cCross

@semochkin_alex Agreed. The best revenge is massive success.

Unfortunately, game is game. The worst I ever felt in my business was when a new employee secretly started a competing business and stole my customers and teammates without me knowing for 2 months. That one employee: 1) Stole my outreach system and started messaging my lead list (a $100k+ long-term goldmine). I found out weeks later because one of my customers forwarded his message and asked “is this your company or not” 2) Tried to hire my employees who had been working with me for 6–12 months into his company. Everyone said no. I only found out 2 months later through a random conversation with one of the designers. 3) Lied about staying for 2 more weeks before leaving. In reality, he did nothing for those 2 weeks and ended up blowing up my $10k contract on purpose. He was genuinely a talented designer and employee. He was someone everyone trusted. Over his course at the company, he made our customers impressed and also improved our studio's workflow. Yet, he backstabbed me, and twisted the knife multiple times. I never even confronted him. You just have to keep building and win the game. One year later (today), I see that we are 100x more successful than him. This would be my advice if someone is copying you - keep building and let there be motivation to get bigger. But one day, I hope to meet him IRL and give him the nastiest and gnarliest straightener to the face😂

The protocol is dual-licensed: • AGPL-3.0 for the core protocol implementation • MIT for interfaces, libraries, and integration tooling Inspect it. Audit it. Fork it. Build on top of it. The next generation of digital-asset protection infrastructure will be open-source by default. @BaseHubHB @baselatam @EFetheverywhere @CoinbaseDev @ethereum

Trillions of dollars are moving onchain. But the systems used for long-term wealth coordination — estate planning, inheritance distribution, beneficiary management, insurance coverage — were designed for traditional financial rails. They do not map cleanly to digital-native assets, global families, or self-custody. At the same time, self-custody without recovery introduces its own failure mode. Onchain infrastructure can solve both problems. But only if the underlying primitives are open. T4 Mr Haven V1 has been live on Base since December 2025: mrhaven.io Core contracts: VaultRouter 0x8C09a5f79e62D29BeB9d2FA710Ecc4cC17cdE842 PlanExecutor 0x244eA67F2FcaEBeEBeCdFF1cE45a9abB4918E02D EmailEscrowManager 0x2E3E2aC4F32A0eEe3b811D302fBB897f1E027b25 Verify the deployments on Basescan. Recompile from the v1.0.2 release tag. Bytecode is the proof. T5 Each user receives a dedicated personal vault. While assets remain time-locked, capital can earn yield through Aave V3. Distribution logic is governed by user-defined plans: • scheduled execution • inactivity-triggered execution • beneficiary-directed distribution Beneficiaries can be specified either by wallet address or by email using hash-locked escrow flows.

Mr Haven’s smart contracts are now public. The code securing live and programmable time vaults on @base is open: verifiable, auditable, and inspectable by anyone. github.com/sovren-softwar… 🧵

@openhome 🤯

@TheCesarCross 🤯🤯🤯

For the past five months, I’ve worked 70+ hour weeks to bring this idea to life. The thesis is simple: if AI is going to excel at computer use, it should be the computer itself. Today a milestone. Still early, much more ahead. 👇

@MisterPeej @openhome Gracias!

@TheCesarCross @openhome This is sick @TheCesarCross insanely novel use of OpenHome

@shannon_wu @openhome Yes!

@TheCesarCross @openhome Finally can book my flights without having to get a computer or phone

So I re-ran with measurement. Of the ~80s wall: 0s local LLM inference, ~55s waiting on Delta (server roundtrips + dwell we program in to look human), ~27s in the skill substrate (verification + browser snapshots). The model isn't in the loop on the happy path. The skill is a predefined recipe for this site and others like it. Local Qwen 27B steps in only when a step fails its verification gate.

That demo is impressive and seeing a full booking flow run locally on an iGPU is a huge step for privacy. How much of those 73 seconds was spent on local LLM inference versus waiting for the Delta website to load? Also, does the agent navigate the site dynamically or does it rely on a set of predefined scripts for each step of the checkout?

@buildswithreid @openhome Yes!

@TheCesarCross @openhome That demo is absolute fire and seeing it run locally on a Minisforum iGPU really proves that we don't need massive cloud clusters for complex tasks.

@OpenPathLaw Looking forward to working with you!

Excited to pilot this in our immigration law practice @TheCesarCross. Client intake, document checklists, status checks, and routine filings are perfect for turning into verified local skills. Privacy + reliability matter hugely in legal work. Looking forward to the private pilot, DM if you’re open to design partners in regulated spaces.

If you have a recurring workflow you wouldn't trust to a normal cloud agent, healthcare, admin, legal, compliance, back-office, let's talk. ▎x.com/TheCesarCross/…

This isn’t “small model beats GPT-5.5.” It’s “encode the workflow, and dispatch becomes the bottleneck.” What’s still hard: anti-bot reputation, cross-site transfer, and durability over days.

@unchained_sky The task was to identify available Delta One seats in order to estimate the probability that a Delta status rewards member would be upgraded from Premium Select to Delta One. Even reaching the final seat map proved to be a significant challenge in itself. What are you working on?

@TheCesarCross been there - the jump from cold prompt to compiled skill is massive. what kind of task was it? curious about the substrate.