Agents, MCP & Developer Experience at IBM ⚑ πŸ₯‘ Tech Author, Speaker, Entrepreneur πŸš€ Sharing opinions (βœ‰οΈ hello@hackteam.io)

Santa Clara, CA
🍾 SOFTWARE DEVELOPER OF THE YEAR I’ve won a @hackernoon Noonies Award for my contributions to the developer community Thanks everyone for voting πŸ™Œ πŸ™Œ
13
7
144
πŸ‘‡
It is easier to build features than it is to announce them
1
Replying to @philnash @resend
Awesome, happy for you!
1
Replying to @uixmat
that's pretty cool, im done with boring charts
1
Replying to @thegarrettscott
He has herdr installed which is great at loopmaxxing, listen to the latest episode on lex fridman
I’m building a personal OS that exposes a MCP apps interface to my existing agent interfaces like Codex. I need to have a central hub that’s always on for this purpose, the central hub has to be local but can spin up sandboxes in the cloud when needed. I would name it Kazu, after the siberian dwarf hamster I had in my childhood
if you’re afraid AI will take your job, then it probably will
1
1
6
A signup form shouldn’t need AI to remember my name. HTML already has autocomplete="given-name", "family-name" and "email". Give the browser the right hints before inventing a smarter onboarding flow.
2
3
Replying to @ljayham
why put ai functionality in your product without testing it..
1
A voice-agent demo I’d like to see: I turn away and answer someone else in the room, then come back. Does it know that conversation wasn’t for it? Knowing when to stay quiet matters as much as sounding human.
1
5
Roy Derks πŸš€ retweeted
so many gems and great tips in this talk from @yminsky about how to improve your codebase for agents β€’ agents thrive on feedback, and types are one of the best kinds β€’ make illegal states unrepresentable with types, and it enforces global rules across your codebase β€’ property based tests, fuzzing, and even full-system deterministic simulation testing β€’ expect tests: just print stuff out and capture it in the test. makes behavior legible. it's very similar to how compilers have fixture tests, it reduces the review surface area β€’ formal methods used to be very expensive: seL4 is about 8,700 lines of C and took around 25 person-years, with 23 lines of proof for every line of C code, but agents change the roi piped.video/watch?v=rUYP4C29…
133
177
2,640
Replying to @kentcdodds
K for kent or kody though πŸ€”
1
thank you gemini
1
4
Replying to @orcdev
but you cannot have it autoswitch / rotate between them? at least i haven't found out how
1
Replying to @blackgirlbytes
Short term vs long term imo. SEO / Ads where always the quickest path to adoption but also easy to replicate for other companies, while community and your reputation are not
Replying to @Yuchenj_UW
this is the only cool demo i saw so far, thank you
fastest way to make yourself irrelevant is by turning a blind eye luckily many others are driving the future of open source with/for/using AI
hi @t3dotcodes the github star counter on your website is way behind love the app, thanks
3