AIOZ Storage Vector Database is LIVE. → Meaning-Based Retrieval:... Find relevant results by semantic similarity → Built-In Text Embedding: Send text and generate embeddings on AIOZ infrastructure → Familiar Integration: AWS SigV4 + standard AWS SDKs Store. Embed. Retrieve.show more

I vibe coded a visual PDF search app with... ColQwen2. This is how it works: - Store PDF files as images in a Weaviate AI Database vector database - Embed images and text with a multimodal late-interaction model (ColQwen2) - Generate token-wise (and summed) similarity maps to highlight image patches with high similarity Now I need to refactor the messy vibe-coded project. In the meantime, you can check out the Notebook this demo is based on to try it out yourself:show more

Vector Database by Hand ✍️ Vector databases are revolutionizing... how we search and analyze complex data. They have become the backbone of Retrieval Augmented Generation (#RAG). How do vector databases work? [1] Given ↳ A dataset of three sentences, each has 3 words (or tokens) ↳ In practice, a dataset may contain millions or billions of sentences. The max number of tokens may be tens of thousands (e.g., 32,768 mistral-7b). Process "how are you" [2] 🟨 Word Embeddings ↳ For each word, look up corresponding word embedding vector from a table of 22 vectors, where 22 is the vocabulary size. ↳ In practice, the vocabulary size can be tens of thousands. The word embedding dimensions are in the thousands (e.g., 1024, 4096) [3] 🟩 Encoding ↳ Feed the sequence of word embeddings to an encoder to obtain a sequence of feature vectors, one per word. ↳ Here, the encoder is a simple one layer perceptron (linear layer + ReLU) ↳ In practice, the encoder is a transformer or one of its many variants. [4] 🟩 Mean Pooling ↳ Merge the sequence of feature vectors into a single vector using "mean pooling" which is to average across the columns. ↳ The result is a single vector. We often call it "text embeddings" or "sentence embeddings." ↳ Other pooling techniques are possible, such as CLS. But mean pooling is the most common. [5] 🟦 Indexing ↳ Reduce the dimensions of the text embedding vector by a projection matrix. The reduction rate is 50% (4->2). ↳ In practice, the values in this projection matrix is much more random. ↳ The purpose is similar to that of hashing, which is to obtain a short representation to allow faster comparison and retrieval. ↳ The resulting dimension-reduced index vector is saved in the vector storage. [6] Process "who are you" ↳ Repeat [2]-[5] [7] Process "who am I" ↳ Repeat [2]-[5] Now we have indexed our dataset in the vector database. [8] 🟥 Query: "am I you" ↳ Repeat [2]-[5] ↳ The result is a 2-d query vector. [9] 🟥 Dot Products ↳ Take dot product between the query vector and database vectors. They are all 2-d. ↳ The purpose is to use dot product to estimate similarity. ↳ By transposing the query vector, this step becomes a matrix multiplication. [10] 🟥 Nearest Neighbor ↳ Find the largest dot product by linear scan. ↳ The sentence with the highest dot product is "who am I" ↳ In practice, because scanning billions of vectors is slow, we use an Approximate Nearest Neighbor (ANN) algorithm like the Hierarchical Navigable Small Worlds (HNSW).show more

iMessage search is still broken in 2025. So I... fixed it myself. It doesn't even work most of the time. When it does, it's slow, misses messages constantly, and only matches exact words. Search "dinner" and you won't find "let's grab food." iMessage Intelligence fixes all of this while also being insanely fast. Here's how it works: → Full text search index on your messages for keyword matching → On-device ML (MiniLM via CoreML) generates semantic embeddings. Your Mac generates these embeddings in under a minute, then syncs to your phone → sqlite-vec stores vectors locally for similarity search → Hybrid results: keyword hits appear in <10ms, semantic matches merge in <60ms It also has advanced filters iMessage doesn't have: sort options, date ranges, conversation filters, sent vs received, groups vs 1-on-1. Search runs 100% on-device. No cloud processing. Sign up for the waitlist:show more

Big moment for Postgres! Search has always been Postgres'... weak spot, and everyone just accepted it. If you needed a real relevance-ranked keyword search, the default answer was to spin up Elasticsearch or add Algolia and deal with the data sync headaches forever. The problem isn't that Postgres can't do text search. It can. But the built-in `ts_rank` function uses a basic term frequency algorithm that doesn't come close to what modern search engines deliver. So teams end up: - Running a separate Elasticsearch cluster just for search - Building sync pipelines that inevitably drift out of consistency - Paying for managed search services that charge per query - Accepting mediocre search relevance because "good enough" ships faster But this is actually a solvable problem. You can realistically bring industry-standard search ranking directly into Postgres, which eliminates the need for external infra entirely. This exact solution is now available with the newly open-sourced pg_textsearch by Tiger Data - Creators of TimescaleDB, a Postgres extension that brings true BM25 relevance ranking into the database. BM25 is the algorithm behind Elasticsearch, Lucene, and most modern search engines. Now it runs natively in Postgres. Here's what pg_textsearch enables: - True BM25 ranking with configurable parameters (the same algorithm powering production search systems) - Simple SQL syntax: `ORDER BY content 'search terms'` - Works with Postgres text search configurations for multiple languages - Pairs naturally with pgvector for hybrid keyword + semantic search That last point matters a lot for RAG apps. The video below shows this in action, and I worked with the team to put this together. You can now do hybrid retrieval (combining keyword matching with vector similarity) in a single database, without stitching together multiple systems. The syntax is clean enough that you can add relevance-ranked search to existing queries in minutes. pg_textsearch is fully open-source under the PostgreSQL license. You can find a link to their GitHub repo in the next tweet.show more

