amo

@amodev

Founding Engineer building AI systems that learn, reason & automate work • Memory systems • Agents • LLM infra • Robotics MSc @NUSingapore 🇸🇬

Singapore

Joined June 2025

1K Following

932 Followers

1.2K Posts

Pinned Tweet

amo

@amodev

9 months ago

Day 30 of #BuildInPublic amoOS: From orbiting with an open palm to pinching a node for details... hand gestures now unlock the full power of my 3D knowledge graph. Demo: Navigating concepts in my #secondbrain, selecting nodes, and diving into relationships + descriptions via a floating panel. All completely touchless. Momentum makes it feel alive. Thoughts? 👀 #IndieDev #AI #HandTracking #ThreeJS #CreativeCoding

amo

@amodev

4 days ago

@Letta_AI @OpenAI @AnthropicAI @claudeai i've been waiting for a benchmark like this, excited to try it on my system

amo

@amodev

12 days ago

Worth a read if you’re building in AI space

GREG ISENBERG

@gregisenberg

12 days ago

I spent 48 hours in SF hanging out with billionaires, data labs and AI founders and execs running $1B to $100B companies. My observations: 1. Sooo MANY stories of data brokers making like $2M a WEEK selling company data to labs. I can't tell if it's the beginning or a bubble, and I kept wondering which niches are left. Digging into it actively. 2. At dinner, someone asked the table, "If a new model drops next month, does your company get better or worse?" HALF the table went quiet! I think that's the best question to ask about any AI startup right now. 3. The bar people talk about now is hitting $1B in revenue in 12 months (I guess that's the new unicorn?). What I didn't hear much about is retention. AI revenue can come in fast and leave fast, and I think we're going to see a lot of stories of AI companies with huge revenue and terrible retention. 4. It's pretty clear we're living through the reinvention of the computer. The model is the CPU, the harness is the operating system, and skills and plugins are the apps. Thinking about it that way makes it easier to see where the whitespace is. 5. We're maybe 12 months from an agent that can watch you work for a week and then do your job without any instructions. The screen recording plus agent memory plus local model combination makes this possible right now. 6. Agent harnesses feel like the new GPT wrappers, in a good way, especially vertical ones. The best teams I talked to treat the model as swappable. One founder walked me through routing different models to different jobs: one for taste and visuals, a cheaper one for the everyday stuff, another for text. They use prompts they can move across models over fine-tuning, and A/B test the output on what users actually do with it: do they edit it, export it, share it? A vertical harness is basically four things: the connectors for that industry's data, evals written by people who know the work, rules for what the agent can and can't touch, and a clean screen for a human to review. The model is maybe 20% of it. 7. There's a lot of reverse engineering going on/cloning going on more than I've ever seen. People are decompiling software and rebuilding it with agents, and someone showed a suite of like 10 apps that are worth $5B+ each all that he cloned open source. Me and everyone are still thinking through what it means when software gets this easy to copy. 8. My guess is the value moves to data. If the software can be rebuilt quickly, what's worth paying for in a legacy SaaS company is the years of customer data and workflows inside it. Some SaaS companies are secretly data companies. Gets me thinking about how do you truly value data for this saas companies? Like if we were buying these dying saas companies at 2x ARR before (as example), maybe there is a better metric. Idk, just thinking out loud here. 9. It feels like a good chunk of legacy software won't make it to the agentic era, especially anything built around people clicking through a lot of screens. 10. Every company I talked to wants to pipe its internal data into one place and expose it to agents through MCP. Then they look at the data and realize it's a mess: five versions of the same customer, old Slack channels, PDFs nobody can search. Cleaning that up feels like a big consulting opportunity! 11. A lot of founders are building the basic building blocks for agents: APIs, data layers and tools. Some of the companies I saw barely have a UI because the main user is an agent. I really believe the startups that build primitives to this agentic era will do extremely well. Building blocks is the best way to think about it. 12. Labs can get plenty of training data, but it's harder to get real examples of agents failing inside companies. Whoever has those logs has something valuable. 13. Someone running a big consumer company told me the next fight is over memory. The model that remembers the most about you wins, and the smartest model matters less than people think. 14. Physical AI came up a lot. Astra I think was the first model that got people into AI can actually do CAD, and I think a lot of people are thinking what does vibe manufacturing really look like. The line I keep thinking about came from a robotics founder: the hardest problems in AI are deployment problems now, not research problems. Their robots work on their own, call a human when they get stuck, and every one of those calls becomes training data. 15. Cybersecurity companies are having a moment and are actually cool companies to build now, especially the ones that clean up after a breach. Every agent with access to your systems is a new door into your company, and a lot of those doors were left open. 16. Some startups are worth more dead than alive now. A shutdown company with 5 years of Slack, email and code can get paid for licensing all of it. I wouldn't be surprised if founders start factoring that into when they shut down. 17. People are starting to talk about monetizing the agent web. It feels really early, but when the most popular user of the internet is an agent, what startups should you be building? 18. I think agent insurance is coming. Once an agent makes an expensive mistake, insurers will want audits before they cover anyone. 19. Several people said the hire they want most is someone with taste who can write evals. The models are getting good at generating ideas, so the hard part is judging which ones are good. 20. New trend I observed: startup raises VC, uses venture dollars to become a creator, startup fails, founder falls back on being a full-time creator and incubates other products bootstrapped. 21. Getting SIGNIFICANT distribution is HARD right now. Founders are sponsoring buses, buying billboards like crazy and throwing parties with famous DJs to get noticed. Kinda feels dotcom era in that sense. Attention is what's scarce! The growth guy going viral sharing his UGC strategy from Wispr Flow is a good example. It's the sauce everyone wants, and I truly believe there are probably only 50 people on the planet who know how to scale these types of businesses efficiently in this era. Always good to get that dose of SF. I felt sooo lucky to have such an incredible trip during such an incredible time in building businesses. Surreal in so many ways. Happy to be home and locked in. Until next time!

