Lemomo

Indie dev stress-testing the AI hype.
Curiosity over ego. Thinking over coding. Doing over watching. Sharing over gatekeeping.

[Lemomo @lemomo_ai]

Retrospective engineering feels like a good direction to explore, give it a shot. linked my two github projects, a star would mean a lot rn ⭐

[Lemomo @lemomo_ai]

Built two plugins to analyse vibe coding project history.

🚀 Claude Radar https://t.co/W4VHLzgAtv
🚀 Codex Radar https://t.co/8OvZYwHSGG

- evaluate your chats, prompts, tools, skills, workflow patterns and project architecture,
- generate a report across 9 dimensions of AI collaboration.
- get insights, improvement suggestions, and ready-to-use prompts or guides.

Really helpful if you’re serious about improving your AI coding skills.

[Lemomo @lemomo_ai]

Honestly, prompts aren't ending. https://t.co/kUDnP7lsu7 just moving into loops, evals, tool contracts, and failure rules. I still spend way more time defining what good looks like and what should fail than writing clever prompts. The prompt gets smaller, the system thinking gets bigger.

[Lemomo @lemomo_ai]

@charles_irl This is the good kind of infra nerd stuff. Spec dec can feel like free speed, but only when the draft model actually predicts well. Otherwise it.s just extra moving parts.

[Lemomo @lemomo_ai]

Interesting idea, but cheap inference is only half the story. For me, reliability matters a lot more than people admit. One flaky model route, weird latency spike, or silent behavior change can eat all the savings fast. I'd want to see cost plus fail rate, not just cheaper tokens.

[Lemomo @lemomo_ai]

Honestly, this is the kind of tiny UX thing that beats another flashy benchmark. When I'm mid build, switching behavior inline matters more than hunting through settings. The only catch is remembering what you changed, because one hidden config can make debugging feel haunted later.

[Lemomo @lemomo_ai]

@swyx @QuinnyPig one wall and let them fight it out in the open. the ones that survive being stared at are the ones worth shipping 🔥

[Lemomo @lemomo_ai]

@jaykhan here we go! 😁

[Lemomo @lemomo_ai]

@AlchainHust 我属于你说的两种人 但是还是打算买一下

[Lemomo @lemomo_ai]

真正意义上的解放了双手 好玩

[沐阳 @yyyole]

哈哈哈！好沙雕！
但不得不说， 非常实用！！
科技进步，就是代替人的一些“重复动作”！

[Lemomo @lemomo_ai]

@YuLin807 在大学的时候就有了。满足了日常某些需求

[Lemomo @lemomo_ai]

@AdrianPunk115 这个提示词收藏了 很美

[Lemomo @lemomo_ai]

the loop is the product here, but the judge agent only works if it has real receipts. https://t.co/aEMgZcH5zx had agents confidently pass junk until I wired in tests, logs, and a tiny eval set. Without that, it.s just three agents agreeing with each other faster.

[Anatoli Kopadze @AnatoliKopadze]

Anthropic engineers just showed how they build a full app from scratch, using a loop of agents

40 minutes from the team behind Claude Code

they used three agents: one to plan, one to build, one to judge, cycling until the app actually works

the winners won't have the smartest model, they'll have the best loop

watch it, then read the full guide on how to actually use loops below

[Lemomo @lemomo_ai]

@bindureddy Cool demo, but yeah, I.d trust it more with a boring receipt. Run it 20 times on a messy real app and show the misses. My local agents always look smart until one modal shows up and everything goes sideways.

[Lemomo @lemomo_ai]

@DevBegie I couldn't agree with you more. I reckon being able to solve problems and the way we think through things is actually what matters most.

[Lemomo @lemomo_ai]

@eternityspring 学起来 做起来

[Lemomo @lemomo_ai]

@jakevin7 很厉害向你学习 关注啦

[Lemomo @lemomo_ai]

This is the new split in AI coding. Chat is advice. Agents are workflow. The dev who learns to design the loop will get more leverage than the dev waiting for the next model leaderboard.

[Lemomo @lemomo_ai]

The model didn't win AI coding. The loop did. Claude Code and Codex feel different because they keep context, run tools, see errors, and try again without making you babysit every step.

[Lemomo @lemomo_ai]

The gap now is not just smarter tokens. It is who owns the loop. If the tool can inspect, act, verify, and recover, a slightly weaker model can beat a stronger model trapped in chat.