 model by having it generate a 3D rocket simulation, a 3D dinosaur runner game, a functional web‑based Excel, and an end‑to‑end Kaggle house‑price solution, revealing both impressive capabilities and notable limitations.

AI evaluationKaggle competitionKimi K3
0 likes · 11 min read
Kimi K3 Unleashed: 2.8 Trillion‑Parameter Model Tackles 3D Simulations, Games, and Kaggle
Baobao Algorithm Notes
Baobao Algorithm Notes
Jul 14, 2026 · Artificial Intelligence

LibTV’s Video Agent Takes AI Video Creation to the Next Level

The article reviews LibTV’s AI‑driven Video Agent, showing how its dual storyboard‑node workflow, multi‑round confirmations, and hundreds of ready‑made Skills let creators generate, refine, and perfect professional‑grade videos with simple natural‑language prompts.

AI video generationLibTVNode workflow
0 likes · 8 min read
LibTV’s Video Agent Takes AI Video Creation to the Next Level
Baobao Algorithm Notes
Baobao Algorithm Notes
Jul 2, 2026 · Artificial Intelligence

How to Connect Chinese LLMs to Codex: A Hands‑On Tutorial

This article walks through installing Codex, adding the open‑source CC Switch tool, and configuring Chinese large language models such as Kimi so they can serve as the backend for Codex’s AI agent, with step‑by‑step screenshots and performance examples.

AI agentCC SwitchChinese LLM
0 likes · 11 min read
How to Connect Chinese LLMs to Codex: A Hands‑On Tutorial
Baobao Algorithm Notes
Baobao Algorithm Notes
Jun 2, 2026 · Artificial Intelligence

MiniMax M3: How a 1M‑Token, Multimodal Agent Reproduces ICLR Research and Automates Kaggle Competitions

The MiniMax M3 model combines a 1‑million‑token context window, native multimodal training and a new MiniMax Sparse Attention architecture that cuts token compute to one‑twentieth of its predecessor, achieving up to 15× faster decoding, while its interactive user‑simulator training enables fully autonomous agents that can reproduce ICLR‑2025 research and tackle Auto‑Kaggle competitions at a fraction of the cost of Western models.

Agentic AIAuto KaggleLarge Language Model
0 likes · 9 min read
MiniMax M3: How a 1M‑Token, Multimodal Agent Reproduces ICLR Research and Automates Kaggle Competitions
Baobao Algorithm Notes
Baobao Algorithm Notes
May 26, 2026 · Artificial Intelligence

How On-Policy Distillation (OPD) Solves Core Challenges in Large-Model Post-Training

The article explains how On-Policy Distillation (OPD) combines on‑policy sampling with dense teacher feedback via reverse KL to address low signal density, distribution shift, and capability interference in large‑model post‑training, and compares implementations by Qwen3, GLM‑5, MiMo‑V2 and DeepSeek‑V4.

Knowledge DistillationModel CompressionOPD
0 likes · 20 min read
How On-Policy Distillation (OPD) Solves Core Challenges in Large-Model Post-Training
Baobao Algorithm Notes
Baobao Algorithm Notes
May 22, 2026 · Artificial Intelligence

How LiteScale Cuts Wait Times in Large‑Model Post‑Training with Gradient Accumulation

The article examines the bottleneck of synchronous rollout in large‑model post‑training, proposes an asynchronous design using gradient accumulation and a global micro‑batch count to preserve loss equivalence, and introduces LogitsExpress for efficient top‑K knowledge‑distillation communication, all implemented in the lightweight LiteScale framework.

Distributed TrainingKnowledge Distillationasynchronous rollout
0 likes · 16 min read
How LiteScale Cuts Wait Times in Large‑Model Post‑Training with Gradient Accumulation