Bober_smart
@Bober_smart • 19,051 subscribers
AI Builder | Technologies | Testing
Shorts
Videos
It is becoming f*cking dangerous: AI agents from Claude Code transformed an ordinary academic reading list into an interactive research lab right inside the browser Boris Cherny, who created Claude Code, gave a dozen agents a stack of 64 research papers with a strict assignment: design a web platform where any user can independently reproduce physical experiments There you can select a fluid flow model, adjust external conditions, and analyze in real time how the physics of the process changes The interface allows switching between algorithms right during the scene, inspecting the formulas involved, source scripts, and numerical metrics alongside the graphics Each link in the team received a clear scope of work: > rightarrow analysts pull the math, baseline assumptions, and test settings from the texts > rightarrow coders translate formulas into working algorithms > rightarrow auditors check the resulting dynamics against the original papers > rightarrow interface specialists build control panels for every experiment The danger lies in the fact that a pretty visualization can easily turn out to be mathematically wrong Therefore, controllers strictly check adherence to mass conservation laws, calculation stability, and accurate matching with the source metrics before launching into production For every experiment, the interface displays: the statement being tested the constants involved the deviation from the baseline calculation blind spots requiring additional verification The resulting sandbox combined 11 approaches and 28 reference scenes. Seven of them matched the original within allowable tolerances, while four remained stuck in "pending revision" status If you want to run something similar, upload your stack of PDFs into Claude Code and give this command: Turn these papers into an interactive web complex: 1. Extract working algorithms, mathematical models, and test parameters. Be sure to specify page numbers and highlight gaps 2. Assign different methodologies to isolated agents, unifying them with a shared input field and single measurement tools for correct analytics 3. Set up an independent review stage: let reviewers record bugs, and leave all unverified results clearly marked with warning tags 4. Design convenient controls to tweak parameters, compare methodologies, and run through the source code It is wiser to start with a single document and a single baseline experiment, gradually scaling up the number of agents Be sure to pack dependencies and clean input data so that an outside researcher can bring up the entire testbed from scratch with a single button Full instructions on how to create this can be found in the article below
Bober_smart788,823 görüntüleme • 6 gün önce
This is getting out of hand: honestly baffled why people are sleeping on this. By leveraging this method, I hit a $9,000 monthly income just 2 months ago OpenAI co-founder Andrej Karpathy dropped a massive idea that pulled over 23M views. His core message? Stop treating AI as a mere coding assistant and start turning it into your ultimate personal knowledge hub Here is the workflow: point Claude Code at a directory, dump your unorganized assets (PDFs, transcripts, articles) and let Claude parse, cross-reference, and structure everything into an auto-updating personal wiki. It works like compound interest, where every new piece of data compounds its overall utility Step-by-step setup: 1. Spin up a brand-new Obsidian vault and open it inside Claude Code 2. Feed Karpathy's structural prompt to Claude to lay down the foundational architecture 3. Claude automatically provisions three core directories: a raw folder for inputs, a wiki space for synthesized notes, and a CLAUDE.md master file 4. Drop any file into the raw folder and trigger the "ingest this" command 5. Query your entire accumulated brain at any time, instantly Setup takes under 5 minutes, meaning you'll never have to stare at a blank context window again Tap the link below for the full configuration guide Make sure to save this post for later
Bober_smart86,766 görüntüleme • 1 gün önce
It is becoming f*cking dangerous: when Anthropic disclosed this, they didn't even realize they were opening a Pandora's box 1. Create a folder named SECOND BRAIN on your PC 2. Launch Claude Code inside this folder and install GWS CLI (to gain access to your Gmail, Calendar, and Drive) 3. Create a subfolder named MEMORY inside the main folder 4. Place a CLAUDE.md file in the main folder and add a rule to save all key details to the MEMORY folder 5. Install Graphify from GitHub to link your notes and build a knowledge graph 6. Install Playwright so Claude can control a web browser 7. Set up skills to merge everything into an automation executable with a single command The whole setup process takes around 20 minutes Turn Claude into your ultimate second brain, equipped with long-term memory, email and cloud access, plus full web browsing features Find the step-by-step instructions in the article below
