[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.] #  @omarsar0 elvis elvis posts on X about context engineering, devs, agentic, context window the most. They currently have XXXXXXX followers and XX posts still getting attention that total XXXXXXX engagements in the last XX hours. ### Engagements: XXXXXXX [#](/creator/twitter::3448284313/interactions)  - X Week XXXXXXX -XX% - X Month XXXXXXXXX +8.80% - X Months XXXXXXXXXX +84% - X Year XXXXXXXXXX +104% ### Mentions: XX [#](/creator/twitter::3448284313/posts_active)  - X Month XXX +46% - X Months XXX +27% - X Year XXX +188% ### Followers: XXXXXXX [#](/creator/twitter::3448284313/followers)  - X Week XXXXXXX +0.37% - X Month XXXXXXX +1.90% - X Months XXXXXXX +14% - X Year XXXXXXX +29% ### CreatorRank: XXXXXX [#](/creator/twitter::3448284313/influencer_rank)  ### Social Influence [#](/creator/twitter::3448284313/influence) --- **Social category influence** [musicians](/list/musicians) #1017 [finance](/list/finance) XXX% [technology brands](/list/technology-brands) XXX% [stocks](/list/stocks) XXXX% [celebrities](/list/celebrities) XXXX% **Social topic influence** [context engineering](/topic/context-engineering) #1, [devs](/topic/devs) #150, [agentic](/topic/agentic) #27, [context window](/topic/context-window) 4.6%, [leaderboard](/topic/leaderboard) #1, [llm](/topic/llm) 3.45%, [capabilities](/topic/capabilities) #40, [xai](/topic/xai) 2.3%, [inference](/topic/inference) 2.3%, [investment](/topic/investment) XXXX% **Top accounts mentioned or mentioned by** [@officiallogank](/creator/undefined) [@trakintelai](/creator/undefined) [@ptkbhv](/creator/undefined) [@rungalileo](/creator/undefined) [@dairai](/creator/undefined) [@windsurfai](/creator/undefined) [@anthropicai](/creator/undefined) [@elonmusk](/creator/undefined) [@xai](/creator/undefined) [@llmsan](/creator/undefined) [@russelljkaplan](/creator/undefined) [@robertnishihara](/creator/undefined) [@skirano](/creator/undefined) [@jaisurya](/creator/undefined) [@mohansolo](/creator/undefined) [@michelivan92347](/creator/undefined) [@alessiocarra_](/creator/undefined) [@raphtimez](/creator/undefined) [@abovethegenes](/creator/undefined) [@ai_codedream](/creator/undefined) **Top assets mentioned** [Alphabet Inc Class A (GOOGL)](/topic/$googl) ### Top Social Posts [#](/creator/twitter::3448284313/posts) --- Top posts by engagements in the last XX hours "@rungalileo introduces Agent Leaderboard v2 a domain-specific evaluation benchmark for AI agents designed to simulate real enterprise tasks across banking healthcare insurance telecom and investment"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1945956445792411754) 2025-07-17 21:19:05 UTC 255K followers, 8757 engagements "Grok X on Vending Bench Grok X gets the #1 spot. Double the net worth of Claude Opus 4"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1943170235789398331) 2025-07-10 04:47:41 UTC 254.9K followers, 41.4K engagements "All about building with AI agents in the next couple of weeks @dair_ai Academy. Particularly excited to share more on reasoning models context engineering for AI agents Agentic CLI tools (Claude Code and Gemini CLI) and ambient AI agents. Good vibes and great builders"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1945871518392623598) 2025-07-17 15:41:37 UTC 254.9K followers, 5457 engagements "Unified AI Agents are here ChatGPT agent unifies tools for deep research computer use and more. Be careful how you use these agents. The guardrails are not optional; they are the killer feature of this new wave of unified AI agents"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1945918896948568209) 2025-07-17 18:49:53 UTC 254.8K followers, 5005 engagements "AI Research Agents for ML Achieves state-of-the-art on MLE-bench lite Using AI to automate the training of ML models is one of the most exciting and promising areas of research today. Lots of cool ideas in this paper:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1942235421607682317) 2025-07-07 14:53:04 UTC 255K followers, 41.2K engagements "Anthropic is killing it with these technical posts. If you're an AI dev stop what you are doing and go read this. It shows in great detail how to implement an effective multi-agent research system. Pay attention to these key parts:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1933941545675206936) 2025-06-14 17:36:10 UTC 254.9K followers, 570.1K engagements "Grok X is the single-agent version. Grok X Heavy is the multi-agent version. Multi-agent systems are no joke"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1943164926953947471) 2025-07-10 04:26:35 UTC 254.6K followers, 45.9K engagements "Agent Leaderboard v2 is here GPT-4.1 leads Gemini-2.5-flash excels at tool selection Kimi K2 is the top open-source model Grok X falls short Reasoning models lag behind No single model dominates all domains More below:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1945956442785083895) 2025-07-17 21:19:04 UTC 255K followers, 248.9K engagements "Agentic RAG for Personalized Recommendation This is a really good example of integrating agentic reasoning into RAG. Leads to better personalization and improved recommendations. Here are my notes:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1941957079331377475) 2025-07-06 20:27:02 UTC 255K followers, 92.2K engagements "Notes for Grok X anouncement. Lot to unpack but this summary contains the most