human software engineer

🇵🇪
Joined July 2022
Anthony Cueva retweeted
Grok bot for builders 🇵🇪 The builder energy in Peru is always so high! #buildinpublic #techevent
1
5
65
We're bringing Peru's first pop-up Hacker House to Huancayo 🇵🇪 Meet Launch Mafia. This October 22–25, during Huancayo Tech Week, we're bringing together founders, builders, and community leaders to live, build, and connect under the same roof. 4 days. 3 nights. 8 residents. The idea is simple: instead of meeting at conferences and going our separate ways, what if we actually spent a few days building together? → Talks, workshops, and connecting with the local tech ecosystem → Hack nights and time to build our own projects → BBQs, conversations, and sharing ideas beyond the conference → Content creation and behind-the-scenes of what we're building → Meeting other founders and community builders from across Peru We're putting this together through @nucleo_lab × @CrafterStation. Maybe we'll ship new products. Maybe new collaborations will come out of it. Either way, we're documenting the whole experience. 🏠 launchmafia.dev/ 📅 luma.com/launch-mafia
1
4
7
330
Anthony Cueva retweeted
We’re just getting started ⛰️ Happy building! 👨‍💻 #HackTheAndes
2
3
54
learning the layer below your tools changes what you can understand. @unclebobmartin tells @mattpocockuk why he used to suggest a weekend of assembly language, in their conversation about agents.
1
36
if every change to a house cost $1, would you plan it the same way? @unclebobmartin uses that thought experiment with @mattpocockuk to explain his preference for small changes and feedback.
36
keep the quality values. reconsider which human work habits an agent needs. @unclebobmartin makes that distinction in his chat with @mattpocockuk.
37
a module with a clear purpose gives an agent less conflicting context to deal with. @unclebobmartin and @mattpocockuk discuss why clean boundaries still help when agents write the code.
23
architecture rules can be checked after the agent writes code. @unclebobmartin explains his dependency checks to @mattpocockuk: specify which modules may depend on each other, then require violations to be fixed.
25
writing the feature is one stage of @unclebobmartin's workflow. in his chat with @mattpocockuk, he walks through separate agents for code cleanup, mutation testing, and qa.
28
a qa procedure should actually use the system. @unclebobmartin tells @mattpocockuk how he turns a human-written story into acceptance tests and a procedure that works through the ui.
29
focused tasks help keep agent context manageable. @unclebobmartin's chat with @mattpocockuk covers fresh contexts, parallel work, and the startup cost of handing work between agents.
26
give an agent a check it can run, then let it work until the check passes. @unclebobmartin explains the quality tradeoff to @mattpocockuk. that extra work has a cost too.
32
a longer instruction file doesn't guarantee better results. @unclebobmartin talks with @mattpocockuk about context getting lost in the middle, and why he keeps the initial prompt short.
30
messy code can trap an agent in a cycle of fixing one bug and creating another. @unclebobmartin describes seeing this happen in his chat with @mattpocockuk. cleanup still matters when an agent writes the code.
1
20
a passing test suite can still miss broken behavior. @unclebobmartin explains mutation testing in this chat with @mattpocockuk: change the code on purpose and check that the tests notice.
1
29
product work means understanding enough problems to find a solution that addresses many of them. @thdxr explains to @GergelyOrosz why that still takes experience and careful thinking.
40
agents make it easier to replace old patterns across a codebase. @thdxr tells @GergelyOrosz why opencode is using that ability for cleanup and a better place to work long term.
2
105
Replying to @maritime_sh
@maritime_sh + Notion Community Fest 2026.
1
1
1
7
400
ai time savings don't automatically become more output. @thdxr tells @GergelyOrosz why people may finish their work sooner, and why motivation and compensation change that outcome.
18
Anthony Cueva retweeted
Banks, funds and fintechs are on stage at @aiDotEngineer NYC this week, talking about agents in production. One question we'd add to every deployment checklist: When the agent is wrong, can you show what it remembered, where that came from, and who corrected it?
1
1
3
72