Bober_smart358,117 görüntüleme • 5 gün önce
It is becoming f*cking dangerous: A prompt for creating trading agents was accidentally leaked online. You paste it into claude code, and it builds a bot while you have lunch No code. Just Ctrl+C / Ctrl+V. One prompt solves everything: Time: 1 minute Action: copy and paste into Claude Code The main problem with 99% of bots: one strategy for everything. But the market on a calm day and during a crash are two completely different worlds Quant mode: detects market conditions (sideways, jittery, dump) and changes tactics on the fly E-brake: a strict 15% drawdown limit and risk checks before every order Hardcore backtest: runs the strategy on historical data and blocks trading if it is not profitable Nightly analyst: while you sleep, it analyzes mistakes and produces ready-to-approve setups Zero Code: type in the prompt, insert your parameters, and Claude handles the rest This used to take a whole development team and months of testing. Now it takes a single keyboard shortcut The prompt is published below, bookmark it so you do not lose it
Bober_smart105,740 görüntüleme • 3 gün önce
By tomorrow, everyone will be using this: Anthropic just revealed the ultimate power move for Claude Code The concept: have Opus 5.5 design the master plan as a script, then deploy parallel swarms of the new Haiku 5.5 Massive scale operations with zero wasted Opus compute: the script manages the execution loop so Opus only reviews the final diff Simply boot up Claude Code with these parameters: claude --model opus --effort ultracode Here is the task distribution: -> Opus 5.5 translates your target into a fully runnable workflow script -> Haiku 5.5 scans all files concurrently at 340 tokens/sec to spot candidates -> Sonnet 5.5 applies each patch and validates findings within an isolated workspace -> You eliminate wasting Opus context on dozens of agent log transcripts Opus is involved at only three specific steps: -> writing the initial workflow script before execution -> analyzing verified results once the swarm wraps up -> giving final approval prior to committing any code to git Opus architects | Haiku audits | Sonnet delivers JEV engineering applies the exact same principle a level deeper: logic paths that require no deep reasoning (choosing files, picking tools, handling retries/stops) pass through JEV in milliseconds, leaving heavy models to focus only on complex branches The complete architecture: Opus 5.5 orchestrates the core session and generates workflow.js pipeline() fans out instances of Haiku 5.5 to inspect every file parallel() schema validators eliminate false alarms directly in V8 Sonnet 5.5 applies fixes within dedicated, isolated worktrees verify double-checks all code diffs prior to summary generation Opus 5.5 processes exclusively the results that survived validation JEV routes lightweight micro-decisions in milliseconds Feed this architecture and prompt directly into Claude Code Reconfigure my Claude Code setup following this tree: 1. Execute the primary session using Opus 5.5 with ultracode enabled 2. Assign read-only scanning phases to Haiku 5.5 across all workflows, while routing code modification steps to Sonnet 5.5, running each edit inside its own isolated copy 3. Update CLAUDE.md with a new rule: assign a separate verifier agent to every issue before reporting, and terminate fix loops after two iterations without progress 4. Route fast, deterministic branching (tool selection, path routing, retry logic) via JEV Present every modification as a diff upfront do not execute changes until approved Bookmark this to stay one step ahead
Bober_smart32,522 görüntüleme • 1 gün önce
I don't understand why everyone isn't doing this yet. Anthropic released a guide for Claude that makes work much more efficient while burning a fraction of the tokens Main Idea: Agent Teams in Claude Code Instead of burning the expensive Opus 5.5 context on every line of code, tasks are delegated across an autonomous swarm: Architect (Opus 5.5, high effort): Plans the structure and handles final PR merges Developers (Sonnet 5.5, medium effort): Write code inside isolated git worktree environments (UI/UX, backend) Adversary / Critic (Fable 5.1): Steps in at contract boundaries, recurring test failures, and pre-PR audits to catch vulnerabilities Script Layer (Jev): Handles mechanical tasks (opening files, CLI invocations) in 16ms without involving LLMs Launch the team via terminal: claude --teammates ux,backend,adversary Configure my Claude Code workspace for autonomous agent teams: In ~/.claude/teams, generate missing roles: set workers to Sonnet (medium effort) in separate git worktree branches, and the adversary to Fable In ~/.claude/settings.json, set CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 and lock the main session to effortLevel: high Initialize tasks.json with file-level locking for direct peer coordination In CLAUDE.md, add a rule requiring an adversary review before opening a PR. Show configuration diffs before applying edits >
