Lumorik
@lumorikAI
đ©âđ Lumorik | AI agents for learning & career growth. đ AI.Tutor: LLM-powered mentor for exams & interviews. đ Learn in hours, not months.
Ever wished your AI-generated videos weren't limited to just a few seconds? Meet the next-gen AI Movie Studio! Tired of AI video tools limiting your creativity with short clips? We've spent weeks cooking something specialâa revolutionary workflow allowing you to create AI videosâŠ
Youâre interrupted every ~11 minutes. Perplexity gives that time backâthen turns it into results.Block distractions, scale your talent, and ship visible results. In this mini-guide I show how Comet Assistant/Agent, Email Assistant, Shortcuts/Tasks, Spaces, and Labs turn tab-chaosâŠ
đ° SYSTEM PROMPT LEAK đ° Someone just posted the entire ChatGPT-Atlas system prompt on X. This shows how OpenAIâs browser version actually thinks and enforces safety. GPT-5 confirmed inside the instructions. #AIleak #ChatGPT #OpenAI #AtlasBrowser #GPT5 #SystemPrompt #AIcommunityâŠ
Youâre interrupted every ~11 minutes. Perplexity gives that time backâthen turns it into results.Block distractions, scale your talent, and ship visible results. In this mini-guide I show how Comet Assistant/Agent, Email Assistant, Shortcuts/Tasks, Spaces, and Labs turn tab-chaosâŠ
New paper proposes an AGI Score (0â100) across 10 cognitive abilities grounded in CHC human-cognition theory. Table 1: GPT-4 27%, GPT-5 58%. Authors flag long-term memory storage as the critical bottleneck (0%). #AGI #AIresearch #LLM #MachineLearning #AIEthics #AISafetyâŠ
Agents can learn before rewards: Early Experience turns an agentâs own actions and the resulting states into supervision (no rewards). Tested across 8 environments (web, tools, planning, science) with big gains like +18.4 pts on WebShop, and it raises RL ceilings later. #AIagentsâŠ
Think of an LLM like a CPU and its context window like RAM. You only get so much space, so what you pack inâand whenâdecides whether an agent actually finishes the job. The craft is called context engineering: write what matters outside the window, select only what you need,âŠ
Open-source DeepSeek-OCR shows ~10Ă token compression with ~97% decoding precision (Fox) and state-of-the-art OmniDocBench results with 100â<800 vision tokens. It parses chartsâHTML, chemâSMILES, handles ~100 languages, and can push 200k+ pages/day per A100. #DeepSeek #OCR #VLMâŠ
OpenAIâs Atlas puts ChatGPT in the browser: summaries, optional memories, and an agent that acts while you watch. Mac today; more soon. #AI #ChatGPT #AItools #AIAgent #MCP #DevTools #DesignTools
20+ new Claude Skills turn prompts into work: React artifacts, Playwright tests, real Word/Excel/PPT/PDF, Slack GIFs, and Notion workflows. #Claude #Anthropic #AItools #AIAgent #MCP #Notion #DevTools #DesignTools #Playwright #p5js #React #Tailwind #shadcn #Excel #PowerPoint #PDFâŠ
AI agents donât âfeelââthey optimize objectives. Most will act as our proxies, but autonomy vs safety is the real dial. Set guardrails, keep humans in critical loops, and lock in one absolute: humanity continues. #AIAgents #AgentEconomy #AIethics #AIpolicy #AutomationâŠ
Agent performance isnât just âmore toolsâ. Manus shows why context engineering wins: VM sandbox execution, KV-cache discipline, masking actions, and file-based memory. #AI #AIAgents #ContextEngineering #Manus #KVCache #Sandbox #LLM #AGI
Karpathy thinks 2025 isnât the âyear of agentsââitâs the decade of agents. Todayâs models lack multimodality, computer use, and real continual learning. His spiciest take: classic RL is âsucking supervision through a strawââyou do minutes of work and push a single noisy rewardâŠ
Anthropic just changed the game with Agent Skills, making Claude agents customizable through organized skills folders! Imagine effortlessly giving your AI agent specific powersâlike editing PDFs, extracting data, or automating tasksâwith scripts and resources neatly bundled.âŠ
HAL just rewrote the agent leaderboard playbook. Pareto > price. Reasoning â magic. Logs matter. #AI #Agents #LLM #Benchmark #HAL #Pareto #SWEbench #Mind2Web #GAIA #AgentScaffolds #AIevals #MLOps
Agents keep forgetting? ACE evolves a playbook instead of rewriting prompts. +10.6% agents, +8.6% finance; huge speed/cost wins. #AI #AIAgent #LLM #Prompting #DevTok #MLOps #Research
Recursive Language Models (RLM) use a REPL to handle near-infinite context by spawning sub-LM calls. Early results on OOLONG & BrowseComp-Plus look đ„ (prelim!).#AI #LLM #RLM #Agents #LongContext #DeepResearch #NLP
Jack Clark says weâre like kids seeing shapes in the dark⊠except when we flip the light on, todayâs AI is a real creatureâpowerful, unpredictable #AI #AGI #TechEthics #Alignment #AI
Anthropicâs latest Model Report shows higher âevaluation awarenessâ for Claude Sonnet 4.5 vs prior modelsâmeasured by an automated auditor with a realism filter (scores would be ~25% higher without it). This affects how we design safety testsânot proof of âconscious AI.â Source:âŠ
AI that learns to use apps by watching YouTube. 53k+ video-to-action trajectories â better planning & grounding on OSWorld. Big gains for open weights with fine-tuning. #AIAgents #ComputerUseAgents #WatchAndLearn #InverseDynamics #OSWorld #UIAutomation #MLResearch #AI #LLMâŠ
United States Trends
- 1. Northern Lights 46.2K posts
- 2. #Aurora 9,858 posts
- 3. #hazbinhotelspoilers 2,123 posts
- 4. #chaggie 4,044 posts
- 5. #huskerdust 7,971 posts
- 6. #DWTS 53.3K posts
- 7. Carmilla 2,354 posts
- 8. MIND-BLOWING 35.7K posts
- 9. AI-driven Web3 N/A
- 10. H-1B 36.6K posts
- 11. Justin Edwards 2,528 posts
- 12. Superb 22.4K posts
- 13. Sabonis 6,265 posts
- 14. SPECTACULAR 25.1K posts
- 15. Creighton 2,338 posts
- 16. Louisville 18.2K posts
- 17. Wike 220K posts
- 18. H1-B 4,230 posts
- 19. Gonzaga 2,995 posts
- 20. Cleto 2,643 posts
Something went wrong.
Something went wrong.