←
GenAI.Works1,249 posts
GenAI.Works avatar

GenAI.Works

@GenAI_Now

Discover, learn & grow with AI Helping beginners to learn AI in the simplest way +13 Million AI Community Start your AI journey here 👇

◷ Joined May 2025▧ 853 Photos and videos
Steve Nouri avatar
⟳ GenAI.Works retweeted
Steve Nouri@SteveNouri·Nov 11

Unbelievable new feature from @Adobe MAX sneak. Wow

1:52

@Adobe CEO just announced crazy new features at Adobe MAX. All Adobe products now support MCP connections. Means Chatgpt and Claude can help creators directly within platforms.

Post attachment
Udi Ngethe avatar
⟳ GenAI.Works retweeted
Udi Ngethe@UNgethe·Nov 1

Built bothy.trustfall.xyz @GenAI_Now Open Agent Hack Bothy answers complex supply-chain exposure q's by connecting data that normally lives in separate systems One about gallium export restrictions, answered by federating an ops file, SEC filings + an EU registry @Zetaris

1:08

#coding got fast, but access to #enterprisedata remains slow! Fix that with Zetaris Data Harness, @spacexai and @nvidia at the @GenAI_Now Open Agent #Hackathon, October 22nd - 27th! 144 hours. 5,000 builders. $20K in prizes to be won! Register now hackathon.genai.works/event/…

0:34
Salah Alden avatar
⟳ GenAI.Works retweeted
Salah Alden@SalahAldenAlm·Nov 4

Roughly a week ago, I submitted my hackathon project. I participated in the track of the agent that explains things. The biggest thing I've enjoyed is the realization, after every feature implementation, of what AI can do nowadays, the feeling of empowerment and how easily you can do things with AI in today's world. The tool that made the biggest difference during my building process is Nightshift. It gave me access to a free Nvidia powerhouse of excellent models and certainly Claude Code. One of the biggest things I've learned is that I can do big stuff in a short amount of time, something I've struggled with throughout my life, but this hackathon showed me I can do great things easily if discipline is implemented. @GenAI_Now

Post attachment
Kenneth avatar
⟳ GenAI.Works retweeted
Kenneth@symplyKen·Nov 10

Impact 24.0 / 30 Technical 15.5 / 20 Innovation 6.5 / 15 Demo 11.0 / 15 Product & UX 6.5 / 10 Sponsor tech 7.0 / 10 We didn't win this one, thank you @GenAI_Now for the feedback, more hackathons should adapt this feedback methods. Now we know where to improve on

Post attachment

Your parent sees different doctors, takes multiple medications, and gets lab tests from different hospitals. But who's connecting the dots between those medical records? We built CareSync, an AI-powered health coordination agent for family caregivers.

4:00
Jennycruzy avatar
⟳ GenAI.Works retweeted
Jennycruzy@jennyoliver57·Nov 10

I placed 3rd in Track 1 at the #OpenAgentHackathon by @GenAI_Now . Thank you to the judges and the team behind it. What I built Fieldwork: You ask a question about a neighborhood in plain English, like "which parts of Montgomery have high asthma rates and a lot of housing code violations?" No single website has that answer. The health numbers are on the CDC site, the violations are on the city's site, and the neighborhood map is somewhere else. Fieldwork goes and finds those sources by itself, connects them through @Zetaris, checks that they really line up, and answers on a map. Every number links back to the real records it came from. If the data doesn't exist, it says so instead of guessing. Try it: askfieldwork.space Now that the leaderboard scores are out, here is what I learnt: I finished 1 point behind 1st place in my track. My Product & UX score was the best in the track. My build quality and video scored as high as the winners'. The whole gap was in one place: Impact. Judges asked who exactly this helps, and what that person does differently tomorrow because of it. I aimed too wide. Fieldwork was built for city staff, health analysts, reporters and residents, and a tool for everyone is hard to judge as vital to anyone. Finding the truth in scattered data is half the job. The other half is turning it into the next move for one specific person. What I will do next time: Keep everything that scored well, and add what was missing: - One person I am building for, with a real cost when the problem goes unsolved - An answer they can act on, not just read - Something they come back to every day. Thank you again to the judges and team for publishing these scores because It helps me know where to improve and what to keep doing. Lets build more!!