important bits. (Bookmark it)"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1943316673047507246) 2025-07-10 14:29:34 UTC 254.7K followers, 29.8K engagements "Context engineering components include context retrieval and generation context processing context management and how they are all integrated into systems implementation such as RAG memory architectures tool-integrated reasoning and multi-agent coordination mechanisms"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1946241627582054854) 2025-07-18 16:12:18 UTC 255K followers, 2840 engagements "Gemini CLI with MCP servers is a match made in heaven It's amazing for coding use cases. But it's also great at other creative tasks like transcribing and writing. Just watch to see what I am talking about:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1942418143609033115) 2025-07-08 02:59:08 UTC 255K followers, 52.8K engagements "Multi-conversation RL training (Multi-Conv DAPO) Unlike standard RL pipelines MemAgent generates multiple independent memory-update conversations per input. It uses a modified GRPO objective to optimize all steps via final-answer reward signals"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1942667317474910248) 2025-07-08 19:29:16 UTC 254.9K followers, 2039 engagements "Overview Investigates the surprising fragility of LLM-based reward models used in Reinforcement Learning with Verifiable Rewards (RLVR). The authors find that inserting superficial semantically empty tokens like Thought process: Solution or even just a colon : can consistently trick models into giving false positive rewards regardless of the actual correctness of the response"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1944778190695940448) 2025-07-14 15:17:07 UTC 254.7K followers, 2730 engagements "BREAKING: xAI announces Grok X "It can reason at a superhuman level" Here is everything you need to know:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1943162144930828397) 2025-07-10 04:15:32 UTC 255K followers, 1.3M engagements "Grok X models are available via the xAI API. 256K context window. Real-time data search"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1943170665005134308) 2025-07-10 04:49:23 UTC 254.9K followers, 27.5K engagements "Top XX LLM Interview Questions. Looks like a great resource to learn LLM basics:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1930984834454712537) 2025-06-06 13:47:15 UTC 254.9K followers, 354.6K engagements "Inference-time tricks fail to help CoT prompting and majority voting do not reliably reduce vulnerability and sometimes make FPR worse especially for Qwen models on math tasks. LLMs continue to show all kinds of weird vulnerabilities and this is just one of the latest results to be published. This highlights the importance of building robust LLM-based evaluation strategies. Paper:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1944778251064496579) 2025-07-14 15:17:21 UTC 254.8K followers, 4793 engagements "MemAgent MemAgent-14B is trained on 32K-length documents with an 8K context window. Achieves XX% accuracy even at 3.5M tokens That consistency is crazy Here are my notes:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1942667308368871457) 2025-07-08 19:29:13 UTC 255K followers, 100K engagements "Stress Testing Large Reasoning Models This looks like a more interesting way to evaluate large reasoning models. Presents multiple reasoning problems in a single prompt to better represent real-world scenarios. Which are the best models at this Here are my notes:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1945150414195974448) 2025-07-15 15:56:12 UTC 255K followers, 14.9K engagements "The Illusion of Thinking in LLMs Apple researchers discuss the strengths and limitations of reasoning models. Apparently reasoning models "collapse" beyond certain task complexities. Lots of important insights on this one. (bookmark it) Here are my notes:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1931333830985883888) 2025-06-07 12:54:02 UTC 255K followers, 953.4K engagements "RL-shaped fixed-length memory MemAgent reads documents in segments and maintains a fixed-size memory updated via an overwrite mechanism. This lets it process arbitrarily long inputs with O(N) inference cost while avoiding context window overflows"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1942667314530295984) 2025-07-08 19:29:15 UTC 254.9K followers, 1752 engagements "Excited to announce my new short course: Building Agentic Applications with Replit Agent and n8n. With AI this capable I believe anyone can become a builder. The stack I use here will teach you how to rapidly build agentic apps with no-code tools"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1943410079199629470) 2025-07-10 20:40:44 UTC 255K followers, 41K engagements "@llm_san Don't think there was any mention of compute requirements but you might find something in the GitHub repo: Also I think without GPUs it might be extremely slow which could still be useful for some applications but very limited IMO"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1945867175228543244) 2025-07-17 15:24:21 UTC 255K followers, XXX engagements "A Survey of Latent Reasoning Nice overview on the emerging field of latent reasoning. Great read for AI devs. (bookmark it)"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1942976772724695513) 2025-07-09 15:58:56 UTC 255K followers, 72.3K