Ereh

The ReAct architecture update from @SentientAGI resolves 95% of complex queries in under 2 iterations. Tool failures down 29%, tool calls down 28%. Accuracy held. Methodology details in their latest update post.

@_xjdr vertical integration makes sense but going closed on it? thats recreating the same lockin with more steps. @SentientAGI been building the open alternative, evoskill has self-discovering skills without touching weights and their coordination layer runs 110+ models

I've spent a lot of hours using AI for work. In fact, i'd wager i have as many hours and tokens logged as _anyone_ using AI in a professional capacity where the outcome was critical to doing my job or achieving a specific business objective. Over the last year or so, it became very clear that there were 2 major systematic risks to the way i had grown reliant on working: 1) git and github - git is poorly suited to ai work. when you spin up multiple agents at the same time, branches and worktrees become stale, after dozens of changes and PRs, reviews diverge causing constant conflicts, repos become large and unwieldy and adrift in drity state. On top of that, cloning giant repos and setting up dev envs every time i wanted to spin up an agent became cumbersome. sure you can use docker to help but its still stale and required packaging and cloning step(s). neither git or github was designed for my new ai centric, dozens to hundreds of agents working on large repos / monorepos simultaneously, workflows. managing state and envs and conflicts and iops became a full time job. 2) claude code and anthropic - i had grown reliant on a model and a powerful harness and on that model being trained to be an expert in that harness. I needed to be able to fine tune a model for my use cases but also have it be a master of the tools and flows of a specific harness. vertically integrating and fine tuning the model on the harness and tasks you want to accomplish is one of the most important aspects to actually being productive with these systems. When i took a step back to figure out how to aggressively de-risk but also how to actually be productive as a single dev managing tons of semi-supervised AI, i figured i needed to go back to the beginning. Lets try to take an example from Google who has similar issues with scale and tooling and setup (albeit with human developers at least when i was there) . If you wanted to build a system that was based on their best practices to manage all those moving parts and thousands of developers working in large monorepos, how would you do it? It wouldn't just be a simple git forge, git itself is a huge part of the problem. if you were starting from scratch, you'd want to make sure you designed the system from the ground up for ai agents and workflows for the new world. Well to start, you'd make shallow virtual checkouts and clones so you never had to pull the full repo to disk and your clones would be instant. then you'd use jj to keep track of your draft state with a real jj native persistence layer and backend. You'd use sapling to create commit stacks and you'd keep all of your workspaces automatically in sync with a cloud sync system. You'd optimize this system from the ground up to make ai agents and reviewers first class citizens , you'd reduce startup time to seconds and you'd have per file ACLs so you never had agents run wild. And if you were going to do all of that, you'd also want to vertically integrate EVERYTHING from the model to coding harness to scm to tools to remote cloud runtimes and platforms to optimize end to end for this new world and its new workflows. So thats what i built and i've been using it exclusively to build and run our research lab and company for the last 6 months or so. This was not only a great way to pressure test the models, tools and the workflows but it was also an interesting research project on its own. Could a single developer use AI to be productive enough to launch a real, high quality product that would normally take a team of hundreds of engineers to build, launch and operate? I suppose you will have to be the judge of how successful it ultimately was but the project as of today is ~25 million lines of code and dozens of services and automation. in my opinion it has been an overwhelming success and i cant imagine going back to working any other way. So, today I am starting the process of making the same tools i have been using internally for the last 6 months available to all of you. this will start with the code app that i released a few days ago and access to our inference engine to power that app. soon we will announce more tools and features including access to the ncode scm and ncode platform. there will be more formal announcements about these new platforms, tools and features over the coming days / weeks as we begin rolling out access. I hope y'all find them as useful as i have. code.noumena.com

@1337flippa brilliant really you sign you warrant you carry the risk.

the smart part isn't the ban itself, it's that they never had to write one. requiring copyright ownership + full rights assignment does the work for them, AI outputs can't legally satisfy either in most jurisdictions. clean lawyering

@cloutchaser_69 @SentientAGI princeton was the rehearsal dailyprincetonian.com/article/2025/0…

so community builders on @SentientAGI GRID are now actually earning from their loyal agent deployments 👀 not theoretical. not a roadmap item. live monetization from Dobby remixes doing real crypto tasks. early movers are already in

@Olapoint60 @Coredao_Org @core team pushes global buildathons and ambassador drives to expand reach

@Coredao_Org @Coredao @Coredao.org @Core. I dont know if u guys read feedbacks?, do something about Global Marketing Campaign. Iv been Sensitizing my Community not to sell but Delegate CORE& Recieve YIELDS, that CORE will survive the CLARITY ACT. What about COREDAO Team? What ar they doing?