Post attachmentPost attachment

I asked an AI agent a question no single dataset can answer. It went and found the data itself. This is Fieldwork, my solo build for the #OpenAgentHackathon by @GenAI_Now . My track Track 1: Solving Fragmented Intelligence. The problem: Ask "which Montgomery neighborhoods have high asthma rates and a lot of housing code violations?" The asthma data is on the CDC site, the violations are on the city portal, the neighborhood map is from the Census. No one has that table. What Fieldwork does: You type the question in plain English. It searches public data portals live, connects the sources through @Zetaris without copying any data, checks they really match up, and answers on a map. Every number links back to the real rows it came from. If the data doesn't exist, it says so. In the demo I also point it at Louisville, a city it had never seen. It found the sources and answered in 92 seconds. What I enjoyed most: Seeing my work help the sponsor directly. While building, I hit data sources on Zetaris's own "known to fail" list, so I fixed them and sent pull requests. Both were merged by Zetaris's CTO: - PR #36: Singapore air quality, now working github.com/zetaris/gettin… - PR #39: CDC health data + Census maps, added as new sources github.com/zetaris/gettin… "Super helpful… always great to add another confirmed data source into the set of known to work." After the hackathon I kept going. Using the @cursor_ai agent, PR #43 (merged this week) took the known-to-fail list from 6 sources to 1 github.com/zetaris/gettin… I also had the Cursor agent check Fieldwork's answers. It used only Zetaris and never saw Fieldwork's answers. On 5 of my questions it got the same numbers on 4, and the same top 5 on the last, with a few counts off by 1 or 2. Tools that made the biggest difference: - Zetaris: one SQL query across live CDC data and my own database, with every answer saved back as a reusable view - Meterless engines: H-MEM so the agent remembers which sources worked, World Model to track each run, Scout Intent to block poisoned source text - @nvidia Nemotron: writes the SQL and the answers What I learned, and what I'd do differently: Testing beats demos. On 25 real questions my first full run passed 12. The final run passed 25 of 25, about 47 seconds per answer. The same AI model on its own answered 0 of 20; Fieldwork answered 18. Next time I'd start that full test on day one, not day three. Thank you @GenAI_Now , @Zetaris and Meterless for a great week📌🔥 Try it: askfieldwork.space Code: github.com/Jennycruzy/fie…

Post attachmentPost attachmentPost attachment
Shamex avatar
⟳ GenAI.Works retweeted
Shamex@Shamex_Ent·Nov 10

Grateful to have been part of the @GenAI_Now Open Agent Hackathon as an ambassador. It was a great experience contributing to the community, and I'm glad to have this recognition. Looking forward to more opportunities to learn, contribute, and grow. 💚

Post attachment
Frederick R Newbrough avatar
⟳ GenAI.Works retweeted
Frederick R Newbrough@FR_Newbrough·Oct 28

Built something at the Open Agent Hackathon? Show us Zetaris working live. Zetaris Demo Challenge: $10,000, 3 winners ($5K/$3K/$2K). Entries close 5 Nov, 23:45 UTC. Rules: zetaris.com/zetaris-demo-cha… Made with Grok Bot, Grok Imagine, Kokoro voice

0:24
Steve Nouri avatar
⟳ GenAI.Works retweeted
Steve Nouri@SteveNouri·Oct 22

I sat down with @JensenHuang , CEO of @nvidia, to discuss one of the biggest concerns surrounding AI: safety and security, and what NVIDIA is doing to address them. Jensen has been vocal about his opposition to pausing AI development. His argument is that AI safety is fundamentally an engineering problem, and we need to build the technology to solve it. But here's where things get interesting. At @NVIDIAGTC Berlin yesterday, NVIDIA introduced its new OpenShell Reference Architecture, designed to make autonomous AI agents safer to deploy. The idea is surprisingly straightforward: → Give AI agents only the permissions they actually need. → Isolate them from sensitive systems and data. → Continuously monitor their behaviour. → Enforce security boundaries independently of the agents themselves. → Use hardware-level controls to stop agents that violate those boundaries, potentially within milliseconds. NVIDIA is essentially building a security layer for a world where billions of AI agents could be working autonomously. And I think this represents an important shift in how we approach AI safety. For years, much of the conversation has focused on making AI models safer through training, alignment and guardrails. But as AI moves from answering questions to executing actions, model-level safety alone won't be enough. We also need to secure the environments in which AI operates. Of course, this doesn't solve every AI safety challenge. Questions around misuse, alignment and long-term risks remain. But it is a concrete example of turning safety research into engineering.

2:38
GenAI.Works avatar
GenAI.Works@GenAI_Now·Sep 23

Still thinking about joining the Open Agent Hackathon? There's still time. ⏳ 📅 Oct 15–20 · fully online 🛠 4 tracks + a bonus Tinkerer Track ⏳ Registration closes Oct 13 Secure your spot 👇 hackathon.genai.works/event/…

Post attachment
IzzyOAP avatar
⟳ GenAI.Works retweeted
IzzyOAP@isreal_izzyH·Sep 15

In 12 months, there will be two types of people: Those who watched the AI revolution unfold. And those who built during it. 🏆 Up to $20,000 in prizes 🌍 Global competition 🤖 Build AI agents that solve real problems The next breakout founder, engineer, or AI operator could be reading this tweet right now. Register: hackathon.genai.works/ Build something that makes people say, "How the hell did they make that?" Join @GenAI_Now Global Hackathon.

0:10
Steve Nouri avatar
⟳ GenAI.Works retweeted
Steve Nouri@SteveNouri·Sep 10

I’ve partnered with @nvidia to give AI builders a shot at a Golden Ticket to NVIDIA GTC Berlin. 🎫 If you’re building with open models, show us what you’re working on, you could be joining us in Berlin. Your Golden Ticket includes: → Free conference pass → VIP seating for Jensen Huang’s keynote → Exclusive NVIDIA merch → Access to special events How to enter: Share your project below. Only one day left (11 Sep) 🏆 Winner announced by September 14 👉 Contest details: nvda.ws/4hP8W9S Building something worth seeing? "Comment" your project below.👇 Or tag an AI builder who should be in Berlin.

Post attachment