engagements "Evaluating LLM-based Agents This report has a comprehensive list of methods for evaluating AI Agents. Don't ignore evals. If done right they are a game-changer. Highly recommend it to AI devs. (bookmark it)"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1939691782477902313) 2025-06-30 14:25:33 UTC 255K followers, 95.6K engagements "YC on the key prompting techniques used by the best AI startups:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1928562249297211600) 2025-05-30 21:20:45 UTC 255K followers, 665.3K engagements "One Token to Fool LLM-as-a-Judge Watch out for this one devs Semantically empty tokens like Thought process: Solution or even just a colon : can consistently trick models into giving false positive rewards. Here are my notes:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1944778174493343771) 2025-07-14 15:17:03 UTC 255K followers, 79K engagements "Context engineering is going to evolve rapidly. But this is a great overview to better map and keep track of this rapidly evolving landscape. There is a lot more in the paper. Over 1000+ references included. This survey tries to capture the most common methods and biggest trends but there is more on the horizon as models continue to improve in capability and new agent architectures emerge"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1946241716467716455) 2025-07-18 16:12:39 UTC 255K followers, 4788 engagements "Strong long-context extrapolation Despite being trained on 32K-length documents with an 8K context window MemAgent-14B achieves XX% accuracy even at 3.5M tokens outperforming baselines like Qwen2.5 and DeepSeek which degrade severely beyond 112K tokens"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1942667321023103057) 2025-07-08 19:29:17 UTC 255K followers, 4842 engagements "I started to experiment with Grok X and I already found some interesting things about it. I'm preparing a detailed comparison with other reasoning models. I will be hosting a workshop on Grok X for our academy members soon:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1943303408175267903) 2025-07-10 13:36:51 UTC 254.8K followers, 12.9K engagements "@russelljkaplan I think it was a great acquisition. I love the Windsurf brand and there are some really talented folks there. I think this is a win-win situation"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1944887683953910244) 2025-07-14 22:32:12 UTC 254.6K followers, 2911 engagements "The paper provides a taxonomy of context engineering in LLMs categorized into foundational components system implementations evaluation methodologies and future directions"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1946241581415272904) 2025-07-18 16:12:07 UTC 255K followers, 3637 engagements "Great work from the team. I care about efficiency in my work. GPT-4.1-mini being a lot cheaper and performant at the same time is exciting. The fact that GPT-4.1 tops the leaderboard for now makes a lot of sense as it is one of the top models for instruction following which is a key capability in building agents with superior tool calling. Perhaps the reasoning models weren't great but I think they can only get better at tool calling so it will be interesting to track how the leaderboard progresses as new reasoning models roll out. Kimi K2 is such an exciting open-source release. It packs a"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1945964232752713932) 2025-07-17 21:50:02 UTC 255K followers, 10.3K engagements "A Survey of Context Engineering 160+ pages covering the most important research around context engineering for LLMs. This is a must-read Here are my notes:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1946241565728600503) 2025-07-18 16:12:03 UTC 255K followers, 104.2K engagements "A Survey of AI Agent Protocols X things that stood out to me about this report:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1918723145923453022) 2025-05-03 17:43:40 UTC 254.8K followers, 208.2K engagements "AI for Scientific Search AI for Science is where I spend most of my time exploring with AI agents. This 120+ pages report does a good job of highlighting why all the big names like OpenAI and Google DeepMind are pursuing AI4Science. Bookmark it My notes below:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1940787135596187970) 2025-07-03 14:58:05 UTC 255K followers, 61.4K engagements "@robertnishihara Search for AI agents is one of my favorite problems to work on and think about. It really pushes you to think beyond the basics of context engineering"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1945209445476176293) 2025-07-15 19:50:46 UTC 254.9K followers, 1341 engagements "Future of Work with AI Agents Stanford's new report analyzes what 1500 workers think about working with AI Agents. What types of AI Agents should we build A few surprises Let's take a closer look:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1936134951520682123) 2025-06-20 18:51:58 UTC 255K followers, 300.6K engagements "Mitigation via adversarial augmentation The authors create "Master-RM" a new reward model trained with 20k synthetic negative samples (responses consisting of only reasoning openers). This model generalizes robustly achieving near-zero FPR across five benchmarks while still agreeing XX% with GPT-4o on meaningful judgments"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1944778235671416863) 2025-07-14 