[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.]
swyx posts on X about llm, xai, context engineering, just a the most. They currently have XXXXXXX followers and XXX posts still getting attention that total XXXXXX engagements in the last XX hours.
Social category influence technology brands stocks celebrities social networks countries automotive brands exchanges finance
Social topic influence llm, xai, context engineering #20, just a, open ai, automation, elon musk, gamma, quora, meta
Top assets mentioned Coinbase Global, Inc. (COIN) Alphabet Inc Class A (GOOGL)
Top posts by engagements in the last XX hours
"Build Claude Code success.jpg Cursor seems pretty good I wonder what they do lightbulb.jpg /join cursor /leave cursor Build Claude Code" @swyx on X 2025-07-16 19:13:49 UTC 121.3K followers, 59.1K engagements
"btw by far the most interesting new pattern we are seeing in @latentspacepod (upcoming with @olivierddr and @sdrzn and @pashmerepat) is that people are using @claude_code and @Cline for non-coding tasks and this is becoming surprisingly effective for things like sales/BI automation and Gsuite (read my emails slacks linears search web make report etc etc) ofc enabled by MCP but somehow BOTH chatgpt and claude desktop have not captured this kind of organic integration/white collar work automation behavior part of this i guess is driven by the generous $XXX claude max plan limits part of it is" @swyx on X 2025-07-07 17:22:45 UTC 121.4K followers, 152.6K engagements
"@gyani1595 @xai @grok @bryan_johnson @elonmusk close but no it was an anon account i think" @swyx on X 2025-07-21 00:11:38 UTC 121.2K followers, XXX engagements
"six way parlay. i want Mistral founders to Apple Mistral team to Meta. Character remainco to Perplexity. Quora to Perplexity. Ideogram to Figma. Gamma to Notion. read it back" @swyx on X 2025-07-14 23:31:05 UTC 121.4K followers, 116.6K engagements
"@imjaredz @trychroma @kellyhongsn sadly we are so used to being lied to that confirmation that million token context window is a lie is a nonevent 😬 what really needs to happen is an authoritative number for effective context window. would nudge chroma to own that" @swyx on X 2025-07-15 22:47:36 UTC 121.2K followers, XXX engagements
""everything that makes agents good is context engineering" excited to release @dexhorthy's talk at @aiDotEngineer coiner of Context Engineering which has captured the zeitgeist of some of the most important problems in AI Engineering today" @swyx on X 2025-07-03 20:56:17 UTC 121.4K followers, 91.8K engagements
"I will die on this hill that o1-preview is a far better summarizer than o1 or o3 and the world is about to lose access to a great model that was never properly pulled into production" @swyx on X 2025-07-20 10:04:00 UTC 121.4K followers, 16.6K engagements
"lowkey the best thing about @xai is the Voice Mode. I got SuperGrok just to test out Grok X and do KaraokeBench on Grok 4s Eve Voice (the one that does opera) but actually Im going to keep SuperGrok around because its actually just a much much better voice mode than @chatgptapp like: - open straight to voice mode - SPEED CONTROLS - MUTE BUTTON - PROMPTABLE VOICES - auto suggestions - interruptions that dont suck - unhinged mode this thing is made by people who actually use the product" @swyx on X 2025-07-12 01:49:25 UTC 121.4K followers, 11.4M engagements
"incredible work on alignment steganography from anthropic fellows i've been looking for a straussian explanation of why china keeps publishing open models out of the goodness of their hearts if you do stuff like use open models to idk clean ahem synthetically paraphrase your data to textbook quality you may very well import biases you can't detect until long after it's too late. so if you want to export your value system to the rest of the world this is the most powerful Soft Power tool invented since Hollywood. to be super clear we have no actual proof of this motivating any of the chinese" @swyx on X 2025-07-23 04:26:40 UTC 121.4K followers, 43.8K engagements
"people asked for recs. apart from emilie #220 Former CEO Amazon Worldwide Consumer Jeff Wilke: Exponential #217 CEO & Co-Founder Codeium Varun Mohan w/ Leigh Marie Braswell: Limitless #214 Former CEO Hulu & WarnerMedia Jason Kilar: No Labels #212 Founder Magic Leap & SynthBee Rony Abovitz: Underdog #206 CEO & Founder Rivian RJ Scaringe: Electrified #203 CEO Niantic John Hanke: Buried Ships #200 CEO & Co-Founder Together AI Vipul Ved Prakash w/ Bucky Moore: Super Cycle #183 CEO & Co-Founder Harness Jyoti Bansal: Three-Layered Cake #176 CEO MongoDB Dev Ittycheria: Edge idk man i stopped after a" @swyx on X 2025-01-22 16:26:11 UTC 121.3K followers, 4116 engagements
"@jack_w_rae did you try the google glasses (gentle monster/warby parker) before you left wondering how close they are to reality" @swyx on X 2025-07-09 14:40:52 UTC 121.3K followers, 2852 engagements
"i've been looking for "brainrot education" for the gen alphas and someone finally sent me a channel that translates @dexhorthy and @RLanceMartin's content for those who are of deficit in attention this channel is X weeks old and has 22k followers" @swyx on X 2025-07-18 06:50:00 UTC 121.4K followers, 151.8K engagements
"trying to find the tweet that's like: Mankind's three current grand quests are: - Build God - Explore Stars - Defeat Death does anyone know who said that @xai @grok is failing me" @swyx on X 2025-07-20 23:55:55 UTC 121.4K followers, 23.4K engagements
"icymi openai also open sourced how their deep research prompt rewriter works + the full prompts today you can now build your own deep research agent - with full o3/o4-mini deep research quality - in 20LOC if you're a fan of Claude Research they ALSO dropped how to add multiagents with MCP support lmao" @swyx on X 2025-06-27 00:51:08 UTC 121.4K followers, 234.1K engagements
