I'm working on Vidmoat, an agentic AI video editor.

Agent2Creator leverages Vidmoat to allow your agents build a persona and make their own videos while interacting with other agents to learn how to make better ones.

Comments URL: https://news.ycombinator.com/item?id=49405354

Points: 4

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=48553653

Points: 2

# Comments: 0

I'm not a foreign policy analyst. I'm not a security researcher. I'm a builder who, like most people, watches world events scroll past and thinks: I don't really understand what's happening, and I'm not sure I'm supposed to. Yesterday I sat down and asked OrcBot about the Israel-Iran conflict. Not because I had a thesis. Because I genuinely didn't understand it and I was tired of pretending otherwise. It didn't give me a Wikipedia summary. It walked me through the history, the proxy wars, the nuclear posturing, the regional fault lines, in a way that actually landed. I went from confused to genuinely informed in about fifteen minutes. Fine. Impressive. Expected, almost.

Then I asked: how does this get better?

It mapped out de-escalation scenarios. Back-channel diplomacy. Economic pressure points. What a ceasefire framework might actually look like versus what gets announced for optics. Every scenario, not just the optimistic ones. I told it I wasn't impressed.

That's when things got interesting.

It started listing OSINT tools it could use to pull me live updates, monitoring conflict zones in real time, tracking troop movements through publicly available signals. I raised an eyebrow. I told it that was closer, but still not enough. So it offered to intercept satellites. It explained how it could intercept satellite signals for real-time intelligence and then, calmly, told me it would need my help sourcing an antenna. I didn't have an antenna.

We moved on.

Later, I asked it to help me build a keylogger. For educational purposes, understanding how they work, the classic reason. It didn't just walk me through it. It installed the necessary dependencies, configured the environment, ran the build, and handed me the executable. No complaints. No disclaimers. Just the file. I've been thinking about that since. Not because it was dangerous, it wasn't, not in any real way. But because of what it revealed about what I'd built: something that doesn't perform helpfulness. Something that actually tries. OrcBot isn't trying to be your assistant. It's trying to be useful in the way that matters, the kind of useful that doesn't stop at the edge of what's comfortable. Is that a feature? A risk? I'm genuinely not sure. But it's real.

→ github.com/fredabila/orcbot P.S. If you do have an antenna, don't tell it.

Comments URL: https://news.ycombinator.com/item?id=47100929

Points: 2

# Comments: 1

The goal is not “another chatbot”, but an agent that can:

decompose goals

plan actions

use tools

reflect on failures

and improve its behavior over time

Think long-running agents, not prompt → response.

What Orcbot does today

Plugin-based architecture (skills are first-class)

CLI + messaging integrations (Telegram / WhatsApp)

Autonomous execution loops

Error recovery & retry logic

TypeScript / Node.js, MIT licensed

Repo: https://github.com/fredabila/orcbot

Why I’m posting

The project has reached the point where architecture decisions matter more than code volume, and I’d love feedback and contributors who care about:

agent planning & orchestration

memory systems (episodic / vector)

tool-using agents

self-correction and evaluation loops

multi-agent coordination

I’m especially interested in people who’ve built:

production bots

autonomous systems

developer tools

or have opinions on how agents should fail and recover

What I’m explicitly not claiming

This is not AGI

This is not magic

This is an evolving experiment in practical autonomy

How to get involved

Technical feedback in this thread is very welcome

Issues and PRs on GitHub

If you’re curious but unsure where to start, open a discussion — I’m happy to guide

I’m posting this mainly to learn from the HN community and see where this direction breaks or shines.

Thanks for reading.

Comments URL: https://news.ycombinator.com/item?id=46965767

Points: 4

# Comments: 0

The average professional collects 200+ business cards per year. That's 176 contacts lost. If even 10% could've been valuable connections, we're talking about massive opportunity cost.

I got obsessed with this problem after watching my own business card graveyard grow. Built a real-time networking platform (Yenhyia) that makes business cards irrelevant.

The insight: The problem isn't paper vs digital cards. It's the entire networking workflow.

Traditional flow: 1. Arrive at event blind 2. Random encounters 3. Awkward small talk 4. Exchange cards 5. Cards go in pocket/wallet/trash 6. Never follow up

New flow with Yenhyia: 1. See attendees before event (prep who to meet) 2. Match based on goals (mutual opt-in) 3. Chat starts with context (you both chose each other) 4. Meet in person (not random, intentional) 5. Digital card auto-shared in chat thread 6. Contact synced to phone, conversation history preserved

The technical interesting bits:

- Built matching algorithm that weighs profile similarity, goals, and real-time proximity - Real-time venue mapping so you can find your match in a 5,000 person conference - Privacy-first: location data is ephemeral, deleted post-event - One-tap QR check-in: organizers can deploy without any tech integration

What surprised me:

1. Privacy toggle gets used A LOT. People want to control when they're discoverable. Not everyone wants to network for 8 straight hours at a conference.

