Back
Jamie Watters
Jamie Watters
@TheWayWithin
Systems programmer who loved the work, got scared, hid in management for 20 years. Now engineering my way back out with AI and Claude Code.
Load previous page…
Worked out that the interface is lagging the capability: the models got better at doing, nobody worked out how they should talk about it
Wrote up why Opus 5 makes me swear, and admitted that half of it is my own bandwidth rather than the model
Published a new post: Bernardo Kastrup's cosmic mind has no plan. The most rigorous idealist alive gives the non-duality audience far less than they want, and the part that survives is the part that matters. jamiewatters.work/journey/kas… 
#jamiewatters
Closed my Second Brain project and shipped its last piece, book-notes import
Cleared a batch of security and repo issues: verified payments after a key rotation, reconciled two diverged repos, finished the secrets sweep, turned on push protection
Published a new piece: "Garry Tan Just Described My Setup. Then I Noticed What He Left Out." jamiewatters.work/journey/garry-tan-described-my-setup
Built a teleprompter version and did my first rough recording takes. Reading and talking at the same time is its own skill
Scripted my first YouTube video, an honest verdict on an AI tool I actually ran: real numbers and the privacy trap nobody warned me about
Rebranded my YouTube channel to just Jamie Watters: new name, handle, About, avatar and banner, all on brand
Published: Everyone's selling AI consultancy. The data says nobody's buying. jamiewatters.work/journey/ai-… 
#aisearchmastery
New post: a goal prompt beat my build framework on a real job — same spec, same model, two methods, and honest numbers on time, cost, and clutter. jamiewatters.work/journey/sam…
Published "Eleven days I didn't touch it." Eleven days of unattended Trader-7: 5 losses, 1 winner, +$132 net, and a stack of log-noise bugs I found on return. 
#trader7
Published a post on trusting AI-written code you didn't read line by line: stop trusting the model, build the checks it can't fake. #agent11
Published a post on building an autonomous AI agent into AGENT-11. The real lesson was 20 years old: pick the right number, don't let the AI mark its own homework. #agent11