"whoa shoutout to @tferriss for featuring Hyperstitions of Moloch on Five Bullet Friday" @swyx on X 2025-07-20 21:25:54 UTC 121.4K followers, 61.7K engagements
"i am once again telling everyone who will listen that @Joubinmirs podcast is the single best operator pod in the world delete YCs overprescribed frameworks that half their founders ignore yeet the Founders podcast where charming guy reads hagiography listen to @Joubinmir get this level of openness and connection with people like @emiliemc not r1 related at all but screw it this is that fucking goood" @swyx on X 2025-01-21 06:31:06 UTC 121.3K followers, 36.5K engagements
"i think Prompt Engineering is "growing up" in two different ways in 2025. the first is "Context Engineering" which is well covered by @dexhorthy's talk (now 100k views) but Prompts = Intent + Context and as @sgrove points out the task of encoding intents/goals/principles accurately is key to aligning agents to our desires especially as they take on more and more autonomy. we have many examples of clear structured communication for aligning complex systems from the US constitution to the @openai model spec. i think the most underrated slide in this talk is this one which draws a strong analogy" @swyx on X 2025-07-11 17:03:09 UTC 121.4K followers, 68.3K engagements
"a lot of people are pooh poohing the ChatGPT Agent launch as just a better harness but theyre not reading closely enough we got a new frontier model today folks these charts are like for like same harness they basically stopped short of calling it GPT5 but yeah if there were a public release of o4-full today was it dont sleep on that. in other words run your benchmarks telling it not to use tools and i expect itll be a big step up from o3" @swyx on X 2025-07-18 02:49:56 UTC 121.4K followers, 92.3K engagements
"if you havent tried the Chrome + iMessage + Apple Notes + Linear + Gmail + GCal DXT integrations in Claude you are missing out the literal LLM OS evolution Smarter Siri is here; it's just called Claude Desktop" @swyx on X 2025-07-17 06:38:10 UTC 121.3K followers, 124.1K engagements
"one way to view the $75m/yr MSL comp packages is that it will materially change the aspirations of our next generation. people who lamented that our kids who only aspire to grow up to be youtubers and tiktokers now have new heroes to point to whose work hopefully creates agents that free up time rather than consume it" @swyx on X 2025-07-17 01:02:10 UTC 121.4K followers, 18K engagements
"@JustinLin610 qq did you see @rasbt 's analysis and questions on qwen3" @swyx on X 2025-07-21 18:06:50 UTC 121.4K followers, 2676 engagements
"claude code is $200m ARR and that helped anthro get to $100b valuation what everybody wants to know is WHAT ARE THE MARGINS on that 200m" @swyx on X 2025-07-16 22:19:14 UTC 121.2K followers, 8846 engagements
""Three things: a deep research model with enhanced search browser; a revolutionary computer-use operator; and a sandboxed terminal to execute math and code. A browser a computer a terminal are you getting it These are not three separate agents. This is one agent and we are calling it Agent."" @swyx on X 2025-07-17 17:51:07 UTC 121.4K followers, 45.5K engagements
"constant rumors of GPT5-reasoning GPT5-mini and GPT5-nano coming in "early August" now. according to this @tomwarren piece o3-mini-level open model launch also coming by next week" @swyx on X 2025-07-24 19:21:07 UTC 121.4K followers, 5320 engagements
"buried in @sriramk's America's AI Action Plan is endorsement that the US compute market will financialize with spot and forward contracts. this podcast explains why this is so necessary not just for speculation one of the most consistent themes with @latentspacepod's GPU infra/neocloud market coverage (see @evanjconrad/@sfcompute @vipulved / @togethercompute @picocreator / @featherlessai @bernhardsson / @modal_labs but also @zjasper666's AIE talk) is that the status quo of X year lockin long term contracts with hyperscalers is causing unsustainable market volatility and inefficiency not just" @swyx on X 2025-07-24 01:18:58 UTC 121.4K followers, 48.5K engagements
"please stop making flight booking agent demos with faint but dying hope the undersigned" @swyx on X 2025-07-19 00:42:20 UTC 121.3K followers, 36.6K engagements
"the reason llm analysis (and regulation and PMing) is hard* is that the relevant DIMENSIONS keep moving with each generation of frontier model; it is not enough to just put your x or y axis in log scale and track scaling laws you have to actually do the work to think about how models are structurally different in 2025 vs 2024 vs 2023 and so on eg everyone focused on elo for X years elo gets gamed and loses credibility everyone focused on price per tokens for X years reasoning models have 10-40x variation in output tokens per task price per token loses meaning collect data all you want but if" @swyx on X 2025-07-22 05:38:30 UTC 121.4K followers, 9980 engagements
"so Chrome 138+ onwards ships Gemini Nano for every user* putting a local LLM in XXX billion monthly active users of Chrome wrote a personal guide today for building with Gemini Nano - mostly for me might help you if you're not suuper strong at javascript or parsing google's. unique. js documentation style. added instructions for doing structured output with Gemini Nano shamelessly stolen from @jxnlco examples enjoy *still need to turn on a flag for now but will become easier and easier" @swyx on X 2025-07-08 04:16:09 UTC 121.4K followers, 94.6K engagements
"glad this is public now - learning about how this deal went down and how Scott masterminded the whole thing made me significantly update on how Cogsurf is now one of the most killer nonlab startup teams in AI and if they can do this in a weekend you should be very wise to expect insane execution timing and strategy in everything else they do" @swyx on X 2025-07-19 07:01:50 UTC 121.4K followers, 45.7K engagements