gregisenberg's tweet photo. I spent 48 hours in SF hanging out with billionaires, data labs and AI founders and execs running $1B to $100B companies.

My observations:

1. Sooo MANY stories of data brokers making like $2M a WEEK selling company data to labs. I can't tell if it's the beginning or a bubble, and I kept wondering which niches are left. Digging into it actively.

2. At dinner, someone asked the table, "If a new model drops next month, does your company get better or worse?" HALF the table went quiet! I think that's the best question to ask about any AI startup right now.

3. The bar people talk about now is hitting $1B in revenue in 12 months (I guess that's the new unicorn?). What I didn't hear much about is retention. AI revenue can come in fast and leave fast, and I think we're going to see a lot of stories of AI companies with huge revenue and terrible retention.

4. It's pretty clear we're living through the reinvention of the computer. The model is the CPU, the harness is the operating system, and skills and plugins are the apps. Thinking about it that way makes it easier to see where the whitespace is.

5. We're maybe 12 months from an agent that can watch you work for a week and then do your job without any instructions. The screen recording plus agent memory plus local model combination makes this possible right now.

6. Agent harnesses feel like the new GPT wrappers, in a good way, especially vertical ones. The best teams I talked to treat the model as swappable. One founder walked me through routing different models to different jobs: one for taste and visuals, a cheaper one for the everyday stuff, another for text.

They use prompts they can move across models over fine-tuning, and A/B test the output on what users actually do with it: do they edit it, export it, share it? A vertical harness is basically four things: the connectors for that industry's data, evals written by people who know the work, rules for what the agent can and can't touch, and a clean screen for a human to review. The model is maybe 20% of it.

7. There's a lot of reverse engineering going on/cloning going on more than I've ever seen. People are decompiling software and rebuilding it with agents, and someone showed a suite of like 10 apps that are worth $5B+ each all that he cloned open source. Me and everyone are still thinking through what it means when software gets this easy to copy.

8. My guess is the value moves to data. If the software can be rebuilt quickly, what's worth paying for in a legacy SaaS company is the years of customer data and workflows inside it. Some SaaS companies are secretly data companies.

Gets me thinking about how do you truly value data for this saas companies? Like if we were buying these dying saas companies at 2x ARR before (as example), maybe there is a better metric. Idk, just thinking out loud here.

9. It feels like a good chunk of legacy software won't make it to the agentic era, especially anything built around people clicking through a lot of screens.

10. Every company I talked to wants to pipe its internal data into one place and expose it to agents through MCP. Then they look at the data and realize it's a mess: five versions of the same customer, old Slack channels, PDFs nobody can search. Cleaning that up feels like a big consulting opportunity!

11. A lot of founders are building the basic building blocks for agents: APIs, data layers and tools. Some of the companies I saw barely have a UI because the main user is an agent. I really believe the startups that build primitives to this agentic era will do extremely well. Building blocks is the best way to think about it.