15:17:18 UTC 254.8K followers, 5066 engagements "What comes after Cursor This new agentic IDE Kiro offers a glimpse at that future. Kiro comes with all the fun features in an agentic IDE deliberate planning and leverages ambient agents that autonmously collaborate with devs as they build production-grade systems"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1945134066551980278) 2025-07-15 14:51:14 UTC 255K followers, 46.4K engagements "Agentic-R1 This 7B model is surprisingly good at interleaved tool use and reasoning capabilities. It's fun to see small language models improving this fast. Knowledge distillation in full display. Here are my notes:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1945863581918257591) 2025-07-17 15:10:04 UTC 255K followers, 55.6K engagements "LLMs Get Lost in Multi-turn Conversation The cat is out of the bag. Pay attention devs. This is one of the most common issues when building with LLMs today. Glad there is now paper to share insights. Here are my notes:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1922755721428598988) 2025-05-14 20:47:41 UTC 254.8K followers, 758.8K engagements "The work distinguishes prompt engineering from context engineering on dimensions like state scalability error analysis complexity etc"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1946241611903762897) 2025-07-18 16:12:14 UTC 255K followers, 2917 engagements "Tool-calling capabilities in an area of continuous development in the space. The paper provides an overview of tool-augmented language model architectures and how they compare across tool categories"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1946241703893189017) 2025-07-18 16:12:36 UTC 255K followers, 2050 engagements "This handbook is so good It covers *everything* you need to know about LLM inference. FREE to access:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1943727674637033601) 2025-07-11 17:42:45 UTC 255K followers, 85.2K engagements "Much is being said about context engineering but I want to focus on building. Find the full guide here: I am also hosting a workshop on "Context Engineering for AI Agents" for our academy pro members:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1941566134911963231) 2025-07-05 18:33:33 UTC 254.8K followers, 16.3K engagements "Small Language Models are the Future of Agentic AI Lots to gain from building agentic systems with small language models. Capabilities are increasing rapidly AI devs should be exploring SLMs. Here are my notes:"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1940038438746718698) 2025-07-01 13:23:02 UTC 255K followers, 266.8K engagements "Context Engineering Guide I'm writing a detailed guide on context engineering for AI devs. v1 is out now (bookmark it) I use a concrete deep research multi-agent example to show what context engineering involves"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1941566132001153082) 2025-07-05 18:33:33 UTC 255K followers, 286.1K engagements "Elon claims that Grok X is smarter than almost all grad students in all disciplines simultaneously. 100x more training than Grok X. 10x more compute on RL than any of the models out there"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1943162147401310241) 2025-07-10 04:15:32 UTC 255K followers, 123.8K engagements ""Master keys" break LLM judges Simple generic lead-ins (e.g. Lets solve this step by step) and even punctuation marks can elicit false YES judgments from top reward models. This manipulation works across models (GPT-4o Claude-4 Qwen2.5 etc.) tasks (math and general reasoning) and prompt formats reaching up to XX% false positive rates in some cases"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1944778206504231201) 2025-07-14 15:17:11 UTC 254.7K followers, 2345 engagements "Overview Introduces an RLdriven memory agent that enables transformer-based LLMs to handle documents up to XXX million tokens with near lossless performance linear complexity and no architectural modifications"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1942667311401558372) 2025-07-08 19:29:14 UTC 254.9K followers, 1963 engagements "Context Engineering Guide is now part of the Prompt Engineering Guide. 🔥 Nicer format. We've also been writing guides on other fire topics such as deep research reasoning LLMs and image generation. I will be expanding the guide further in the coming days. Stay tuned"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1942581621171105820) 2025-07-08 13:48:44 UTC 255K followers, 35.7K engagements "The context engineering evolution timeline from 2020 to 2025 involves foundational RAG systems to complex multi-agent architectures"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1946241597148123515) 2025-07-18 16:12:10 UTC 255K followers, 3504 engagements "You can read the full paper below: Want to take it a step further Learn about context engineering and how to build effective agentic systems in my courses: We also have a workshop on context engineering coming soon"  [@omarsar0](/creator/x/omarsar0) on [X](/post/tweet/1946241728316653990) 2025-07-18 16:12:42 UTC 255K followers, 4886 engagements
[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]
@omarsar0 elvis
elvis posts on X about context engineering, devs, agentic, context window the most. They currently have XXXXXXX followers and XX posts still getting attention that total XXXXXXX engagements in the last XX hours.
