←
limone 🍋5,880 posts
limone 🍋 avatar

limone 🍋

@limone_eth

i build things in health & longevity | co-founder & CTO omea.io

◷ Joined March 2021▧ 810 Photos and videos
limone 🍋 avatar
limone 🍋@limone_eth·Nov 10

launching Waggle 🐝 stop checking terminals. your agents bring every question and review to you in one inbox, with the mockups and docs to decide fast answer in a click, and the agent picks up where it stopped free, open source 👉 waggle.so

0:46
limone 🍋 avatar
limone 🍋@limone_eth·Oct 2

"A lot more of our work will rise up the abstractions into oversight and understanding"

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

Post attachment
Colin @ Dreamwork avatar
⟳ limone 🍋 retweeted
Colin @ Dreamwork@colindoeswork·Oct 1

Introducing Dreamwork, the last tool you'll ever need to find your dream job. With just a resume we match you to millions of jobs, tailor each resume and submit them for you - all with just a click. But it's more nuanced than that ⤵

0:44
limone 🍋 avatar
limone 🍋@limone_eth·Sep 30

🙂‍↔️🙂‍↔️🙂‍↔️

TBPN@tbpnSep 29

.@sama says the advice to pick one thing to build and pour all your focus into it no longer applies. "The canonical advice that was correct two years ago was, 'Pick one, and put all your effort into it, because you can't build all 30 things.'" "You can now build all 30 things. And you can get people to use them all. And you can work more on the ones that work." "So I think this mindset of lots of ideas, quick feedback, and being open to a lot of things not working is great for this new era for how people build."

0:57
limone 🍋 avatar
limone 🍋@limone_eth·Sep 16

I'm 30. Italian, based in Lisbon. Building a health tech startup as co-founder & CTO. Looking to connect with more founders, biohackers & healthmaxxi 🧬

Post attachment

I'm 29. Solo founder from Brazil, based in Barcelona. Looking to connect with more marketers & indie hackers!

Post attachment
limone 🍋 avatar
limone 🍋@limone_eth·Sep 2

the problem with “personalized” medicine is that it often adapts the treatment to the person, while still aiming for targets defined by the population. after almost two years trying to understand what’s happening to my thyroid, i realized i may have been asking the wrong question: not “what works, on average?” but “what works for me?” that led me to n=1 experiments, and to how hard it actually is to run them well higherstate.substack.com/p/n…

Post attachment
limone 🍋 avatar
limone 🍋@limone_eth·Aug 20

shared so many moments, experiments, events, late nights and memories with the Talent Protocol team over the years very grateful our paths crossed, and proud to have been a small part of the journey @0xmacedo, @pcbo, @leal, @tolga and team what a ride. i'm sure these years taught you a lot, and even more sure you'll be up to something great next you'll never build alone 🫡

@iptsai has acquired Talent Protocol, with support from @protocollabs. Builder Score is becoming a public good. Interplanetary Talent Services (IPTS) will receive part of our reputation data to match builders with roles across AI, crypto, hardware, life sciences and other frontier technologies. The Builder Score will live on as a public good, running locally in the browser, and using public data from GitHub and 4 blockchains. Every calculation can be verified and builders can publish their scores as attestations on @base. Together, they carry 5 years of work forward: → 6.6 million builder profiles and 86 million events indexed → More than $600,000 distributed through Builder Rewards → 116 builders from more than 15 countries supported through Talent House Talent Protocol will conclude commercial operations. The API, Talent+ and social channels will close at the end of August. The team is not joining IPTS or Protocol Labs, and $TALENT was not part of the acquisition. A deep thank you to every builder, team member, investor, partner and advisor who helped us build Talent Protocol. Read the full story and the Protocol Labs announcement in the replies. ⤵️

Post attachment
limone 🍋 avatar
limone 🍋@limone_eth·Aug 19

i haven't been reading a single line of code for months now i focus on clearly defining what needs to be built: writing user stories, producing context files for agents, and defining acceptance criteria then I review the output against those criteria, test that it does what it's supposed to do (lately i've started to automate this part as well), and iterate from there curious how many others are already working this way

David@dzhngAug 18

software engineering Q3 2026

Post attachment
limone 🍋 avatar
limone 🍋@limone_eth·Aug 18

farcaster is where i leveled up the most in the past 4 years. where i found incredible people: builders, creators and founders from all walks of life learnt a lot, built a lot, failed a lot, made some of my closest friends and somehow found myself surrounded by people who kept pushing me to think bigger and build better grateful for this weird little corner of the internet and everyone i crossed paths with along the way long live @farcaster_xyz 🙏🏻

update on @farcaster_xyz, @clanker_world and @neynarxyz we’ve started a process to look for a new home / team to run the products going forward. earlier this year, this seemed to be a good fit for our team: it was a developer-first network, and we'd been serving developers from the start. There’s been a lot of change since then and we’re not the right fit for what’s needed next. talking to a few teams we think could be a good fit for running decentralized social apps and related developer products. If you’ve thoughts / are interested, reach out. our company will return its balance sheet (most of it remains) and team members will move on to something new. this is not a decision we made lightly. I’m optimistic that with this next iteration, Farcaster will find its long term fit. it’s loved enough that it’s unlikely to simply perish - thanks to all of you, and lindy-ness.

limone 🍋 avatar
limone 🍋@limone_eth·Aug 18

building an mvp in health tech is a whole different world i used to ship, measure, iterate in days - one fast loop, tight feedback, move on now i'm running two: 1) product / interface -> days, weeks 2) protocol / body -> months you can't sync them, and you don't set the pace of the second one the part nobody tells you: before we say anything to a user, that a marker is high, that something will help them, we have to ask ourselves what's behind it and if and how we should share that information that question kills more ideas than any technical constraint "minimum" starts much higher than i expected. a rough consumer app looks scrappy. a rough health app is scary as nobody messages you to say they don't trust you - they just leave is there anyone here with experience in health tech willing to share their way around this?

Post attachment
ETHRome 🇮🇹 avatar
⟳ limone 🍋 retweeted
ETHRome 🇮🇹@ETHRome·Aug 11

We're happy to welcome @arkivnetwork as a sponsor for ETHRome 2026! 🇮🇹 Web3 databases with blockchain features and guarantees. Arkiv brings queryable, tamper-proof, wallet-owned data to our 40 builders. Grazie @arkivnetwork and see you in Rome! 🏛️ Apply here 👇

Post attachment
ETHRome 🇮🇹 avatar
⟳ limone 🍋 retweeted
ETHRome 🇮🇹@ETHRome·Jul 21

🏛 Introducing ETHRome IV - 2026 40 selected builders 3 days building inside @urbeEth Hub, Italy's Ethereum Community Hub 🐺 We want real work already in motion, not weekend projects. 📅 11-13 Sep · Rome APPLY NOW 👉 luma.com/huhelf53

0:09