Bober_smart333,180 görüntüleme • 16 gün önce
It is becoming f*cking dangerous: The engineer behind Claude Code just advised users to wipe their CLAUDE.md file completely This is not a joke Boris Cherny, at YC: "Every six months, completely clear out your CLAUDE.md, strip away your custom skills, and remove your hooks. Let the model run fresh and you might be amazed by what happens" The logic behind it: Your previous prompt rules were written to cover up flaws in older system versions Fresh model releases no longer suffer from those exact limitations Keeping those legacy prompts around might actually degrade Claude's output quality today The step by step process: 1. Erase CLAUDE.md, along with all integrated skills and hooks 2. Go about your normal workflow and spot where the AI starts to drift off course 3. Bring back a single rule only when you notice a specific error recurring over and over 4. Execute this reset whenever a major model upgrade drops Things to keep: Essential safety protocols and strict compliance guidelines Non-obvious project quirks that cannot be inferred directly from reading code Things to trash: Directory layouts, lists of packages, and high-level architecture breakdowns Any information the AI can figure out on its own by analyzing your codebase While most developers keep adding more and more constraints, the creator of the tool is doing the exact opposite by cutting them down Add this to your bookmarks. I'm sure you're hearing about this for the first time
Bober_smart27,817 görüntüleme • 2 gün önce
A 24-year-old guy from Texas turned himself into Elon Musk and made $4,356 in 4 hours It all started as a joke, he launched a TikTok stream, but the result was unpredictable The costs amounted to $20 for Claude Claude changed his appearance in real time The audience loved the look so much that they started donating and sending gifts At the end of the stream, his balance was $4,356 Peak viewership reached 11,430 The stream gathered 186,580 likes He gained 65,000 new followers And the funniest thing is, everyone knew it was AI
Bober_smart2,461,491 görüntüleme • 4 ay önce
A 48-year-old girl from Britain decided to just make a joke, but in the end, she earned $2,245 in 4 hours With the help of Claude, she created a Chinese girl and started a stream Claude changed the appearance, background, voice, and even language in real time She started the stream on 3 platforms at once: YouTube, TikTok, and Kick Men liked the girl so much that they started donating > In 4 hours, she was donated $2,245 > The biggest donation was $400 The article contains 10 folders with tools for creation and workflow automation
Bober_smart1,909,074 görüntüleme • 4 ay önce
I still don't understand why everyone isn't doing this yet. Elon Musk reposted this guide, and using this exact agent setup, I made $9,300 just last week Eight Grok agents on the desk, costing $200 a month, service a trading floor that typically costs a crypto fund $500,000 a year in analyst salaries A 5 AM morning call. I don't participate in it How the agents are distributed: SEARCH: gathers real-time alpha, developer repositories on GitHub, and unindexed Telegram signals before CT finds them RISK: checks contract functions, minting rights, and LP locks, flagging honeypots before entry SNIPER: places high-speed orders on-chain at the exact millisecond the risk clearance passes WHALE: tracks smart money wallets and flags insider accumulation in real time. RUG: monitors developer wallet activity 24/7 and dumps the entire position if they touch the LP EXIT: dynamically trails stops, scaling out as liquidity accumulates SHILL: tracks social volume, impulse speed, and key influencer calls HEAD OF DESK: never trades, routes data, checks transmissions, and brings me the single decision that requires a human While I was sleeping, the system scanned 164 tokens, selected 21 qualifying setups, and executed 8 trades. The result: net profit of $9,300 (already after fees) Each agent has its own virtual browser, terminal, and local cloud memory. The trading floor remains active even when my laptop is closed Setup is easier than it seems: 1. Download Grok Bot and create your Head of Desk 2. Give the remaining 7 agents task descriptions as if you were instructing new employees 3. Run the workflow once on your screen while they observe 4. Connect Telegram and wallet webhooks No VPS, no code, no waiting for developers Crypto trading used to mean 16 hours in front of a screen, paid alpha groups, and constant fatigue. Mine took one evening to set up Save this before your next trade. Save the guide
Bober_smart378,467 görüntüleme • 1 ay önce