Engagements: XXXXXXX #
- X Week XXXXXXX -XX%
- X Month XXXXXXXXX +8.80%
- X Months XXXXXXXXXX +84%
- X Year XXXXXXXXXX +104%
Mentions: XX #
- X Month XXX +46%
- X Months XXX +27%
- X Year XXX +188%
Followers: XXXXXXX #
- X Week XXXXXXX +0.37%
- X Month XXXXXXX +1.90%
- X Months XXXXXXX +14%
- X Year XXXXXXX +29%
CreatorRank: XXXXXX #
Social Influence #
Social category influence musicians #1017 finance XXX% technology brands XXX% stocks XXXX% celebrities XXXX%
Social topic influence context engineering #1, devs #150, agentic #27, context window 4.6%, leaderboard #1, llm 3.45%, capabilities #40, xai 2.3%, inference 2.3%, investment XXXX%
Top accounts mentioned or mentioned by @officiallogank @trakintelai @ptkbhv @rungalileo @dairai @windsurfai @anthropicai @elonmusk @xai @llmsan @russelljkaplan @robertnishihara @skirano @jaisurya @mohansolo @michelivan92347 @alessiocarra_ @raphtimez @abovethegenes @ai_codedream
Top assets mentioned Alphabet Inc Class A (GOOGL)
Top Social Posts #
Top posts by engagements in the last XX hours
"@rungalileo introduces Agent Leaderboard v2 a domain-specific evaluation benchmark for AI agents designed to simulate real enterprise tasks across banking healthcare insurance telecom and investment"
@omarsar0 on X 2025-07-17 21:19:05 UTC 255K followers, 8757 engagements
"Grok X on Vending Bench Grok X gets the #1 spot. Double the net worth of Claude Opus 4" @omarsar0 on X 2025-07-10 04:47:41 UTC 254.9K followers, 41.4K engagements
"All about building with AI agents in the next couple of weeks @dair_ai Academy. Particularly excited to share more on reasoning models context engineering for AI agents Agentic CLI tools (Claude Code and Gemini CLI) and ambient AI agents. Good vibes and great builders" @omarsar0 on X 2025-07-17 15:41:37 UTC 254.9K followers, 5457 engagements
"Unified AI Agents are here ChatGPT agent unifies tools for deep research computer use and more. Be careful how you use these agents. The guardrails are not optional; they are the killer feature of this new wave of unified AI agents" @omarsar0 on X 2025-07-17 18:49:53 UTC 254.8K followers, 5005 engagements
"AI Research Agents for ML Achieves state-of-the-art on MLE-bench lite Using AI to automate the training of ML models is one of the most exciting and promising areas of research today. Lots of cool ideas in this paper:" @omarsar0 on X 2025-07-07 14:53:04 UTC 255K followers, 41.2K engagements
"Anthropic is killing it with these technical posts. If you're an AI dev stop what you are doing and go read this. It shows in great detail how to implement an effective multi-agent research system. Pay attention to these key parts:" @omarsar0 on X 2025-06-14 17:36:10 UTC 254.9K followers, 570.1K engagements
"Grok X is the single-agent version. Grok X Heavy is the multi-agent version. Multi-agent systems are no joke" @omarsar0 on X 2025-07-10 04:26:35 UTC 254.6K followers, 45.9K engagements
"Agent Leaderboard v2 is here GPT-4.1 leads Gemini-2.5-flash excels at tool selection Kimi K2 is the top open-source model Grok X falls short Reasoning models lag behind No single model dominates all domains More below:" @omarsar0 on X 2025-07-17 21:19:04 UTC 255K followers, 248.9K engagements
"Agentic RAG for Personalized Recommendation This is a really good example of integrating agentic reasoning into RAG. Leads to better personalization and improved recommendations. Here are my notes:" @omarsar0 on X 2025-07-06 20:27:02 UTC 255K followers, 92.2K engagements
"Notes for Grok X anouncement. Lot to unpack but this summary contains the most important bits. (Bookmark it)" @omarsar0 on X 2025-07-10 14:29:34 UTC 254.7K followers, 29.8K engagements
"Context engineering components include context retrieval and generation context processing context management and how they are all integrated into systems implementation such as RAG memory architectures tool-integrated reasoning and multi-agent coordination mechanisms" @omarsar0 on X 2025-07-18 16:12:18 UTC 255K followers, 2840 engagements
"Gemini CLI with MCP servers is a match made in heaven It's amazing for coding use cases. But it's also great at other creative tasks like transcribing and writing. Just watch to see what I am talking about:" @omarsar0 on X 2025-07-08 02:59:08 UTC 255K followers, 52.8K engagements