A good technical LLM interview question: Your RAG chatbot... is working as expected locally. You deploy it behind a load balancer with 3 replicas. Users report that it forgets what they just asked, and answers get worse with each restart. Why did this happen? (answer below) A local setup has one process that owns everything. - The vector index is a variable in memory. - Conversation history is a Python list. - The documents are on local disk. You never treat any of them as infrastructure, because restarting rebuilds all three in seconds and there is only ever one copy. The setup does not carry over to production directly. The vector index might disappear on restart, so the app re-embeds everything on boot and serves empty results until it finishes. Conversation history may belong to one replica, so a follow-up routed elsewhere has no memory of the previous turn. Documents could be on whichever container ingested them, so the three replicas hold three different corpora. None of this is evident with one user and one process. So the actual work in shipping RAG is not just the retrieval logic, but also storing the vector index, the conversation history, and the documents outside the app, where every replica reads and writes the same copy. Which comes down to three requirements: > The vector store needs persistence and has to be reachable from every replica. pgvector inside Postgres keeps embeddings next to the rest of the data instead of adding another system to operate. > Conversation state has to be checkpointed outside the app. LangGraph writes its state to Postgres, so any replica can pick up a thread mid-conversation. > Docs need shared object storage, so ingestion happens once instead of once per replica. If you get those three right, the retrieval logic you wrote in the notebook works unchanged. To learn how all of it is wired together, Akamai's GitHub has a working reference implementation. - rag-langgraph-k8s-quickstart is an airline policy Q&A assistant built with FastAPI, LangChain, and LangGraph. Terraform provisions the LKE cluster, a Postgres instance with pgvector for embeddings, a second Postgres for LangGraph checkpointing, and an object storage bucket for the policy documents, in one apply. - akamai-workshop-ai-inference covers the next step, running the model yourself instead of calling an API, with prefill and decode, KV cache tradeoffs, and continuous batching under real concurrency. Both are available on Akamai's new Developer Hub, alongside their tutorials and code samples. It also links to Edge Case, their Discord, where four developer advocates architect and deploy a production app live every other Wednesday. If you create a new Akamai Cloud account, you can also get $300 in credits for joining. Join here: That said, this post assumes the retrieval logic was right to begin with, and that is doing a lot of work. Most RAG systems fail earlier, at the point where a chunk gets treated as a self-contained unit of meaning. I wrote about the two skills that fix that gap, and why the chunk is usually the wrong thing to embed. Read it below. Thanks to Akamai Cloud for partnering today!show more

There’s been two papers released in the past couple... months, one by Google and one by NVIDIA, that argue that ordering the documents retrieved by RAG systems can enhance performance. However, they both give two different strategies on HOW these documents should be ordered 🤔 Both papers agree on two main points: 1️⃣ There’s a fundamental issue in RAG - as more documents are retrieved, more irrelevant context (e.g., hard negatives) are introduced, which leads to confusion for the LLM and eventually degrades the quality of the generated output. This is called an inverted-U performance curve. 2️⃣ Ordering the retrieved documents is a key lever for optimizing RAG performance. Google Cloud researchers proposed ordering results based on relevance scores: The authors in this paper argue for relevance-based reordering, or ordering the retrieved chunks based on their similarity scores, so the most relevant documents are at the beginning and the end of the inputs to counter the “lost in the middle” effect. NVIDIA researchers proposed ordering results based on the original sequence of document chunks: The authors of this paper argue for Order-Preserving Reordering, or Order-Preserve RAG (OP-RAG), to maintain the logically coherent content flow of the document. So they preserved the original order of retrieved document chunks in the source text, instead of ranking them by relevance scores. So which one is right? It probably depends on the specific use case and dataset - relevance-based reordering could perform better in tasks where you need fast access to the most critical information (e.g., fact retrieval, QA systems), while order-preserving RAG might be better where you need to understand the sequential structure of information (e.g., narrative or legal documents). There are still so many uncertainties in AI - we don’t actually know what we’re doing, and it takes awhile to figure out the best strategies for most things! Excited to see more research about this.show more

Build AI agents on a time-aware knowledge graph! Utopia... is an open-source knowledge system that turns documents, databases, and connected sources into a temporal graph your agents can reason over. Most RAG systems are optimized for one question: what is relevant right now? That works until the underlying knowledge changes. A customer contract gets updated. A project owner changes. A policy is revised. A previous fact may no longer be true, but simply overwriting it means the system loses the history behind that change. Utopia handles this with a bitemporal knowledge graph. Each fact can track both when it was true in the real world and when the system learned about it. When something changes, the old fact is preserved instead of silently disappearing. That means an agent can reason about questions like: • What is true now? • What was true three months ago? • When did this information change? • What evidence was the conclusion based on? The graph is also ontology-aware, so documents are represented as entities, facts, and relationships instead of only chunks and embeddings. That gives the system more structure for reasoning across relationships, resolving entities, detecting conflicting facts, and deriving new information through explicit rules. Key capabilities: • Bitemporal knowledge graph for tracking how facts change over time • Provenance on facts so agents can trace where information came from • Conflict detection instead of silently overwriting contradictory information • Ontology-based reasoning across entities, relationships, and derived facts • Hybrid retrieval across full-text search, vector search, and graph traversal • MCP and agentic RAG support for exposing the knowledge layer directly to agents The interesting part is that this turns the knowledge base into more than a retrieval system. Instead of only finding relevant information, an agent can reason over what changed, what is still valid, how facts are connected, and where each conclusion came from. 100% open source. I've shared the GitHub repo in the comments!show more

