boltUpdate
Tools & SDKs
·
Jul 8, 2026
·
5 min read
I used to think the commit was the natural unit of software history. It is clean: a hash, a message, something CI can chew on and a reviewer can revert, cherry-pick, or blame. Then AI coding agents made the gap around the commit impossible to ignore.
scienceDeep Dive
AI & LLM
·
Apr 21, 2026
·
11 min read
Before MCP existed, adding tools to an AI application meant writing the same glue code over and over. You had OpenAI’s function calling syntax. Anthropic had tool use with a slightly different schema. LangChain abstracted over both, but now you depended on LangChain’s versioning decisions. Every new model provider meant rewriting your tool definitions. Every new tool meant re-registering it across every AI integration you maintained.
scienceDeep Dive
Developer Tools
·
Mar 21, 2026
·
12 min read macOS has had built-in dictation since Monterey. It is fine: press and hold a key, speak, done. But it requires Apple’s servers (unless you download the enhanced on-device model), only works in some apps, and you have zero control over punctuation, formatting, or hotkeys.
scienceDeep Dive
DevOps
·
Jan 3, 2026
·
9 min read Expose localhost with a stable custom subdomain using Cloudflare Tunnel — a free ngrok alternative that works behind NAT and corporate firewalls, with no session limits.
scienceDeep Dive
AI & LLM
·
May 25, 2025
·
8 min read
At some point I had three side projects each talking to a different LLM provider, with API keys pasted into three .env files and three slightly different client wrappers. Swapping GPT-4o for Claude in any of them meant editing code. That is a silly amount of friction for what is, underneath, the same chat-completion call, so I put a LiteLLM proxy in front of everything and never went back.