Joel Timana

Today, for the first time, @dianamunozlar and I are introducing @buivoai 🔥. AI gave every role a faster way to work alone. Business prompts. Product prompts. Engineering prompts. Going in different directions. The problem was never the LLMs. It was the interface. So we built it. The oldest human expression now ships software. The waitlist is open: buivo.ai/?utm_source=tw…

Imagine those hands but coding 😳

@dianamunozlar @buivoai 🚀 We are launching on July 21st. Join the waitlist: buivo.ai/?utm_source=tw…

Today, for the first time, @dianamunozlar and I are introducing @buivoai 🔥. AI gave every role a faster way to work alone. Business prompts. Product prompts. Engineering prompts. Going in different directions. The problem was never the LLMs. It was the interface. So we built it. The oldest human expression now ships software. The waitlist is open: buivo.ai/?utm_source=tw…

The best way to stress test your product is to have it used at a YC 24h Hackathon 👀

Paper and resources pymut.ai/labs/reactlines

Introducing ReactLines. Atomic Procedural Memory Units for cognitive agents. The problem Agent behavior lives in giant prompts. Instructions collide, drift, and conflict. They can't be scoped or reused. A formal 11-field schema for behavioral policies who does what, when, why, and under what constraints. Six scopes, from narrow to global: TURN → SESSION → FLOW → AGENT → ORG → GLOBAL. Broader scopes subsume narrower ones. A 5-stage retrieval protocol injects only the relevant rules, recovering 95% of them at top-3. Built for scale: add more rules without growing your prompt. At 100 rules, 97% fewer tokens than a monolithic prompt Deployed in real-world production environments Research designed and executed for large-scale orchestrations. PS: Useful resources and links in the first comment

Introducing ReactLines. Atomic Procedural Memory Units for cognitive agents. The problem Agent behavior lives in giant prompts. Instructions collide, drift, and conflict. They can't be scoped or reused. A formal 11-field schema for behavioral policies who does what, when, why, and under what constraints. Six scopes, from narrow to global: TURN → SESSION → FLOW → AGENT → ORG → GLOBAL. Broader scopes subsume narrower ones. A 5-stage retrieval protocol injects only the relevant rules, recovering 95% of them at top-3. Built for scale: add more rules without growing your prompt. At 100 rules, 97% fewer tokens than a monolithic prompt Deployed in real-world production environments Paper and resources pymut.ai/labs/reactlines

AI chat is dead for building software...

Introducing HyMoEx. Hybrid Modular Coordinated Experts an architectural paradigm for scalable multi-agent systems and expert coordination. The problem: Multi-agent systems work with 2 or 3 agents. At 5, 10, 20, 50 or more; flat architectures break under quadratic communication complexity. A formal 7-role agent taxonomy with typed message protocols. Three deployment modalities M1, M2, M3 with a subsumption theorem proving M1 ⊂ M2 ⊂ M3. Migration preserves 100% of existing agent definitions. Mixture-of-Experts gating adapted from neural networks to discrete agents. 96.7% expert selection accuracy. 93% token reduction from 5 agents onward. Framework-agnostic by design. Bidirectional adapters included. Deployed in real-world production environments across sectors such as developer-tools, fintech, hr, sales, deep-tech Research designed and executed for large-scale orchestrations. Pymut Labs @PymutAI Paper, Resources and links pymut.ai/labs/hymoex

Paper and resources pymut.ai/labs/hymoex

Introducing HyMoEx. Hybrid Modular Coordinated Experts an architectural paradigm for scalable multi-agent systems and expert coordination. The problem: Multi-agent systems work with 2 or 3 agents. At 5, 10, 20, 50 or more; flat architectures break under quadratic communication complexity. A formal 7-role agent taxonomy with typed message protocols. Three deployment modalities M1, M2, M3 with a subsumption theorem proving M1 ⊂ M2 ⊂ M3. Migration preserves 100% of existing agent definitions. Mixture-of-Experts gating adapted from neural networks to discrete agents. 96.7% expert selection accuracy. 93% token reduction from 5 agents onward. Framework-agnostic by design. Bidirectional adapters included. Deployed in real-world production environments across sectors such as developer-tools, fintech, hr, sales, deep-tech Research designed and executed for large-scale orchestrations. Pymut Labs @PymutAI PS: Useful resources and links in the first comment

The rule @jowyang sets in every room: - Unconditionally help others. Llama Lounge 25 @Stanford, one of the best spaces in Silicon Valley to find AI founders, investors, corporates & builders all in one room. Every series is better than the last. 🦙🐚 Were you there? Let's connect! #LlamaLounge

I used to think you could build from anywhere. Then I moved to San Francisco. Yesterday @snowmaker nailed it at @fdotinc 💚: the best thing about SF is the people. The smartest, most ambitious, most open minded people you’ll ever meet. SV is the best place in the world to build!

Introducing Pymut What if the next breakthrough in AI doesn't come from a single lab but from a collective of outliers building together? That's @PymutAI The ecosystem where AI Outliers co-create frontier AI that competes globally. We don't supervise. We co-execute. We don't separate research from shipping. We fuse them. Three verticals. One loop: - Run, discover the outliers - Origin, form the collective - Habitat, R&D lab + co-living We don't wait for the future. We research it We code it We ship it Until it exists. Searching for other outliers pymut.ai

@cory letsgoooo

hosting the "dropout graduation" in SF on may 30th i left school after my freshman year to build. never had a proper graduation until dropout graduation. commencement speaker to be announced soon. @ reply or DM if you want to attend. allies/graduates allowed to attend as well

We got in to @fdotinc SLM trained rn in stealth just shipping but it's time if you are in SF let's connect

We got into @fdotinc 💚 We just moved to San Francisco. Two founders. One problem nobody solved. Until now. 🌁 A new chapter starts. Thank you @hthieblot @adriannalakatos If you're part of #canopy, let's connect!

@lilyyang169 Community

Starting a Whatsapp group for community leads of VCs and accelerators. It will be a chat for us to candidly discuss programming, events, community operations, and contribute to the growth of the ecosystem as a whole. Comment "community" for the link.

Have you noticed that soon we'll stop building software where the end user is a human? Wait, actually, I think it already started