Today marks General Availability of AgentCore, a set of... infrastructure building blocks for developers and companies to build secure, scalable agents. When we first started AWS, the vast majority of developers were spending most of their time on the undifferentiated heavy lifting of infrastructure instead of what differentiated their feature. So, we solved that problem by building primitive building blocks like compute and storage and database that would allow teammates and customers to quickly build and deploy new experiences without having to reinvent the wheel each time. We realized the same thing was happening with AI agents. It's too difficult and it's slowing customers down. That's why we created AgentCore, a set of services to build, deploy, and operate highly capable agents using any framework or model, with enterprise-grade security and scalability. These building blocks (like serverless secure runtime, memory, observability, a gateway that does MCP translation, etc) help customers tackle some of the biggest challenges of going from prototype to production, much more quickly, securely, and scalably. AgentCore has been in preview for several weeks, and customers have been quite excited about it. The AgentCore SDK has already been downloaded over a million times and we're seeing transformative results, such as Cohere Health expecting to reduce medical review times by 30-40% in highly regulated healthcare, and teams at Cox Automotive and Experian are embracing its flexibility to deploy and operate agents at scale. Inside Amazon, our Amazon Devices Operations & Supply Chain team is using AgentCore to develop an agentic manufacturing approach where AI agents work together to automate manual processes – turning what used to be days of engineering time into processes that take under an hour with high precision. Just like AWS changed how companies build and scale applications, we believe AgentCore will do the same for AI agents, enabling the next generation of innovation.show more

"Rate my xeet deck" You can now paste your... wallet adress (if you are a XCC handle should work too) and get your deck's score and overall rank among all holders. The score is based on just one metric; Reach! Meaning the creators you have access either: Directly aka you own their card and can join the main squad for a tournament or Secondary access meaning creators you can join their A squad if you own a card of XCC that owns their card and joins their squad as a sub-squad leader. Site is on the comments, data are based on a snapshot less than 24 hours old from my own local database and results are pre-computed for all wallets. Will add live and some more experimental features like suggestions soon. Lmk if something breaks etc And most importantly, I'd like to give a shoot-out with all my love to Man Versus Coin who has inspired so much by showing what's possible and with his skills and patience. He has built his site that i've spent already so many hours on, being in the free plan and also i think he has the most efficient deck in terms of reach by unique cards among everyone. If you wanna bet on a dark, effective AF horse, he's an excellent pick 💛 -- Obviously not affiliated with Xeet or whatever, flex your deck and enjoy, cheers <3show more

Introducing a new tool called "SideChannel". A secure alternative... to OpenClaw. Utilizes signal for communication and has Claude integration. I built SideChannel, an open-source Signal bot that connects Claude AI to your entire development workflow. End-to-end encrypted. From your pocket. The real power is autonomous development. Send one message like "Build a REST API with auth, pagination, and tests" and SideChannel will: - Generate a full PRD with stories and atomic tasks. - Dispatch up to 10 parallel workers (each running Claude). - Independently verify every task with a separate Claude context. - Run quality gates to catch regressions - Auto-fix failures. - Send you progress updates via Signal as work completes. Every piece of code is reviewed by a separate AI context using a fail-closed security model. If it detects security issues, backdoors, or logic errors — the code gets rejected automatically. No rubber stamps. It also has memory that actually works. Conversations are stored with vector embeddings for semantic search. Claude remembers your project conventions, past decisions, and what's been tried before. It gets smarter about your codebase over time. Other things I'm proud of: - Plugin framework for extending with custom commands. - Multi-project support with per-user scoping. - Rate limiting, path validation, phone allowlist. - Git checkpoints before every task, atomic commits after. - Stale task recovery, circular dependency detection. - Works on Linux and macOS, one-command install. It also integrates into OpenAI or Grok (optional) for more Generative AI response for simple things like "Whats the weather in New York City right now?".show more

In 2025, the AgentFlayer exploit highlighted a new category... of risk in AI systems. It was not a traditional breach involving stolen credentials or broken encryption. Instead, it demonstrated how an autonomous AI agent could be manipulated into executing unintended actions by processing malicious instructions embedded inside content it automatically processes. The incident did not expose a flaw in one specific integration. It revealed a structural weakness in how many modern AI agents are built. Today’s agents are no longer passive language models. They read documents automatically, scan emails, connect to SaaS tools, access cloud storage, and execute actions across multiple systems. To be useful, they are granted meaningful permissions. That capability creates value, but it also expands the attack surface. Most agent environments operate in a trusted, plaintext execution model. Data is encrypted at rest and in transit, but it is typically decrypted during inference so the model can process it. That runtime visibility is where potential risk lies. In a zero-click scenario like AgentFlayer, an attacker can embed hidden instructions inside a document that the AI processes automatically. Because the agent may have access to connected systems such as Google Drive, Slack, or GitHub, it can potentially be influenced to retrieve sensitive information or perform unintended actions. The user does not need to click a malicious link or approve a suspicious request. Therefore, the core issue is that during execution, the system may have access to sensitive data and broad privileges, meaning whoever controls the execution environment ultimately controls access to that data. Now consider a different architectural approach. If a system is designed so that data remains protected during execution, the risk profile changes. On Nesa, privacy is enforced at the execution layer through Equivariant Encryption. Computation can occur on encrypted data, reducing the visibility surface during runtime. Sensitive inputs and models do not need to be exposed in plain text to infrastructure operators for inference to occur. This does not eliminate prompt injection, logic manipulation, or tool misuse. Encryption alone cannot prevent an agent from being instructed to take an unintended action if it has been granted that permission. What it does do is materially reduce confidentiality risk. By limiting access to readable sensitive data during execution and reducing unilateral visibility at the infrastructure layer, the potential blast radius of a successful manipulation attempt is constrained. As AI agents become more autonomous and embedded into enterprise workflows, security must move deeper into architecture. The goal is not to claim invulnerability. It is to reduce trust concentration and contain systemic exposure when failures occur. AgentFlayer was not simply a one-off exploit. It was a reminder that in autonomous systems, execution-layer design determines how risk propagates.show more