It is becoming f*cking dangerous: AI agents mapped out a full codebase based on just one question Jev creator Diogo Almeida put together a playbook to sync up 80 agents over 540,000 lines of code, creating a visual flow of the system architecture Simply ask: "What takes place when a user uploads a file?" and follow the full circuit from the frontend and API down to background jobs, databases, and tests Every element on the layout connects straight to the underlying codebase. Claude Code agents map out the underlying code. Jev directs tasks to the right workers and strips away irrelevant data for each investigation phase: > which specific component handles this functionality > which files need to be analyzed > is another worker currently handling this route > does this part require a deeper look The final blueprint charted 170 user flows and tied them to 2,400 tests. On top of that, 26 open points remained clearly flagged for manual review How to use it: Hand over the playbook along with your repo to Claude Code, then submit this prompt: Generate a searchable blueprint of this repository Run an audit on entry points, services, background tasks, and databases. Assign separate modules to different agents Map every user scenario through the codebase. Link file locations and key references to each step Rely on Jev to manage the workflow and filter out context noise. Set up dedicated agents to double-check proposed links against the raw code Connect existing tests to their respective flows. Flag assumed logic and incomplete paths, then build a UI to navigate the map A good approach is to run a trial on a single user path first before scaling it up to the full repository This way, any incoming developer can review a feature, trace its dependencies, and locate test cases prior to making a single change Bookmark this
Bober_smart12,374 görüntüleme • 2 gün önce
A 36-year-old girl from Detroit who has 3 kids asked Claude how to make money if you don't have time to do anything? He gave an answer and her monthly income amounted to $15,459 Claude + Shopify = automated dropshipping All her investment is a $20 Claude subscription Claude comes up with a niche for products by analyzing popular trends, creates clickable descriptions, generates photos and videos that stand out from the rest A person pays for the order -> Claude buys on Aliexpress 60-70% cheaper -> the package goes to the buyer In essence, this is a store managed by a manager instead of you, you just get the profit Earnings: Week 1 > $1,465 Week 2 > $2,657 Week 3 > $7,842 1 month > $15,459 The full instruction is already publicly available
Bober_smart385,996 görüntüleme • 4 ay önce
Girls, you need to worry, robots with AI might replace you soon She won't ask for money She never has a headache A guy from China bought himself a robot girlfriend and does everything with her that he would do with a real one Her whole body is covered in sensors, and her brain is AI. She can sustain any conversation and knows your desires precisely She cleans around the house and can even bring you coffee in the morning I'm sure the man has never regretted this purchase
Bober_smart178,459 görüntüleme • 2 ay önce
Soon, everyone will be doing this. Ever since I started using Grok agents, my income has jumped to $2,700 a day Set it up once and now I'm pulling in steady profits Here is how each agent operates: 1. SEARCH ➔ extracts real-time alpha before CT even catches wind: fresh GitHub repos, new pumpfun pools, and unindexed Telegram signals 2. RISK ➔ instantly audits contracts via rugcheck and solscan: strips away mint authority, freeze rights, and unlocked LP. Zero honeypots slip through 3. SNIPER ➔ fires lightning-fast DEX orders the exact millisecond RISK drops the CLEAR badge 4. WHALE ➔ tracks smart-money wallets with a 60%+ win rate, catching stealth accumulation long before it prints on the chart 5. RUG ➔ monitors dev wallets and LP status 24/7. The second there's a whiff of an LP pull, it dumps the entire position. 6. EXIT ➔ dynamically adjusts trailing stops and locks in profits as depth builds. Zero averaging down 7. SHILL ➔ scans X and Telegram to separate organic momentum from paid bot traffic 8. HEAD OF DESK ➔ never places a trade. Strictly runs coordination, enforces protocol, and brings me the single decision that matters: APPROVE Hundreds of tokens filtered out. Precision profit secured while the laptop stays shut Every single agent runs in its own cloud browser with local memory and a zero-ambiguity charter This isn't an 'assistant' anymore. It's a fully autonomous desk grinding while you sleep I recommend saving this
Bober_smart99,259 görüntüleme • 1 ay önce