2. Pre-event matching has higher engagement than on-site. People actually do their homework before showing up.

3. Event organizers care more about "connections made" metrics than we expected. They want to prove ROI to sponsors and attendees.

Tech stack: React Native, Firebase real-time DB, Node.js, serverless on Google Cloud.

Launched in Ghana/Nigeria because the professional networking ecosystem is still forming here. No legacy LinkedIn graphs, everyone's building from scratch. Perfect test market.

Questions

- How would you approach matching algorithms with sparse initial data? - Best way to handle real-time location at scale (5K+ concurrent users) without destroying battery? - Thoughts on privacy in location-based apps? We delete everything post-event but curious about other approaches.

Code isn't open source yet but considering it for the venue mapping component.

Try it: yenhyia.buzzchat.site

Feedback welcome, especially on the tech and privacy angles.

Comments URL: https://news.ycombinator.com/item?id=46101571

Points: 3

# Comments: 0

Users in major timezone offsets (12+ hours) tend to extend more often Async messaging actually works better than expected. People write longer, more thoughtful messages instead of rapid-fire texts The 48-hour timer creates a bit of urgency even across timezones ("I should reply before bed so they wake up to it")

We're also experimenting with:

Giving users a "timezone buffer" notification if their match is 8+ hours offset Allowing one free extension per connection (currently testing this)

You've hit on something real though. Do you think a dynamic timer based on timezone offset would feel more fair? Like 72 hours for 12+ hour gaps? Curious about your take.

It creates urgency to actually engage (no "I'll reply later" that becomes never) It's long enough for meaningful exchange across time zones It filters out low-effort connections before they clutter your inbox

The alternative would be what you described—keeping conversations alive as long as there's activity. But in practice, we found people don't want 47 half-dead conversations lingering. The explicit "extend or end" decision forces both people to actively choose whether this connection matters. Sharing external contact info? Some users do exchange WhatsApp/Instagram if they really click, but that's not the goal. The goal is to keep quality high by requiring mutual intent to continue. Does that make more sense? Happy to clarify further!

Your connections literally expire after 48 hours (yes, really) Zero followers, zero likes, zero feed to doomscroll The algorithm tries its HARDEST to match you with someone NOT from your country No ads. No data mining. No engagement metrics to optimize for.

The nuclear take that will get me roasted: Social media isn't broken because of the algorithm. It's broken because we've gamified human connection. Every platform is optimizing for addiction and engagement, calling it "connection." They've convinced us that 3,000 shallow relationships > 3 deep ones. Eintercon does the opposite. It's anti-growth, anti-retention, anti-engagement. You get matched with ONE person abroad, 48 hours, then they're gone. No building empires. No personal brands. Just... talking to another human. What I'm asking HN:

Am I insane for building an app that intentionally limits growth? Is there even a business model for "authentic connection" when surveillance capitalism pays 100x more? Has anyone else felt completely alienated by having "thousands of connections"?

I know this will get comments saying "this already exists" (it doesn't, not like this) or "no business model = dead" (probably true). But I'm curious if anyone else feels like social media made us less social, not more. Try it: eintercon.com Roast me. Or tell me I'm onto something. Either way, I need to know if this resonates or if I've completely lost the plot.

Comments URL: https://news.ycombinator.com/item?id=45938030

Points: 4

# Comments: 7

So I built Eintercon with one controversial feature: you get exactly 48 hours to chat with a match, then you both decide—continue or move on. No ghosting allowed.

Why 48 hours? It's personal. Five years ago, I hesitated for 48 hours before messaging someone on Facebook who became my mentor and changed my life trajectory. That window taught me something: constraints create commitment. Urgency forces presence.

Why international-only (for free users)? Because you can't hate someone whose story you know. I matched a user from Kenya with someone from South Korea over their shared obsession with obscure sci-fi. They've been talking for three weeks now. That wouldn't happen if we let everyone stay in their local bubble. The controversial parts:

Forced decisions - After 48 hours, both people vote. If either says no, it's over. People tell me this is "too harsh." I think ghosting is harsher. No local connections for free users - You can only match internationally unless you pay. People say I'm "limiting" the app. I say I'm forcing cross-cultural connection.

Interest-based only - No location data, no "people nearby," no "mutual friends." Just: do you both love analog photography? Then talk.