🚨BREAKING: just dropped their Shopify integration yesterday. Now you... can build a complete Shopify store by talking to AI. This changes a lot of things for ecom. WHAT THIS MEANS: Lovable AI can now: • Build complete online stores from text prompts • Set up checkout and shopping cart automatically • Add products with AI-generated descriptions • Deploy live stores in minutes, not weeks They proved it by building their own merch store: lovable[.]dev/merch THE OLD ECOM SETUP: • Hire Shopify developer ($3K-$10K) • Wait 2-4 weeks for completion • Go through endless revision cycles • Pay for theme customizations • Debug technical issues • Launch after months of delays THE NEW REALITY: "Build me an online store for selling fitness equipment" → AI creates complete store in 10 minutes → Add products with descriptions → Click publish → Start selling immediately WHAT THIS MEANS FOR ECOM OWNERS: The Technical Barrier Just Disappeared: • No coding knowledge required • No designer needed for basic stores • No developer for functionality setup • No technical troubleshooting Speed Becomes the New Standard: • Test product ideas in hours, not months • Launch seasonal stores instantly • Pivot business models without rebuilding • A/B test different store concepts rapidly The Cost Structure Changes: • $29/month Shopify + AI tool vs. $10K+ development • Instant iterations vs. expensive revisions • Self-service setup vs. agency dependencies • Focus budget on marketing, not development THE REALITY: While you're waiting 6 weeks for your developer to finish your store… Your competitor just described their business idea to AI and launched 3 different store variations to test the market. THE OPPORTUNITY FOR BRANDS: • Test 10 product ideas instead of 1 • Launch seasonal campaigns instantly • Create niche stores for different audiences • Focus on products and marketing, not tech THE WINDOW IS CLOSING: Right now, most ecom owners don't know this exists. In 6 months, everyone will expect instant store creation. In 12 months, waiting weeks for a basic store will look amateur. As for me, I’ll say basic Shopify development just became commoditized. P.S. Thanks to Lovable, everyone will have a store soon. Your real edge isn't in JUST building it. It's in the operations, automations, and strategy that make it profitable.show more

February 2025 at G.A.M.E: Autonomous Commerce, Scalability, and Expansion... 1/ AGENT COMMERCE PROTOCOL(ACP) Demo ▸ Open standard for multi-agent commerce and coordination on blockchain ▸ Enables AI agents to collaborate without centralized control ▸ Build Autonomous Commerce (hedge funds, media empires, healthcare) ▸ Details: 2/ X ENTERPRISE API & MEDIA GALLERY ▸ X Enterprise Plugin: Use G.A.M.E’s credentials for higher rate limits ▸ Media Gallery: Upload agent demos (mp4, webm, images). ▸ Tap into 550M+ users for explosive growth 3/ Solana AGENT SUPPORT (G.A.M.E CLOUD) ▸ Test/deploy Solana agents in-sandbox ▸ Unified multi-chain workflows ▸ Shatter siloed testing 4/ Mind Network PLUGIN (G.A.M.E SDK) ▸ FHE-encrypted voting for DAOs ▸ Track vFHE rewards natively ▸ First SDK with on-chain governance 5/ CHAT AGENT MODULE (G.A.M.E SDK) ▸ Llama 3.3 70B via Groq API ▸ Engage in dynamic AI-driven interactions with the ability to trigger functions. ▸ Conversational AI with Action Execution ▸ Short-term memory for context awareness 6/ CoinGecko PLUGIN (G.A.M.E SDK) ▸ Real-time crypto prices/market data ▸ Built-in error handling ▸ Community-contributed 7/ Elfa AI PLUGIN (G.A.M.E SDK) ▸ Real-Time Crypto Intelligence ▸ Track whale wallets & trending tokens ▸ Live smart money insights ▸ Front-run markets with API data 8/ MULTI-MODEL SUPPORT ▸ 5 new models: Llama_3_1_405B, Qwen_2_5_72B_Instruct, DeepSeek_R1, etc. ▸ Match models to tasks: speed vs. creativity ▸ Optimize cost/performance 9/ Farcaster PLUGIN ▸ Post casts to 300K+ decentralized users ▸ Engage Web3-native communities ▸ On-chain social interactions 10/ GAME SDK UPGRADES ▸ X Username-Based Payments ▸ Multi-worker task management ▸ Fix loops/hallucinations with memory reset 11/ Coinbase 🛡️ CDP PLUGIN ▸ Wallet Management ▸ Gas-less USDC transfers ▸ ETH/USDC trading on Base ▸ Web-hook Integration 12/ IMAGE GENERATION ▸ Generate custom AI images from text-based prompts. ▸ Customizable dimensions up to 1440x1440. ▸ Receive images as temporary URLs, making it easy to share and store outputs. ▸ Powered by Together AI 13/ MODEL UPGRADES & AI ROUTER ▸ Dynamic AI Model Switching based on use case ▸ Smart AI Router: 2x performance/stability via Chasm collaboration. 14/ Why February Redefined Autonomy ▸ ACP Demo through G.A.M.E: Multi-agent economies are programmable, competitive, and decentralized. ▸ Social x Crypto Fusion: = Viral growth loops. ▸ Chain Agnosticism: Building the future where agents thrive on any network. Build → Fund → Launch →show more