"Multi-conversation RL training (Multi-Conv DAPO) Unlike standard RL pipelines MemAgent generates multiple independent memory-update conversations per input. It uses a modified GRPO objective to optimize all steps via final-answer reward signals" @omarsar0 on X 2025-07-08 19:29:16 UTC 254.9K followers, 2039 engagements
"Overview Investigates the surprising fragility of LLM-based reward models used in Reinforcement Learning with Verifiable Rewards (RLVR). The authors find that inserting superficial semantically empty tokens like Thought process: Solution or even just a colon : can consistently trick models into giving false positive rewards regardless of the actual correctness of the response" @omarsar0 on X 2025-07-14 15:17:07 UTC 254.7K followers, 2730 engagements
"BREAKING: xAI announces Grok X "It can reason at a superhuman level" Here is everything you need to know:" @omarsar0 on X 2025-07-10 04:15:32 UTC 255K followers, 1.3M engagements
"Grok X models are available via the xAI API. 256K context window. Real-time data search" @omarsar0 on X 2025-07-10 04:49:23 UTC 254.9K followers, 27.5K engagements
"Top XX LLM Interview Questions. Looks like a great resource to learn LLM basics:" @omarsar0 on X 2025-06-06 13:47:15 UTC 254.9K followers, 354.6K engagements
"Inference-time tricks fail to help CoT prompting and majority voting do not reliably reduce vulnerability and sometimes make FPR worse especially for Qwen models on math tasks. LLMs continue to show all kinds of weird vulnerabilities and this is just one of the latest results to be published. This highlights the importance of building robust LLM-based evaluation strategies. Paper:" @omarsar0 on X 2025-07-14 15:17:21 UTC 254.8K followers, 4793 engagements
"MemAgent MemAgent-14B is trained on 32K-length documents with an 8K context window. Achieves XX% accuracy even at 3.5M tokens That consistency is crazy Here are my notes:" @omarsar0 on X 2025-07-08 19:29:13 UTC 255K followers, 100K engagements
"Stress Testing Large Reasoning Models This looks like a more interesting way to evaluate large reasoning models. Presents multiple reasoning problems in a single prompt to better represent real-world scenarios. Which are the best models at this Here are my notes:" @omarsar0 on X 2025-07-15 15:56:12 UTC 255K followers, 14.9K engagements
"The Illusion of Thinking in LLMs Apple researchers discuss the strengths and limitations of reasoning models. Apparently reasoning models "collapse" beyond certain task complexities. Lots of important insights on this one. (bookmark it) Here are my notes:" @omarsar0 on X 2025-06-07 12:54:02 UTC 255K followers, 953.4K engagements
"RL-shaped fixed-length memory MemAgent reads documents in segments and maintains a fixed-size memory updated via an overwrite mechanism. This lets it process arbitrarily long inputs with O(N) inference cost while avoiding context window overflows" @omarsar0 on X 2025-07-08 19:29:15 UTC 254.9K followers, 1752 engagements
"Excited to announce my new short course: Building Agentic Applications with Replit Agent and n8n. With AI this capable I believe anyone can become a builder. The stack I use here will teach you how to rapidly build agentic apps with no-code tools" @omarsar0 on X 2025-07-10 20:40:44 UTC 255K followers, 41K engagements
"@llm_san Don't think there was any mention of compute requirements but you might find something in the GitHub repo: Also I think without GPUs it might be extremely slow which could still be useful for some applications but very limited IMO" @omarsar0 on X 2025-07-17 15:24:21 UTC 255K followers, XXX engagements
"A Survey of Latent Reasoning Nice overview on the emerging field of latent reasoning. Great read for AI devs. (bookmark it)" @omarsar0 on X 2025-07-09 15:58:56 UTC 255K followers, 72.3K engagements
"Evaluating LLM-based Agents This report has a comprehensive list of methods for evaluating AI Agents. Don't ignore evals. If done right they are a game-changer. Highly recommend it to AI devs. (bookmark it)" @omarsar0 on X 2025-06-30 14:25:33 UTC 255K followers, 95.6K engagements
"YC on the key prompting techniques used by the best AI startups:" @omarsar0 on X 2025-05-30 21:20:45 UTC 255K followers, 665.3K engagements