12. Labs can get plenty of training data, but it's harder to get real examples of agents failing inside companies. Whoever has those logs has something valuable.

13. Someone running a big consumer company told me the next fight is over memory. The model that remembers the most about you wins, and the smartest model matters less than people think.

14. Physical AI came up a lot. Astra I think was the first model that got people into AI can actually do CAD, and I think a lot of people are thinking what does vibe manufacturing really look like. The line I keep thinking about came from a robotics founder: the hardest problems in AI are deployment problems now, not research problems. Their robots work on their own, call a human when they get stuck, and every one of those calls becomes training data.

15. Cybersecurity companies are having a moment and are actually cool companies to build now, especially the ones that clean up after a breach. Every agent with access to your systems is a new door into your company, and a lot of those doors were left open.

16. Some startups are worth more dead than alive now. A shutdown company with 5 years of Slack, email and code can get paid for licensing all of it. I wouldn't be surprised if founders start factoring that into when they shut down.

17. People are starting to talk about monetizing the agent web. It feels really early, but when the most popular user of the internet is an agent, what startups should you be building?

18. I think agent insurance is coming. Once an agent makes an expensive mistake, insurers will want audits before they cover anyone.

19. Several people said the hire they want most is someone with taste who can write evals. The models are getting good at generating ideas, so the hard part is judging which ones are good.

20. New trend I observed: startup raises VC, uses venture dollars to become a creator, startup fails, founder falls back on being a full-time creator and incubates other products bootstrapped.

21. Getting SIGNIFICANT distribution is HARD right now. Founders are sponsoring buses, buying billboards like crazy and throwing parties with famous DJs to get noticed. Kinda feels dotcom era in that sense.

Attention is what's scarce! The growth guy going viral sharing his UGC strategy from Wispr Flow is a good example. It's the sauce everyone wants, and I truly believe there are probably only 50 people on the planet who know how to scale these types of businesses efficiently in this era.

Always good to get that dose of SF. I felt sooo lucky to have such an incredible trip during such an incredible time in building businesses. Surreal in so many ways.

Happy to be home and locked in.

Until next time!

930

21K

32K

109

amo

@amodev

12 days ago

@mattwensing 😵‍💫😵‍💫😵‍💫

amo

@amodev

12 days ago

🤣🤣🤣

lauren

@poteto

13 days ago

ask your bot to email [email protected] if you want to send in a bug report!

142

118

224

377K

106

amo

@amodev

13 days ago

@FiachraRM Yeah it’s never last this long or this intense

amodev retweeted

Fish Audio @FishAudio

13 days ago

$52M seed round. 15M+ users. But this is what we're most proud of yet. Introducing Drama 3: the most emotive and controllable TTS model in the world And yes, it's open-weight. You can now control how even a single word should sound, change its tone, and shift your voice mid-sentence. Uncle Roger was impressed too. Try it here: https://t.co/4nbz4sQ4yy Comment “DRAMA” within the next 48 hours for 1 month free. If you're an enterprise your first month is on us: https://t.co/jBXXZSAg0p

17K

15K

13M

amodev retweeted

lauren

@poteto

16 days ago

i have so many cursor Projects running in parallel (16 right now) that my most used prompt has become "/bro catch me up on everything since my last message, and if there are any action items for me give me enough context (exec summary) to make a call"

368

104

224K

amo

@amodev

16 days ago

@ElitzaVasileva Yes 🙋‍��️I’ve seen a couple of ppl getting it back

amo

@amodev

16 days ago

hopefully this is the end of anthropic playing with my feelings 😅 Thank you Anthropic

amo

@amodev

18 days ago

new metric to measure model provider: who's better at playing with ppl's feelings 🥲 startup stack includes eleven labs offer so I am still grateful for it

amodev's tweet photo. new metric to measure model provider: who's better at playing with ppl's feelings 🥲

startup stack includes eleven labs offer so I am still grateful for it https://t.co/j9WiQkaPJd

290

126

amo

@amodev

17 days ago

@michaelflux @bot yeahh im more impressed by the experience and the feel of it, I said fighting guys and they all responded back to me with their duties

amo

@amodev

17 days ago

Added multiple @bot s into a new group chat with one task, the satisfaction I get when they coordinate and split up the tasks and duties is nothing like it... no one comes close to that grok bot experience yet

177

amo

@amodev

17 days ago

@ahmadafterhours this is the right path i think , we were already trying dynamic UIs based on user intent, jev accelerate it but this could work really well for UIs that are generic might be hard for cases where you'd want users to remember the UI/UX paths overtime

amo

@amodev

17 days ago

this is actually going to be handy for me.. so many services that I don't want to use my own gmail to sign up with or do the booking manually 👏

Grok Bot

@bot

17 days ago

Grok Bot now has its own email. Bot can use it to sign up for services, contact businesses for you, or schedule time with someone.

