Health to the Web

Running Claude Code in terminals is ok, but I felt managing it all needed a better user interface to organize and track.   conductor is an example of what such a user interface could be

claude code npm tech stack:  typescript - claude code is written in ts (pssst: typescript is a must know language imo) react - ui is written in react and uses ink for interactive command line ink - react components for command line! used by a whole list of AI whos who with command line yoga - embeddable flexbox layout engine and  bun  - js runner, runtime, bundler; choose over webpack/vite etc. because bun is faster) npm to distribute claude code Started as a simple project to query what music someone was listening to. Then added capabilities to access the file system and run batch commands. Usage spread rapidly within Claude Code team who dogfooded it. "around 90% of claude code is written with claude code" (not by, with) claude code is a thin wrapper over the claude model, they deliberately want people to experience the raw model, not obstructed by much business logic a guiding principal is: simplicity, choose the simplest approach possible the most complex part of cl...

Have you noticed that cursor chat requests can use a lot more tokens than you'd expect?  Matt Pocock said it well: "tokens are the currency of LLMs". You're charged by the token. A little, but it does add up. So we need to pay attention to token usage. I ran some tests in cursor chat to review token usage and was surprised by how many tokens are used by my chat requests. I ran these tests in a large repo which has a number of cursor rules files defined.  Tests: 1. ask a general tech question in chat, not related to specific code in repo; context used : 19.7k tokens prompt: "how should I choose between useSWR and react-router v6 for data fetching?" to contrast, same question in Claude 4.0 outside of cursor user 28 input tokens and 768 output tokens in response to contrast further, same question in Gemini 2.5 Pro outside of cursor used 19 input tokens and 1060 output tokens in response almost one twentieth the token usage of cursor chat!!! wow 2. ask to write...

My notes from the stack overflow survey 2025 Interestingly usage of AI tools is widespread (84%). But  positive sentiment has decreased 10% to 60% since 2024 two thirds of devs are frustrated by AI solutions that are "almost right" and debugging AI generated code is more time consuming (45%) more devs actively distrust (46%) AI tools accuracy than trust it A majority of devs don't use AI Agents, but a majority of those who used say it does increase productivity. But I'll bet that increases significantly by next years survey. There's more details when you drill down into subsections in the survey such as AI Developer tools . e.g. 56% say AI is "bad" or "very poor" or "don't use" AI for complex tasks. And 14% are neutral. Only approx 15% are vibe coding The most popular web frameworks among professionals are nodejs (49%), react (47%), jquery (24%), nextjs (22%), asp.net core (21%) , Express (20%), Angular (20%), vue.js (18%) The mos...

These are my notes to Matt Pococks aihero.dev course "ai engineer roadmap" https://www.aihero.dev/ai-engineer-roadmap What is An AI Engineer Matt said his course is partly based on article from Latent Space: "The rise of the ai engineer" " An AI Engineer is a software developer who builds applications powered by AI" An AI Engineer needs strong software engineering fundamentals ability to build reliable scaleable applications knows modern AI tools and frameworks focuses on user experience and applications AI Engineers - use models, use prompt engineering, pipelines/chains, optimize cost/speed/performance, infra, evaluate systems. Different to an ML engineer who: build and train models, heavy math, phd level skills Yes, web developers can become AI Engineers. And Typescript is growing fast and makes a great fit for AI systems (well Matt would say that, wouldn't he!..but I do think it's true) What can you use LLMs for? 1. Converting unstructured to st...

TDD, AI Agents and coding with Kent Beck https://www.youtube.com/watch?v=aSXaxOdVtAQ This podcast was really fun to learn from and I recommend. Kent is famous in the programming world, so his take on AI is worth learning from. Kent says he's spending 6-10 hours a day programming and in 50 years of programming it's the most fun he's had, "its a blast". Kents using agentic tools where it generates a bunch of code from a single prompt. Kent says nobody knows what works so try it all. So we should be experimenting.  Kents tried a number of different languages as he's experimented. Kent thinks of AI as an "unpredictable genie". Its a genie in that "it grants wishes and you wish for something and you get it, but it's not what you actually wanted: it volunteers features, doesn't care about design, willing to cheat (delete/modify tests) there can be some good things with this, but some bad I love this metaphor. I have experienced these aspects o...