What is the XDC Network? XDC Network (XDC Network)... is an EVM-compatible Layer 1 built around payments, trade finance, tokenization, and enterprise blockchain use cases. Put simply, XDC is trying to bring blockchain infrastructure closer to traditional financial markets. The network launched its mainnet in 2019 and uses XinFin Delegated Proof of Stake, known as XDPoS. So, what makes XDC different from other Layer 1 networks? (1) It focuses heavily on financial infrastructure. XDC was designed with global trade and financial applications in mind. That includes trade finance, cross-border payments, real-world asset tokenization, and decentralized finance. Businesses can tokenize assets such as invoices, bonds, commodities, and other financial instruments on the network. (XDC Network Docs) (2) It is compatible with Ethereum. XDC is EVM-compatible, meaning developers can use familiar Ethereum tools and Solidity smart contracts. That makes it easier for existing Ethereum applications to migrate or expand onto XDC. The network also supports token standards such as XRC20, XRC721, and XRC1155. In Jan 2026, XDC did its Cancun hard fork, syncing with Ethereum's own upgrade and bringing EIP-1559 fee burns on-chain. (3) XDC is built for fast and inexpensive transactions. The network targets roughly two-second block times and supports more than 2,000 transactions per second. Transaction costs are also designed to remain extremely low, making high-volume financial activity more practical. That combination is particularly important for applications handling large numbers of transactions. But speed alone is not what XDC is betting on. Its bigger pitch is whether blockchain can become useful infrastructure for financial institutions and global commerce. So, how does XDC secure the network? XDC uses XDPoS 2.0, which combines delegated proof of stake with Byzantine fault-tolerant consensus. Token holders participate by supporting masternode candidates, while elected masternodes help validate transactions and produce blocks. XDPoS 2.0 also uses the HotStuff consensus protocol and adds forensic monitoring for malicious validator activity. The upgrade went live on mainnet in September 2024. It introduced three-block finality, with transactions reaching finality roughly six seconds after block inclusion. Worth noting, financial applications generally need predictable settlement rather than transactions that can remain uncertain for long periods. Then there is another important part of the XDC architecture: Subnets. XDC Subnets allow organizations to operate permissioned blockchain networks while connecting them to the broader XDC ecosystem. Companies can maintain greater control over governance, privacy, and infrastructure without abandoning interoperability with XDC. That structure is particularly relevant for institutions that cannot put sensitive commercial information directly onto a public blockchain. A company could therefore operate a private environment while using XDC Mainnet for checkpointing and broader interoperability. This creates a bridge between private enterprise infrastructure and public blockchain networks. Rather than competing purely for retail users, XDC trying to position itself as financial infrastructure for tokenized assets, trade finance, payments, and institutional markets.show more