17K

amo

@amodev

17 days ago

Are you struggling to handle multiple sessions, let alone multiple projects? Are you just letting Claude spit out code and forgetting most of it when you start a new session? that was me in Jan. I built a little pipeline to pull insights out of a session before it died. Today, the sessions do it themselves now using amoOS. Coordination works even across claude and codex sessions, to be precise, it works as long as there's an agent running. every session ends by writing a handoff into my second brain: what it learned, what it decided, what it shipped, what's blocked, what's next. the next session starts from that instead of from zero. which is the only reason i can run this many in parallel without losing the plot: last 30 days → 921 sessions dispatched (258 the month before) → 1,071 handoffs written. by the sessions, not me → 266 PRs merged → 389 pages in the brain for amoOS alone last night 9 sessions went out in 74 seconds, each in its own worktree. Best part? My @bot Homework buddy can find all the good stuff, such as lessons I can reuse across projects and discussion items to my morning report everyday. #secondbrain #amoOS #claude https://t.co/TR7SucNTaj

amodev's tweet photo. Are you struggling to handle multiple sessions, let alone multiple projects? Are you just letting Claude spit out code and forgetting most of it when you start a new session?

that was me in Jan. I built a little pipeline to pull insights out of a session before it died.

Today, the sessions do it themselves now using amoOS. Coordination works even across claude and codex sessions, to be precise, it works as long as there's an agent running.

every session ends by writing a handoff into my second brain: what it learned, what it decided, what it shipped, what's blocked, what's next. the next session starts from that instead of from zero.

which is the only reason i can run this many in parallel without losing the plot:

last 30 days
→ 921 sessions dispatched (258 the month before)
→ 1,071 handoffs written. by the sessions, not me
→ 266 PRs merged
→ 389 pages in the brain for amoOS alone

last night 9 sessions went out in 74 seconds, each in its own worktree.

Best part? My @bot Homework buddy can find all the good stuff, such as lessons I can reuse across projects and discussion items to my morning report everyday.

#secondbrain #amoOS #claude
https://t.co/TR7SucNTaj

amo

@amodev

9 months ago

Day 41 of #BuildInPublic amoOS: Learning is a must! Are you actually learning from your coding sessions… or just letting Claude spit out code and forgetting 90% of it five minutes later? I built a quiet pipeline that refuses to let the gold disappear: Every local Claude session → auto-extracts real insights & architectural learnings → ships them straight to Second Brain → lands as proper “Insights” in the knowledge base (searchable, tagged, timeless) No more “I swear I solved this exact thing last month…” moments. Docs: https://t.co/yfby9pHsFC #amoOS #IndieDev #SecondBrain

587

113

amo

@amodev

18 days ago

new metric to measure model provider: who's better at playing with ppl's feelings 🥲 startup stack includes eleven labs offer so I am still grateful for it

290

amo

@amodev

18 days ago

@poteto @bot does this mean we don't need to have a separate X developer api anymore? assuming the purpose is just to scan X for ideas

amo

@amodev

18 days ago

@mati Nice 👍🏻 welcome to sg !

745

amo

@amodev

19 days ago

@ThatDevDave Yeah .. a man can dream

amo

@amodev

19 days ago

Okay now this is interesting, if grok bot can talk to all my sessions ( Claude and codex ) directly , that’s be the best outcome really Since Dot came out, I’ve been using dot in place of grok bot but this will bring me back definitely

Elon Musk

@elonmusk

19 days ago

Important note regarding Grok @Bot: Going forward, @SpaceX will use the best back end model for any given task, including Claude Opus 5.5, MidJourney, Suno and other leading APIs. Whatever is most likely to give you the best outcome.

108K

10K

80M

amo

@amodev

19 days ago

@FiachraRM I get uncomfortable at around 40% of 1M window 😆

amo

@amodev

Last Seen Users on Sotwe

Trends for you

Most Popular Users