cedrickchee

Building With Fable 5

If you remember one sentence, make it this:

Fable rewards ambition when the boundaries and verification are concrete.

That is the shift.

cedrickchee

What is Taste?

One word keeps coming up in AI discussions: taste.

Everyone talks about it, but almost no one defines what they actually mean.

If taste is supposed to be the moat in the agentic AI era, we should probably define it first.

Taste is:

• judgment when the available metrics do not yet fully define the right answer.

cedrickchee

Defining Taste

“Taste” is the ability to consistently make high-quality qualitative judgments where no objective metric exists. It’s the creation of something that feels right intuitively, with no real justifiable way to measure that. But when you do it, people feel it.

A person with “good taste” is someone who can do this repeatedly, consistently. The funny thing about taste is that it’s hard to create, but its result is very easy to copy. Once someone makes a tasteful decision, others can imitate it almost immediately.

This is usually an argument against the existence of taste: “look how easy I can copy your work!” And yet, you couldn’t create the work without first having someone to copy it from. One has taste, the other doesn’t.

There have always been people with consistently good taste. But taste is coming up more regularly than ever before. It is becoming a critical differentiator.

cedrickchee

AI Exploration 2026

Learning where AI is perhaps going, agentic AI workflows, AI disruption, and SWE transformation.

Over the past year, I've been thinking about AI agents, loop engineering, and verification systems.

A few areas I'm particularly excited about:

• Software factories and formal methods
• Applied AI research in software verification and correctness
• Infra for reliable AI agents:

cedrickchee

Claude Fable 5

its a myth

a fable

Claude Fable 5 by Anthropic, releasing tomorrow: https://news.ycombinator.com/item?id=48450521

cedrickchee

Codex Mobile Pairing on codex-desktop-linux

These notes describe the patch used to make Codex Mobile discover the unofficial Linux desktop port from https://github.com/ilysenko/codex-desktop-linux.

Important

You do not need to patch the Electron app to connect Codex Mobile to Codex Desktop. You can enable the bridge by adding these feature flags to the Codex config file, usually $HOME/.codex/config.toml:

[features]
remote_connections = true

cedrickchee

AIE Singapore 2026 Leadership Track Recap

Moved to my blog here: https://cedricchee.com/blog/2026-05-23-aie-sg-leadership-workshop-recap/

cedrickchee

Singapore's Summer of AI Has Arrived

The Summer of AI is in full swing in Singapore.

This weekend, more than 1K builders, founders, and operators are expected to walk into the first Asia edition of the AI Engineer conference — an important conference for people looking to wield the power of AI rather than just discuss it. Super pumped for it. Feels like Christmas came early.

Personally, I'm already building, but this conference arrives at the right moment. I want to ship systems into production - go deeper on agents, workflows, infra, production patterns, orchestration layers, evals, AI operating models, governance, and org design in the agent era.

The industry is shifting from "should we use AI?" phase. The hard questions now are operational:

cedrickchee

NanoClaw — Personal Claude Assistant

A self-hosted, compounding-memory AI assistant running on a Raspberry Pi.

---

What Is This?

NanoClaw is a personal AI assistant built on Anthropic's Claude that runs entirely on a Raspberry Pi. It connects to messaging channels (WhatsApp, Telegram, Slack, Discord), processes voice and images, schedules recurring tasks, and — unlike a standard chatbot — accumulates knowledge over time through a structured memory system.

---

cedrickchee

Project Glasswing Is Not Just Marketing Fluff

TL;DR: Project Glasswing is not just PR, but the interesting part is not Anthropic’s narrative, it is the underlying shift in capability and what that means for software security.

Over the past week, some of the most credible people in security have been pounding the same drum: AI-assisted vulnerability research is getting real, fast.

Thomas Ptacek (tptacek) flatly wrote that “vulnerability research is cooked.” Simon Willison (simonw) highlighted the same shift. Daniel Stenberg of curl has also said AI has gotten genuinely useful at finding bugs and vulnerabilities. Colin Percival (cperciva), former FreeBSD security officer. The most significant individual contributions in the narrative given cperciva's credibility