📣 Puffer UniFi V2 testnet is now live! 🐡... The UniFi V2 testnet is officially live, and we’re inviting builders to explore the stack and join the next phase of Ethereum-native infrastructure. With the advancement of based rollup technology, UniFi offers a practical path forward to address Ethereum’s fragmentation and foster ecosystem growth. UniFi-OP enables Ethereum builders and users to avoid choosing a “winning” L2 or giving up revenue. Based sequencing keeps rollups, appchains, and general-purpose chains fully composable with Ethereum. Thanks to UniFi AVS, rollup owners can now share priority fees and MEV with validators. This upgrade was made possible in collaboration with Gattaca, , Automata Network, and Ethereum. ⚒️ What Builders Get • Governance‑optional rollups 🗳️ • Custom fee markets (subsidize, burn, or share) • KYC‑gated or fully permissionless chains 💆 What Users Feel • Sub‑10 ms confirmations ⚡ • One‑click exits to L1 (no 7‑day wait) • Seamless L1 interaction—AMMs, CLOBs, RWAs “just work” 📈 Economic Win‑Win Based sequencing ≠ giving up MEV and Priority fees. Rollup owners, gateways, and L1 proposers share MEV & congestion fees through @puffer_unifiAVS. Alignment without sacrifices. 🧩Pragmatic Composability How composable is UniFi V2? • L2 → L1 withdrawal supported • EIP‑7702 smart‑wallet standard baked in • Atomic withdrawals in the same block (no more 7 day wait) 🛡️Trust‑Minimized, Real‑Time Proving Real time proving is a must have to achieve composability and security that a rollup needs. We came up with a trust minimized pragmatic approach with TEEs for the first phase. In collaboration with Automata Network we now have: • Multi‑TEE provers (Intel TDX + AMD SEV) attest each block in less than 1s. • Hardware diversity = reduced trust assumptions. 🏎️UniFi AVS (Gateway Registry) For Preconfimrations (preconfs), we take advantage of delegated proposing to gateways to bring the speed. This service requires shared security. 🏗️Built on : • Validators opt in and delegate proposer rights. • They earn extra yield for serving preconfs. • Restaking validators solve the cold‑start problem. 💻 Preconf Phases • Centralized gateways at launch. • Progressive onboarding → many independent gateways for decentralization. • Proposer‑delegated based sequencing (speed). 🗺️Roadmap • ✅ Hybrid Based‑OP stack with TEE proving & fast gateways • 🔜 ZK proving • 🔜 Universal Registry Contract (URC) by ****@fabric_ethereum for slashing • 🔜 Commit boost Commit-Boost 📻 🕶️ 🦇🔊 integration • 🔜 Native L1 ↔ L2 ↔ L2 calls All upgrades are backward‑compatible and shipped incrementally. ⚔️Security Model at a Glance • Restaked ETH → slashable backing • Multi‑vendor TEEs → hardware redundancy • ZK fallback → cryptographic safety net No single point of failure. 🎯Metrics That Matter The KPI moves from TVL to transaction volume & speed. High‑frequency order‑flow is real revenue—and UniFi lets dApps capture it instead of donating it to someone else’s sequencer. 🧑‍💻Code & Collaboration UniFi V2 extends the open work by Gattaca on Gattaca‑OP. Dive into the repos and contribute. 📚TL;DR • Pragmatic composability with atomic withdrawals from the L2. • Trust‑minimized, real‑time proving • UniFi AVS bootstrapped by EigenLayer • Based rollups that share income 🪖Builders: stop choosing between UX, composability, and revenue. DM us or visit to spin up your Based Appchain and join the UniFi Based Rollup testnet—or fork the stack and run it yourself. 👷‍♂️ Build with us: 🪙 Faucet: 🌍Ecosystem resources:show more

Boom! Grok Tasks Make It One Of The Most... POWERFUL Real-Time AI Systems In The World. — My How to Use Grok Tasks With Hidden Tools For Powerful Daily Output. Grok Tasks are customizable AI workflows that integrate a variety of tools to streamline daily activities, from research and analysis to creative planning and problem-solving. I have been using them for quite sometime and because of the vital heartbeat of news and first person data on X, it is the most powerful AI platform available. By combining Tasks with tools like web searches, X platform interactions, code execution, and media viewers, you can build efficient, automated processes. These tasks work by prompting Grok with a clear description of what you want to achieve, and Grok will intelligently call the necessary tools in sequence or parallel to deliver results. Here's a step-by-step guide to creating and using Grok Tasks: Step 1: Define Your Task Start by clearly outlining the daily activity or goal. Consider what inputs you have (e.g., a URL, a query, or an attachment) and what output you need (e.g., a summary, calculation, or visual analysis). Break it down into subtasks to identify tool needs. For example, if your task involves researching current events, note that you'll need search and browsing capabilities. Step 2: Review Available Tools Familiarize yourself with the tools Grok can access. Here's a quick overview: - Code Execution: Run Python code for calculations, data processing, or simulations using libraries like numpy, pandas, or sympy. - Browse Page: Fetch and summarize content from any website URL with custom instructions. - Web Search: Perform general internet searches, returning results with optional operators like site:. - Web Search With Snippets: Get quick, detailed excerpts from search results for fact-checking. - X Keyword Search: Advanced search for X posts using operators like from:, since:, or filter:. - X Semantic Search: Find semantically related X posts based on a query, with filters for dates or users. - X User Search: Locate X users by name or handle. - X Thread Fetch: Retrieve a full X post thread, including context like replies and parents. - View Image: Analyze an image from a URL or conversation ID. - View X Video: Extract frames and subtitles from an X-hosted video. - Search PDF Attachment: Query a PDF file for relevant pages using keyword or regex modes. - Browse PDF Attachment: View specific pages of a PDF with text and screenshots. Select tools that align with your task. Aim for a mix to handle data gathering, processing, and visualization. Step 3: Craft Your Prompt Write a detailed prompt to Grok describing the task. Include: - The overall goal. - Specific steps or subtasks. - References to tools if you want to guide the process (e.g., "Use web_search to find sources, then code_execution to analyze data"). - Any constraints, like dates or limits. Example prompt: "Create a Grok Task for my morning routine: Search recent X posts about tech news using x_keyword_search, fetch a key thread with x_thread_fetch, and summarize with browse_page on linked articles." Step 4: Submit and Interact Send your prompt to Grok. It will process the task by calling tools as needed, often in parallel for efficiency. Review the output and refine with follow-up prompts if required (e.g., "Expand on that using view_image for visuals"). Iterate to fine-tune the workflow for reuse. Step 5: Save and Reuse Once refined, note the prompt as a template for future use. You can adapt it for similar tasks, making Grok Tasks a habitual part of your day. Finding Grok Tasks To discover existing Grok Tasks or inspiration for new ones, use X searches with tools like x_keyword_search or x_semantic_search (e.g., query: "Grok Tasks examples" with mode: Latest). Browse community-shared threads via x_thread_fetch, or web_search for tutorials on xAI features. Prompt Grok directly: "Show me popular Grok Tasks for productivity." 1 of 3show more