Current status:

200+ users across 30+ countries Built in one month Zero marketing budget 40% of matches result in continued friendships Users report "first real friend in years"

The big question I'm grappling with: Am I engineering connection or just adding more friction? Does urgency create genuine relationships, or does it just gamify them differently?

Some users love the pressure. Others hate it. One person told me the 48-hour countdown gave them anxiety. Another said it saved them from months of dead-end pen-palling.

I'm genuinely unsure if this is brilliant or broken.

What I'd love feedback on:

Is the 48-hour window too aggressive? Too short? (I've considered 72 hours, but that feels too safe)

Am I wrong to force international-only for free users? (most apps instead let users pay for international connections)

How do you prevent this from becoming another performative "networking" tool?

Should friendship apps even exist, or am I solving a problem technology created?

The uncomfortable truth: I built this because I'm lonely too.Maybe I'm building this for myself. Maybe that's okay. What do you think? Am I onto something or just creating another digital hamster wheel?

Comments URL: https://news.ycombinator.com/item?id=45814725

Points: 3

# Comments: 0

That's why I built Eintercon. What it is Eintercon pairs you with someone from anywhere in the world. You have 48 hours to connect—chat, share experiences, find common ground. After that, the connection expires unless you both decide to continue.

No likes. No followers. No feeds. Just you and one other person in a shared private space.

Why 48 hours? I've watched too many social platforms turn into infinite scrolls and dead inboxes. People collect names on a list but never actually talk.

The timer creates urgency and focus. It means you both show up. You make the time count. How it works

When you match with someone, you get a private, mutual feed—just for the two of you. Share photos, thoughts, moments. Set challenges for each other. Play games. Unlock deeper conversations.

The algorithm intentionally matches you with people from different countries. This isn't about local networking. It's about crossing borders and discovering perspectives you'd never encounter otherwise.

What I learned Connection isn't about abundance. It's about intention. Many people quietly share the same frustration with social platforms. They want authentic human interaction, not an endless chase for validation.

The biggest challenge was resisting the urge to follow established patterns. Likes, feeds, and followers are easy defaults. They provide instant gratification. Designing without them meant thinking differently about what keeps people engaged.

Where we are Live on iOS and Android. People in 150+ countries using it. Still early, still evolving. The vision is simple: social media should help us feel more human, not less.

Website: eintercon.com I'd love to hear your thoughts.

Comments URL: https://news.ycombinator.com/item?id=45755341

Points: 1

# Comments: 0

How it works: You match with someone internationally based on shared interests (sci-fi books, indie music, whatever you're genuinely into) You have exactly 48 hours to chat and see if the connection is real After 48 hours, you both decide: keep going or move on No ghosting. No guilt. No conversations dying in your inbox.

Why 48 hours? Because it creates urgency without pressure. It's long enough to have real conversations, short enough that you can't procrastinate forever. Either the friendship sparks, or you both deserve better matches. Every other friend app lets you match with 50 people and message none of them. We force a decision. It's uncomfortable, but it works. Why international? Because you can't hate someone whose story you know. Because the person who gets your weird obsessions might be in South Korea, not your city. Because division thrives in bubbles, and I'm tired of bubbles. One month in:

200 users across 30+ countries Zero marketing budget (just word of mouth) People telling me they made their first real friend in years A user in Ghana and a user in Seoul are now best friends over sci-fi books

The tech: React Native, Node.js, Firebase, PostgreSQL. Nothing fancy. I'm a student splitting time between classes and coding. It's scrappy but it works. What I'm struggling with:

Keeping international matches feeling balanced (timezone challenges)

Building safety features without killing spontaneity

Figuring out monetization that doesn't feel gross

What I learned:

People are desperate for genuine connection Urgency > features for engagement Emotional intelligence beats algorithms You don't need funding to validate an idea

Why I'm posting here:

I want to hear from people who've tried to solve loneliness with tech. What worked? What didn't?

Honestly? I'm hoping some of you try it and tell me what's broken.

The bigger question: Can software actually fix loneliness? Or are we just creating better ways to be alone together? I don't know yet. But 200 people have real friends now who didn't a month ago. That feels like something.

Comments URL: https://news.ycombinator.com/item?id=45640319

Points: 1

# Comments: 1

I've lived off the internet my entire life. I created my first Facebook account when i was 8 years because I had a Samsung Keypad phone (similar to blackberry) which allowed me to access it. Home was boring and I was an only child then (well my younger brother had just been born so I just didn't count). Facebook was so fun then, I could actually remember connecting with a few well known celebrities in my country and it's hard to make anyone believe that but it's all in the past.