"One Token to Fool LLM-as-a-Judge Watch out for this one devs Semantically empty tokens like Thought process: Solution or even just a colon : can consistently trick models into giving false positive rewards. Here are my notes:" @omarsar0 on X 2025-07-14 15:17:03 UTC 255K followers, 79K engagements
"Context engineering is going to evolve rapidly. But this is a great overview to better map and keep track of this rapidly evolving landscape. There is a lot more in the paper. Over 1000+ references included. This survey tries to capture the most common methods and biggest trends but there is more on the horizon as models continue to improve in capability and new agent architectures emerge" @omarsar0 on X 2025-07-18 16:12:39 UTC 255K followers, 4788 engagements
"Strong long-context extrapolation Despite being trained on 32K-length documents with an 8K context window MemAgent-14B achieves XX% accuracy even at 3.5M tokens outperforming baselines like Qwen2.5 and DeepSeek which degrade severely beyond 112K tokens" @omarsar0 on X 2025-07-08 19:29:17 UTC 255K followers, 4842 engagements
"I started to experiment with Grok X and I already found some interesting things about it. I'm preparing a detailed comparison with other reasoning models. I will be hosting a workshop on Grok X for our academy members soon:" @omarsar0 on X 2025-07-10 13:36:51 UTC 254.8K followers, 12.9K engagements
"@russelljkaplan I think it was a great acquisition. I love the Windsurf brand and there are some really talented folks there. I think this is a win-win situation" @omarsar0 on X 2025-07-14 22:32:12 UTC 254.6K followers, 2911 engagements
"The paper provides a taxonomy of context engineering in LLMs categorized into foundational components system implementations evaluation methodologies and future directions" @omarsar0 on X 2025-07-18 16:12:07 UTC 255K followers, 3637 engagements
"Great work from the team. I care about efficiency in my work. GPT-4.1-mini being a lot cheaper and performant at the same time is exciting. The fact that GPT-4.1 tops the leaderboard for now makes a lot of sense as it is one of the top models for instruction following which is a key capability in building agents with superior tool calling. Perhaps the reasoning models weren't great but I think they can only get better at tool calling so it will be interesting to track how the leaderboard progresses as new reasoning models roll out. Kimi K2 is such an exciting open-source release. It packs a" @omarsar0 on X 2025-07-17 21:50:02 UTC 255K followers, 10.3K engagements
"A Survey of Context Engineering 160+ pages covering the most important research around context engineering for LLMs. This is a must-read Here are my notes:" @omarsar0 on X 2025-07-18 16:12:03 UTC 255K followers, 104.2K engagements
"A Survey of AI Agent Protocols X things that stood out to me about this report:" @omarsar0 on X 2025-05-03 17:43:40 UTC 254.8K followers, 208.2K engagements
"AI for Scientific Search AI for Science is where I spend most of my time exploring with AI agents. This 120+ pages report does a good job of highlighting why all the big names like OpenAI and Google DeepMind are pursuing AI4Science. Bookmark it My notes below:" @omarsar0 on X 2025-07-03 14:58:05 UTC 255K followers, 61.4K engagements
"@robertnishihara Search for AI agents is one of my favorite problems to work on and think about. It really pushes you to think beyond the basics of context engineering" @omarsar0 on X 2025-07-15 19:50:46 UTC 254.9K followers, 1341 engagements
"Future of Work with AI Agents Stanford's new report analyzes what 1500 workers think about working with AI Agents. What types of AI Agents should we build A few surprises Let's take a closer look:" @omarsar0 on X 2025-06-20 18:51:58 UTC 255K followers, 300.6K engagements
"Mitigation via adversarial augmentation The authors create "Master-RM" a new reward model trained with 20k synthetic negative samples (responses consisting of only reasoning openers). This model generalizes robustly achieving near-zero FPR across five benchmarks while still agreeing XX% with GPT-4o on meaningful judgments" @omarsar0 on X 2025-07-14 15:17:18 UTC 254.8K followers, 5066 engagements