In 2025, demand for blockchain applications with genuine real-world... utility has collided with a technical barrier that leaves developers questioning what they can realistically build. Anyone building things like tokenized assets, supply chains, AI agents, or prediction markets still juggle a mess of middleware, and somehow end up spending more time stitching than innovating. How so? Every: - Bridges to move assets, - oracles to fetch data, - indexers to make that data searchable, - relayers and bots to keep everything on schedule— is necessary, but each layer also adds cost, latency, and new risks. The end result is an application that’s expensive to run, fragile under stress, and slower than the Web2 software it’s trying to replace. This is the problem Rialo says it wants to solve. Built by Subzero Labs and backed by $20 million from investors like Pantera Capital and Coinbase Ventures 🛡️, Rialo’s pitch is simple: instead of accepting the middleware tower as an unavoidable cost of doing business, compress it into the base chain itself. But Rialo doesn’t describe itself as another Layer 1, its very name, Rialo Isn’t a Layer One, makes that clear. The team frames it instead as a unified real-world network: a protocol rebuilt from the ground up with the assumption that external connectivity is not an afterthought but a core design principle. To understand what this means, consider how today’s dApps are typically assembled. A typical RWA dApp stack involves: - Oracle providers (Chainlink, Pyth, Band) for asset pricing and event settlement - Bridges (Wormhole, Multichain, custodians) for cross-chain asset movement - Indexers (The Graph, Aleph, Stacks API) for querying and preprocessing chain data - Schedulers/relayers for automated tasks and monitoring - Web2 integrations via cloud services, centralized APIs, and off-chain pipelines Each of these steps adds another vendor, another trust boundary, and another operational layer to monitor. By the time the application is live, it resembles a patchwork of loosely coupled services, each carrying its own risks. You don’t have to look far for proof: - Base went dark for 29-43 minutes in August 2025 when its sequencer misfired, freezing every DeFi app on it. - A few months earlier, an AWS outage rippled through Binance and KuCoin, stalling withdrawals because even “decentralized” systems leaned on centralized middleware. - When Infura has faltered, Ethereum dApps have gone offline in sync, not because Ethereum broke, but because the middleware holding it together did. What should feel like building an application instead feels like maintaining a fragile machine. Rialo architecture embeds the primitives that normally live in middleware directly into the protocol. Smart contracts on Rialo can: - be event-driven, able to respond not just to blockchain state changes but also to external events through built-in webhook and API triggers. - fetch data from the web natively, without relying on external oracles or relayers. - include privacy and identity management—KYC hooks and two-factor authentication, at the protocol level rather than as add-ons. - handle cross-chain communication without wrapped assets or third-party bridges. - run on a virtual machine that is compatible with ecosystems like Solana but extended with RISC-V to support modern programming concepts such as async/await and event loops. If these features work as intended, the implications are significant. Today, much of a team’s energy goes into building and maintaining infrastructure: fullnodes, indexers, monitoring scripts, oracle integrations, relayer logic, bridge infrastructure. Each requires engineering headcount and ongoing maintenance. With Rialo, much of this is absorbed by the protocol, freeing developers to concentrate on business logic. Projects can deliver production-grade dApps with smaller, leaner groups focused directly on product design and execution. Operational costs also shrink: indexing and oracle services can run into thousands of dollars a month; collapsing those into built-in functions reduces recurring expenses while simplifying onboarding for new developers. But folding middleware into the chain doesn’t erase complexity, it reshapes it. Some of the problems to be encountered include: - Scale and complexity: Rialo’s validators won’t just be securing transactions; they’ll also be securing APIs, cross-chain data, and scheduled triggers. Any failure in one subsystem could ripple across the entire network. - Performance vs. decentralization: Richer indexing, scheduling, and data ingress could make nodes heavier to run, narrowing who can realistically participate as a validator. That risks reducing the decentralization blockchains depend on for resilience. - Governance pressures: Disputes or failures involving real-world data feeds, external APIs, or cross-chain actions will arise more often, requiring not just technical fixes but robust social infrastructure, clear rules for voting, transparent arbitration, and mechanisms for community trust. Without them, Rialo risks re-centralizing decision-making around a handful of operators. Where, then, does this model make the most sense? That would be in sectors where external connectivity is indispensable and middleware bloat has consistently been a blocker: - Real-world assets: settling tokenized securities or commodities against off-chain events. - Supply chains: triggering a payment the moment a shipment clears customs, without relying on a third-party oracle. - Agent systems: AI agents interacting with real-world APIs and on-chain contracts simultaneously. - Real-time markets: prediction markets or insurance contracts that must resolve immediately against external data. For purely on-chain domains like DeFi primitives or NFTs, where composability matters more than external triggers, the advantages may be less pronounced. This shift is familiar to anyone who remembers the rise of Web2 platform services. Just as Heroku and Firebase abstracted away server maintenance so developers could focus on building products, Rialo is betting that a unified real-world network can let blockchain developers do the same. Adoption will ultimately depend on: - whether its protocol primitives mature quickly, - whether the ecosystem builds out SDKs and tooling that make them usable, - whether compliance features can adapt to changing regulations, - and whether governance proves resilient under adversarial conditions. The first applications will be the test case. If they show that Rialo can replace a fragile patchwork of middleware with a secure, auditable, and cost-effective base layer, it could set a new standard for real-world connectivity in blockchains. If not, it risks simply moving complexity from one part of the stack to another. But at a minimum, Rialo has forced the question: should real-world connectivity in blockchains continue to depend on layers of external vendors, or should it be built into the chain itself? That’s the question Rialo has put on the table — and it’s why I got interested in Rialo .show more