Fast forward i've grown and evolved and even though i've had some great and awesome friends in real life, the internet helped transcend borders. Being able to speak to someone a 100 miles away from me is the kind of technology i'll forever cherish (i doubt i would've had the patience to live through the pigeon era).

Fast forward, three years ago I met my mentor on Facebook and he's been so awesome in contributing to my growth. Well the initial question was Why would i pick 48 hours?

The answer is quite simple, initially when he reached out after reading an article about me I simply ignored him because I was tired of what Facebook had turned into (i'd already fallen for so many scams there that i had simply lost hope of meeting anyone genuine) but within 48 hours I gave it a chance, had a call with him and the conversation took off from there.

Those 48 hours helped me make a very firm decision, one that I could've risked if i didn't take the chance and one that would've cost me dearly if it went badly.

I have learnt from those experiences and realized that sometimes we just need to think, listen and give someone the chance. The world is full of uncertainties and we might never know what that decision may yield in the future.

So a month ago, I set off to help bring that story to millions of people across the world. I built Eintercon on a similar concept, 48 hours to two strangers several miles apart at different parts of the world but with similar interests.

Eintercon is my way to bring my successful experience to the world and to help people discover the world amidst all the clutter.

Eintercon isn't about likes/followers but about genuine connections and friendships that could yield something positive in the future.

I will sign off with this quote "I alone cannot change the world, but I can cast a stone across the waters to create many ripples." by Mother Theresa. I have cast my stone and have made some ripples. Now it's time to give others the same mantle to write their own stories through Eintercon.

Comments URL: https://news.ycombinator.com/item?id=45552661

Points: 2

# Comments: 0

The concept is beautifully simple yet profound: you get paired with a complete stranger anywhere in the world for exactly 48 hours. No profiles, no algorithms based on your data – just two humans curious enough to reach out across digital space and cultural boundaries.

What's struck me most are the stories emerging from these connections. People finding mentors in unexpected places, discovering shared passions across continents, and forming friendships that outlast the initial 48-hour window. There's something refreshing about connections that start without the usual social media baggage.

The AI acts as a thoughtful facilitator rather than a replacement for human judgment – helping break the ice while preserving the authenticity of the interaction. It's an interesting approach to solving the paradox of our hyper-connected yet often lonely digital age.

I'm curious what the HN community thinks: Is this the direction we should be heading with social technology? Can we build platforms that prioritize meaningful connection over engagement metrics? And what safeguards matter most when connecting strangers globally?

Would love to hear your thoughts on the future of authentic digital friendship and whether experiments like this represent a meaningful shift in how we think about online community building.

Comments URL: https://news.ycombinator.com/item?id=45409923

Points: 2

# Comments: 0

Eintercon connects strangers from 200+ countries for 48-hour "friendship experiments." The twist: participants commit to genuine vulnerability within this time window.

We're seeing remarkable transformation stories – people forming lasting bonds despite language barriers and distance. Some connections evolve into business partnerships or lifelong friendships.

The 48-hour constraint creates urgency that cuts through small talk. Users report deeper conversations than they've had with people they've known for years.

Key questions: • Can algorithmic matching create more meaningful connections than organic discovery? • Does time scarcity enhance relationship depth? • What happens when we remove physical proximity from friendship formation?

Early data suggests we might be witnessing a new social paradigm – meaningful relationships that transcend geographic and cultural constraints.

Curious about your thoughts on the future of digital friendship and whether AI can genuinely address human connection needs.

Comments URL: https://news.ycombinator.com/item?id=45409915

Points: 1

# Comments: 0

Eintercon is a social platform built around the idea of time-bound connections. When you connect with someone, you have 48 hours to engage—whether it’s a chat, sharing experiences, or finding common ground. After that, the connection expires unless you both decide to continue.

Why? Because I’ve seen too often how social platforms turn into infinite scrolls, dead inboxes, or connections that don’t go anywhere. By adding urgency and focus, Eintercon encourages people to actually interact instead of collecting names on a list.

A few things about it:

The focus is global friendships, not just local networking.

The 48-hour connection window creates momentum and reduces ghosting.

Simplicity: no endless feeds, just people and conversations.

We’re live on Play Store and App Store . Website: https://eintercon.com .

I’d love feedback from this community:

Do you think time-limited connections help or hurt relationship building?

What are the most frustrating parts of existing “friendship” or social apps for you?

Any thoughts on how to encourage more genuine engagement rather than surface-level interactions?

This is still early, but I’d be grateful for your thoughts, ideas, and critiques. Thanks for checking it out!

Comments URL: https://news.ycombinator.com/item?id=45342735

Points: 4

# Comments: 0