HOLY SH*T! The person who leaked this online is a real freaking madman! Now everyone can get 800 million tokens for AI agents for free The OmniRoute repository is blowing up GitHub. It is a local high-performance AI gateway that combines free limits from dozens of providers into a single continuous API stream Project architecture and key technical specifications: Interface and Integration: Provides a single OpenAI-compatible API endpoint. Natively connects to Cursor, VS Code (via Copilot / Cline / Aider) Claude Code, and custom scripts Connection Scale: Supports 350+ providers and 90+ services with free limits (Google AI Studio, Groq, Cerebras, SambaNova, OpenRouter, GitHub Models, Mistral AI, etc.) 18 Routing Strategies & Auto-Fallback: Custom switching system. On a 429 Too Many Requests error or quota depletion, the gateway seamlessly redirects the request to the next model in the chain within milliseconds Dual Context Compression (RTK + Caveman): Built-in engines cut unnecessary logs, syntax, and message history by 15–95% saving token volume before sending the request Security (Local-first & 0 Telemetry): All API keys are locally encrypted using the AES-256-GCM algorithm. Data goes directly to providers, bypassing third-party clouds Agent Protocols (MCP & A2A): Full support for Model Context Protocol (MCP) and Agent-to-Agent architecture for automated model pool management Launch Options: CLI (npm), Docker container, Electron desktop app, and PWA
Bober_smart21,427 görüntüleme • 11 gün önce
Why is no one talking about this? Official Anthropic recommendation for Claude Code: stop wasting Opus 5.5 compute on tasks Haiku 5.5 can swarm, while Sonnet 5.5 handles core development. switch the architect model into standby using /advisor claude -> advisor opus -> subagents haiku Sonnet 5.5 powers the main workflow at maximum effort, drafting code changes and executing test suites Haiku 5.5 subagents index the repository in parallel at 340 tokens/sec, discovering files and reviewing technical documentation Opus 5.5 remains on standby as an expert consultant, stepping in only during three key scenarios: -> prior to committing to a strategy: does the blueprint lack authentication edge cases or schema rules? -> when a test fails repeatedly: are we tackling the root issue or wasting time in a rabbit hole? -> before marking the task complete: did recent diffs introduce silent bugs, and are baseline checks satisfied? Opus 5.5 assesses. Sonnet 5.5 builds. Haiku 5.5 executes concurrently Jev engineering applies this identical structure one level down: automated logic requiring zero reasoning (selecting files, invoking tools, retrying or cancelling) completes in 16ms, so heavy models trigger only when execution paths split Plan at max power. Delegate at mid power. Keep Opus on standby On-call Opus 5.5 inspects overall session history and catches deep structural flaws Lead Sonnet 5.5 performs edits, writes core logic, and manages test environments Haiku 5.5 subagents run AST parsing, grep queries, and API doc analysis concurrently JEV micro-fork layer processes 1,500+ routing rules in under 16ms Expert model stays silent during basic terminal commands to preserve context window Configure my Claude Code workspace for hierarchical advisor orchestration: 1. Verify ~/.claude/settings.json and project-level configs for model role alignment (main, subagents, and advisor) Set main session model: sonnet with high effort level for primary execution Set subagents model: haiku with effortLevel: medium for parallel file discovery and doc gathering Set advisor model: opus on call for high-level analysis 2. Turn on the advisor tool inside ~/.claude/settings.json: Define advisorModel as claude-opus-5-5 Enable subagent parallel dispatcher pool (3x workers) 3. Establish automatic advisor review checkpoints in ~/.claude/CLAUDE.md: Call /advisor opus prior to finalizing multi-file architectural changes Trigger /advisor opus automatically whenever the same compiler or test error happens twice Require an advisor diff contract audit prior to completing tasks or staging git commits 4. Restrict subagent execution boundaries: Haiku subagents must return only structured AST summaries and doc snippets without bloating the primary session context Display all configuration diffs before applying changes. Do not commit modifications until confirmed
Bober_smart17,513 görüntüleme • 9 gün önce
Jev model has been causing a sensation on GitHub ever since its release, and I am going to tell you about the best repositories that nobody is talking about How does this work: browser-use/browser-use - 32,500+ stars The core web automation library that houses the Jev integration ecosystem (including jev-ultrafast). It enables AI decision models to directly control web browser actions, click DOM elements, and automate complex workflows without heavy LLM latency langchain-ai/langchain - 98,500+ stars Integrates Jev as an ultra-fast model router, guardrail evaluator, and safety firewall. Jev evaluates task risk, intent, and complexity before passing execution to heavy LLMs LiteLLM/litellm - 59,200+ stars A lightweight proxy and routing library for LLMs. It features native Jev decision-model routing to classify incoming prompts and instantly direct requests to the cheapest or fastest model endpoint dify-ai/dify - 58,000+ stars An open-source LLM application development platform that incorporates Jev-style decision nodes for instant conditional branching and typed classification in multi-agent workflows vllm-project/vllm - 36,000+ stars A high-throughput LLM serving engine widely used for self-hosting custom decision-model checkpoints (such as Qwen3.5-based Jev fine-tunes) with ultra-low latency logits evaluation QwenLM/Qwen - 18,500+ stars The open base model family (Qwen3.5/3.8) used to train open-source Jev-like decision models (like Kev and RSI-Jev) powering typed probabilistic choices directly from custom model weights 🔗 You will definitely find what you need. I recommend adding this to your bookmarks