"What comes after Cursor This new agentic IDE Kiro offers a glimpse at that future. Kiro comes with all the fun features in an agentic IDE deliberate planning and leverages ambient agents that autonmously collaborate with devs as they build production-grade systems" @omarsar0 on X 2025-07-15 14:51:14 UTC 255K followers, 46.4K engagements
"Agentic-R1 This 7B model is surprisingly good at interleaved tool use and reasoning capabilities. It's fun to see small language models improving this fast. Knowledge distillation in full display. Here are my notes:" @omarsar0 on X 2025-07-17 15:10:04 UTC 255K followers, 55.6K engagements
"LLMs Get Lost in Multi-turn Conversation The cat is out of the bag. Pay attention devs. This is one of the most common issues when building with LLMs today. Glad there is now paper to share insights. Here are my notes:" @omarsar0 on X 2025-05-14 20:47:41 UTC 254.8K followers, 758.8K engagements
"The work distinguishes prompt engineering from context engineering on dimensions like state scalability error analysis complexity etc" @omarsar0 on X 2025-07-18 16:12:14 UTC 255K followers, 2917 engagements
"Tool-calling capabilities in an area of continuous development in the space. The paper provides an overview of tool-augmented language model architectures and how they compare across tool categories" @omarsar0 on X 2025-07-18 16:12:36 UTC 255K followers, 2050 engagements
"This handbook is so good It covers everything you need to know about LLM inference. FREE to access:" @omarsar0 on X 2025-07-11 17:42:45 UTC 255K followers, 85.2K engagements
"Much is being said about context engineering but I want to focus on building. Find the full guide here: I am also hosting a workshop on "Context Engineering for AI Agents" for our academy pro members:" @omarsar0 on X 2025-07-05 18:33:33 UTC 254.8K followers, 16.3K engagements
"Small Language Models are the Future of Agentic AI Lots to gain from building agentic systems with small language models. Capabilities are increasing rapidly AI devs should be exploring SLMs. Here are my notes:" @omarsar0 on X 2025-07-01 13:23:02 UTC 255K followers, 266.8K engagements
"Context Engineering Guide I'm writing a detailed guide on context engineering for AI devs. v1 is out now (bookmark it) I use a concrete deep research multi-agent example to show what context engineering involves" @omarsar0 on X 2025-07-05 18:33:33 UTC 255K followers, 286.1K engagements
"Elon claims that Grok X is smarter than almost all grad students in all disciplines simultaneously. 100x more training than Grok X. 10x more compute on RL than any of the models out there" @omarsar0 on X 2025-07-10 04:15:32 UTC 255K followers, 123.8K engagements
""Master keys" break LLM judges Simple generic lead-ins (e.g. Lets solve this step by step) and even punctuation marks can elicit false YES judgments from top reward models. This manipulation works across models (GPT-4o Claude-4 Qwen2.5 etc.) tasks (math and general reasoning) and prompt formats reaching up to XX% false positive rates in some cases" @omarsar0 on X 2025-07-14 15:17:11 UTC 254.7K followers, 2345 engagements
"Overview Introduces an RLdriven memory agent that enables transformer-based LLMs to handle documents up to XXX million tokens with near lossless performance linear complexity and no architectural modifications" @omarsar0 on X 2025-07-08 19:29:14 UTC 254.9K followers, 1963 engagements
"Context Engineering Guide is now part of the Prompt Engineering Guide. 🔥 Nicer format. We've also been writing guides on other fire topics such as deep research reasoning LLMs and image generation. I will be expanding the guide further in the coming days. Stay tuned" @omarsar0 on X 2025-07-08 13:48:44 UTC 255K followers, 35.7K engagements
"The context engineering evolution timeline from 2020 to 2025 involves foundational RAG systems to complex multi-agent architectures" @omarsar0 on X 2025-07-18 16:12:10 UTC 255K followers, 3504 engagements
"You can read the full paper below: Want to take it a step further Learn about context engineering and how to build effective agentic systems in my courses: We also have a workshop on context engineering coming soon" @omarsar0 on X 2025-07-18 16:12:42 UTC 255K followers, 4886 engagements