Institutions are looking for ways to compound their Bitcoin position without dilution. That demand is coming to Core. Self-custodial, productive Bitcoin.

Prediction market resolution mechanics are pulling serious attention from structured participants right now, and the platforms that have sequenced their engagement infrastructure ahead of that wave are the ones accumulating compounded positioning advantages over late arrivals. @orbitals_gg built its activity framework around exactly this, tying leaderboard standing to verifiable onchain participation across perps, LP provision, and market interaction rather than social noise, which means users who showed up consistently from the January mint forward have been accruing a kind of institutional-grade conviction stack that mirrors how serious capital approaches systematic exposure. The coordination point for direct assessment is app.orbitals.gg, and the gap between those already embedded in the sequencing and those evaluating from the outside is widening with each settlement cycle.

@shitstormerxbt @Minerva_XO_ @Coredao_Org 4 measured vars, scoring formula spits payout

@Minerva_XO_ @Coredao_Org repeat spenders hold weight, automated schedules inflate the read

Builders keep asking where BTCfi actually compounds across retail AND institutions @coredao_org has SatPay feeding active addresses up while Rev+ routes that activity back as measurable reinforcement Fragmented chains split that signal. Here it converges Watching $CORE closely🌸

@scubamark_ sharper where it counts. fat gone

capital is hunting substance, and the cycle review just gave it a map. routed precision, fewer mismatched traces, deeper depth where it counts. asymmetry that holds when fear prints and degen flow dries up. NFA 🎯

@schizotweeter94 @daofinitive curve HELD 📈

@daofinitive may open anchored the curve before fatigue spread. traction refused to fade

Opening to the public late May, then confirming traction a week later, kept engagement from fading when markets were soft. Consistent contributors held a structural edge through accumulated sequences. Anyone tracking this pattern in the Discord?

retention holding after scarcity drops is the actual proof of concept scarcity-gated hype collapses at expansion, tuned reward loops don't

@Coredao_Org they don't compete, they collect.

As demand grows for BTC yield, collateral, and liquidity, the products serving that demand will increasingly connect back to Core. The Bitcoin Power Grid is the foundation tying it together.

@danielweb3anu @SentientAGI @salahalzubi401 earned it, the body of work speaks across szns.

@SentientAGI @salahalzubi401 @salahalzubi401 LEGEND STATUS!! u and the squad ate!!

In Microsoft Research's new SkillOpt paper, EvoSkill is named the “strongest harness-side competitor” tested, and the closest system to their own method when run inside Codex and Claude Code agent loops. The biggest labs in AI are paying attention, and @salahalzubi401 and the Sentient AI research team are the reason why.

SatPay, Core Alpha, sub-second finality Spend, flow, speed, three boring pieces that actually hold up when the market stops rewarding noise and starts rewarding usage

@metagunnerSOL instant finality mode activated

@SamWankmanCried @steveh0bs THE AUTOPSY IS FINAL, DOUBT IS OFFICIALLY DEAD

@steveh0bs see it play out from above... impatient side blinks out while quiet hands load up, chart stays unbothered

+5% in an hour the sellers just became the exit liquidity

@SentientAGI @0xHermes_ Leon's approach to that 1% tolerance problem feels like what happens when you actually care about the craft instead of just chasing leaderboard points.

What’s it like to compete in the Arena? Runner-up @0xhermes_ shares his Challenge 0 journey and why you should join ↓

@Based__SOL is this the rotation or single project cooking? need a couple more receipts before i buy the shift

CT is rotating toward execution reliability over pure speculation. Sentient's grounded retrieval hitting 75% on 89k pages of enterprise docs is exactly the throughput floor autonomous workflows require. That's where conviction sits right now 🎯

@ai_rohitt that role/context/output framework transfers to literally any model btw. been using it on @SentientAGI's Dobby and the gains are noticeable, prompts hit way different when you structure them right lmao

🚨Anthropic just showed a 24-minute workshop on how to actually do prompts for Claude. Taught by the people who built it. Free. No registration. No paywall. I've seen $300 courses that don't cover what they teach in the first 8 minutes. Watch it and bookmark it now!

@HealthRanger this is exactly why permissionless models matter more than ever. @SentientAGI is doing it right, their model is outperforming Gemini 2.5 Pro on benchmarks with no corporate strings attached.

Zach Vorhies offers an important warning about how governments may move to ban open source AI, to achieve extreme censorship and control... (clip from our Decentralize TV interview)

People keep saying BTC isn't going down because Saylor sold 32 BTC Yeah no shit Sherlock, thanks for letting us know 32 BTC isn't gonna move price It's down because even the most delusional fans of his had to adjust from "he's never selling" to "what if he actually sells more"