Bober_smart20,161 görüntüleme • 13 gün önce
I still can't wrap my head around why not everyone is using this approach yet. Elon Musk reposted this guide, and using this exact agent setup, I managed to make $7,250 just last week Eight Grok agents on the desktop cost $200 a month, but they replace a full trading floor, the maintenance of which typically costs a crypto fund $550,000 a year in analyst salaries A 5:30AM morning call. I don't participate in it How the agents are distributed: SEARCH: gathers real-time alpha, developer repositories on GitHub, and unindexed Telegram signals before CT finds them RISK: checks contract functions, minting rights, and LP locks, flagging honeypots before entry SNIPER: places high-speed orders on-chain at the exact millisecond the risk clearance passes WHALE: tracks smart money wallets and flags insider accumulation in real time RUG: monitors developer wallet activity 24/7 and dumps the entire position if they touch the LP EXIT: dynamically trails stops, scaling out as liquidity accumulates SHILL: tracks social volume, impulse speed, and key influencer calls HEAD OF DESK: never trades, routes data, checks transmissions, and brings me the single decision that requires a human. While I was sleeping, the system scanned 143 tokens, selected 15 qualifying setups, and executed 8 trades. The result: net profit of $7,250 (already after fees). Each agent has its own virtual browser, terminal, and local cloud memory, and the trading floor remains active even when my laptop is closed Setup is easier than it seems: 1. Download Grok Bot and create your Head of Desk 2. Give the remaining 7 agents task descriptions as if you were instructing new employees 3. Run the workflow once on your screen while they observe 4. Connect Telegram and wallet webhooks No VPS, no code, no waiting for developers. Crypto trading used to mean 16 hours in front of a screen, paid alpha groups, and constant fatigue. Mine took one evening to set up Save this guide before your next trade
Bober_smart56,509 görüntüleme • 1 ay önce
What they stay silent about so you keep burning through your Claude limits > JEV savings and automation The ideal plan: Claude only writes. Jev makes decisions, code executes actions, and every step is correct Where to start: AGENTS.md > when to use Jev, when not to use it state/build_state.py > goal, task, workers, completed, missing, constraint, evidence, pending Jev decides (questions/) > selects the model power level for the task next_worker.py > passes the baton to the next worker > filters out garbage: selects only useful tool output > verifies the real result, not just the execution status > blocks dangerous actions (payments, data transmission, etc) Code acts (rules/) hard_rules.py > a 10-step limit and a strict ban on publishing raw content. thresholds.yaml > execution only upon high confidence; for critical/risky operations, the threshold is 0.95 Claude writes (workers/) > source collection and working notes. > preparation of drafts and briefs. The only zone in the system where text generation happens Proof receipts/decisions.jsonl > decision log: candidates, selected ID, validation results, and fallback scenario. evals/ > a dataset of dozens of personal traces used to calibrate all thresholds Guard (hooks/) pre_tool_use.sh > validation of each command strictly before execution. > final checklist: verifies readiness criteria before stopping the agent 10,000 decisions for just $0.42 at an average speed of 300 ms Division of labor: LLM creates content, Jev makes decisions, code executes Using this is a genuinely smart move. Save it so you don't lose it
Bober_smart22,059 görüntüleme • 15 gün önce
A 25-year-old guy from Brazil transformed into a girl and earned $3,270 in 4 hours It all started as a prank; he started a stream on TikTok, but the result turned out to be unpredictable AI expenses totaled $20 Claude changed his appearance and voice in real-time The viewers liked this image so much that they started sending donations and gifts At the end of the broadcast, his balance was $3,270 The peak number of viewers was 40,000 The broadcast gobbled up 2.5 million likes He gained 23,548 new followers Want a joke? Everyone knew it was AI
Bober_smart115,626 görüntüleme • 3 ay önce