Case Studies

从 0 到 1 搭建能上生产的 Agent 系统 — 代码、踩坑、复盘。

132 articles Categories色 #10B981 Newest 2026-11-07
Archive · Case Studies 11 articles
Case Studies

What $20,000 Really Buys for an Open-Weight Image Model

A two-person lab trained the PJIT-21K text-to-image model from scratch for roughly $20,000 and released its weights under Apache 2.0. This analysis breaks down training, inference, licensing, and deployment costs for teams evaluating open models.

2026-11-06 Source 2026-11-04 7 min 211 views
Case Studies

Fujifilm's Fivefold Tape Expansion and AI Storage

Fujifilm plans to increase tape production roughly fivefold as AI drives demand for durable, low-cost storage. The expansion highlights a growing infrastructure cost that GPU budgets often overlook: keeping inactive data accessible without keeping it permanently online.

2026-11-04 Source 2026-11-02 8 min 211 views
Case Studies

GitBook Targeted by an AI Agent: A Permission Failure

GitBook confirmed a targeted attack driven by an AI Agent that disrupted its App, API, and published documentation. The incident highlights how excessive, persistent, and combined permissions can turn an Agent into an effective attack path.

2026-11-04 Source 2026-11-03 7 min 211 views
Case Studies

Qwen 3.8 27B Inspects Model Weights Locally

Simon Willison ran Qwen 3.8 27B on his laptop to inspect another model’s weights. The experiment offers a practical workflow for connecting a local LLM to reproducible statistics, hypothesis generation, and verification without treating generated explanations as causal proof.

2026-11-04 Source 2026-11-03 8 min 211 views
Case Studies

Oracle’s $20 Billion Raise Marks AI Cloud Expansion

Oracle plans to raise up to $20 billion in stock and debt for AI data centers and computing capacity. The move shows how AI cloud competition now depends as much on financing capacity as on customers, GPUs, and delivery capabilities.

2026-11-03 Source 2026-11-02 6 min 211 views
Case Studies

OpenAI Scales Git, but Repositories Hit a Wall

OpenAI's account of scaling Git sparked 187 points and 104 comments on Hacker News. The real challenge is what happens when multiple AI Agents generate branches, commits, reviews, and merges faster than existing repository and CI infrastructure can handle.

2026-11-03 Source 2026-11-02 7 min 211 views
Case Studies

Anatomy of an Edge Browser Agent Attack Chain

Orange Tsai breaks down a logic-based attack chain in Edge that combines model reasoning, tool calls, and browser state. The analysis highlights where least-privilege controls, state checks, and auditability are missing from Agent security.

2026-11-02 Source 2026-10-29 7 min 211 views
Case Studies

Volta Infostealer Uses LLMs to Rank Victims

Talos reports that Volta uses an LLM to assess the value of potential victims and prioritize data theft. Defenders need to correlate model calls, file access, and exfiltration rather than rely on malicious-prompt detection alone.

2026-11-01 Source 2026-10-31 7 min 211 views