Founder in Residence at Antler. Former CTO of 12Go, APAC’s leading ground transportation OTA, where I spent 10 years scaling the platform to 30,000 bookings daily with a remote team of 50 engineers.
Based in Singapore. Building what’s next.
Reading WhatsApp from an AI Agent Without Giving SSH Full Disk Access
The usual advice for reading protected Mac data over SSH is to give sshd Full Disk Access. That hands every SSH login your Mail, Messages and Safari history. A 154-line launcher gives the grant to one fixed program instead.
Why Gemini Translates Into Russian Better Than Claude and GPT
For months I have sent every Russian translation through Gemini, because Claude’s Russian reads like American English. I assumed Google’s search index was the reason. The data says Gemini really is ahead, but the lead is one year old, and it is not the index or the tokenizer.
The Real Cost of a Claude Code Session Is the Language Server, Not Claude
Summing RSS says 26 Claude Code sessions eat 50GB. Measuring PSS/USS says 32.5GB — and the entire swing is the TypeScript language server, not Claude.
The Path Has To Exist: Fixing Claude Code's CI Panel for Remote Dev (Without Melting a CPU)
Claude Code’s desktop CI panel shells out to local gh in the session’s working directory — a remote path that doesn’t exist on my Mac. I fixed the premise by making the path exist: first with a FUSE-T mount that pinned a CPU at 100%, then with a git-worktree mirror that doesn’t. Plus the open-source tool that does it for you.
Web 4.0 Is Open Databases
I asked my AI agent to plan a family escape from Chiang Mai’s burning season. It reverse-engineered a proprietary air quality encoding, scraped flights, checked fuel costs, and compared 15 cities across 10 years of data. This is what Web 4.0 actually looks like: open databases + agents that query them.
Agent Experience (AX): 10 Principles for CLI Tools AI Agents Can Actually Use
We have UX. We have DX. But AI agents are now the primary users of developer tools, and nobody’s designing for them. Here are 10 principles from watching real agent behavior through usage telemetry.
How We Make Claude Remember: Learnings Over Skills
Skills don’t reliably auto-invoke. We built a three-layer system: searchable learnings files, a curation skill, and a post-commit hook that reminds you to document.
Serve Markdown to AI Agents (10x Smaller Payloads)
An entire infrastructure layer (CSS, JS, frameworks) is becoming optional for a growing class of consumers. Here’s how to serve markdown via HTTP content negotiation.
The AI Data Trap: Why You Can't Opt Out
Your competitor uses Claude or GPT to move faster. If you don’t, you fall behind. That’s the trap.
The Best Agent Architecture Is Already in Your Terminal
The Best Agent Architecture Is Already in Your Terminal My project’s CLAUDE.md file had grown to 55KB—242 learnings crammed into one massive file. The problem? Claude prepends this file to every single prompt. A 55KB context file means less room for thinking and acting. Sessions hit context limits faster. Compaction happens sooner. I noticed the degradation: sessions became noticeably shorter, context compaction triggered more frequently, and the agent seemed to lose track of longer conversations. ...