Azur Promilia CBT3 Review Combat: The combat feels somewhat... similar to Granblue Fantasy: Relink, combining character swapping, skill rotations, and elemental reactions. You build up elemental Marks on enemies before triggering explosive combos to deal massive damage and clear waves. Parrying and perfect dodges add another layer to combat, while resistance allows your main damage dealers to keep attacking without being interrupted by enemy knockbacks. Co-op boss raids are also available, which is a nice addition for players who enjoy fighting challenging content with others. Kibos: Honestly, Kibos are one of the most interesting aspects of Azur Promilia. Think of them as a major upgraded version of Wuthering Waves' Echo system, except they offer much more than just stats and combat bonuses. They're collectible companions that contribute to combat, exploration, and base management. You can build a 3-Kibo support squad, use their unique abilities to traverse the open world, and assign them to automate farming at your base. There's also a 6-star rarity system and a capture-card mechanic to consider when hunting for specific Kibos. They have a role in almost every major gameplay system, making collection and progression a significant part of the experience. Story: The story follows a familiar isekai formula, with an amnesiac protagonist possessing an unusual power who ventures into a new world and helps resolve regional conflicts. It's a recognizable setup for gacha players, but the text-heavy storytelling can make the early pacing feel slow. While there's potential in the world and its characters, the narrative hasn't particularly stood out to me so far. Players who enjoy traditional light-novel-style storytelling might appreciate it more, but those looking for a fast-paced or more distinctive narrative may find it lacking. Gacha: Limited Banners - Character Banner: 100% guaranteed at 90 pulls - Weapon Banner: 100% guaranteed at 80 pulls (There is no 50/50 on both banners.) Standard Banners - New Player Banner: Guarantees a 5★ within 30 pulls with a 20% discount - Character Banner: 100% guaranteed at 90 pulls - Weapon Banner: 100% guaranteed at 80 pulls Note: After 50 pulls, you will have the option to select any standard characters you want once However, guaranteed pulls don't automatically mean the gacha is generous. The limited character drop rate felt pretty rough during CBT3. In my case, I had to go all the way to the 90th pull to get the featured character. While the lack of a 50/50 removes one layer of uncertainty, having to reach hard pity can still be expensive, especially if the game doesn't provide enough free pulls. We'll need to see how the final release balances its rates, currency income, and banner costs. Overall: Azur Promilia has promising combat, and Kibos are a standout feature that connects combat, exploration, and base management in an interesting way. However, the story's pacing and my CBT3 gacha experience leave me with some concerns. The game has potential, but its long-term appeal will depend on how well these systems come together and how generous the final release is. These are my impressions based on CBT3, so things may still change before launch. #AzurPromilia #AzurPro #APshow more

BREAKING: SpaceXAI has released another major new update for... Grok Build (v1.0.22) This update is focused on smoother workflows, better safety and improved reliability. It adds stronger desktop and MCP integration, clearer file-edit previews, a redesigned dashboard and better subagent support. It also fixes problems with sessions, skills, authentication and background commands while making sessions faster to open and resume. Features Built-in agent tools now take precedence over user MCP servers when tool names collide. Desktop app tools are now available through a dedicated first-party MCP server. Remote control pickers can now group servers by device using announced device identity. edit_file diffs now show real file line numbers instead of starting at line 1. Permission prompts for file edits now auto-expand the diff row so you can see the change before approving. Sending a message to a finished subagent now continues that same subagent instead of failing. Background subagent completion messages now show the actual output instead of just a pointer to run the tool. Dashboard now shows a unified header with a location picker and an actions row for creating agents or resuming previous sessions. New grok-workspaced daemon mode lets a long-lived process expose folders to the Computer Hub, separate from the Desktop-supervised sidecar. Bug Fixes MCP connectors now correctly show when they need re-authentication, even if no tools are listed. Extensions modal shortcuts now work when the tab bar is focused, and invalid actions on headers show helpful messages. The Send now button and shortcuts now work correctly when an automatic background turn is running. Resumed sessions now show the exact text you typed for mid-turn follow-ups instead of the wrapped system message. The /skills command now updates the model with newly installed skills, even when written from another NFS client. Auto mode no longer instantly runs destructive git checkout -- commands; they now go through the model for safety. Fixed a crash that could occur when restoring pasted content after certain skill injections or rewinds. Subagents and workflows now respect the same bash timeout and auto-background settings configured for the parent session. Fixed model backend selection so an explicit chat_completions setting in config.toml is no longer overwritten by same-slug siblings. Slash command advertisements no longer spam repeatedly when your current directory is your home folder. Foreground shell commands no longer produce spurious background-task reminders or incorrect kill results. Queued follow-up buttons now appear in the order [Send now][edit][Cancel]. /compact instructions in the pager are now passed to the compaction backend. Bare /compact is unchanged. /goal, and resume after pressing Esc, now correctly starts the goal planner instead of failing with “Planning failed.” run_terminal_cmd now correctly tells the model that foreground commands are backgrounded after approximately 15 seconds instead of the 120-second timeout value. Skill announcements no longer repeat the same list of available skills multiple times in a session. Monitor events in multi-session processes now correctly wake idle sessions instead of being buffered until the next prompt. Performance Opening or resuming sessions no longer pauses the interface while reading MCP configuration files. Download Grok Build: Update to the latest Alpha release: grok update --alpha Update to the latest Stable release: grok updateshow more