[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.]
#  @DataChaz Charly Wargnier
Charly Wargnier posts on X about ai, llm, prompt engineering, windsurf the most. They currently have XXXXXXX followers and 1691 posts still getting attention that total XXXXXX engagements in the last XX hours.
### Engagements: XXXXXX [#](/creator/twitter::19628766/interactions)

- X Week XXXXXXX -XX%
- X Month XXXXXXXXX +30%
- X Months XXXXXXXXXX +317%
- X Year XXXXXXXXXX +387%
### Mentions: XX [#](/creator/twitter::19628766/posts_active)

- X Week XX -XX%
- X Month XXX +9.60%
- X Months XXX +227%
- X Year XXXXX +249%
### Followers: XXXXXXX [#](/creator/twitter::19628766/followers)

- X Week XXXXXXX +0.49%
- X Month XXXXXXX +2.30%
- X Months XXXXXXX +12%
- X Year XXXXXXX +24%
### CreatorRank: XXXXXXX [#](/creator/twitter::19628766/influencer_rank)

### Social Influence
**Social category influence**
[technology brands](/list/technology-brands) [stocks](/list/stocks) [travel destinations](/list/travel-destinations) [finance](/list/finance)
**Social topic influence**
[ai](/topic/ai), [llm](/topic/llm) #140, [prompt engineering](/topic/prompt-engineering) #22, [windsurf](/topic/windsurf) #48, [$googl](/topic/$googl) #771, [vibe coding](/topic/vibe-coding) #87, [matter](/topic/matter) #1880, [agi](/topic/agi) #198, [deepfake](/topic/deepfake), [mcp server](/topic/mcp-server) #55
**Top assets mentioned**
[Alphabet Inc Class A (GOOGL)](/topic/$googl) [Microsoft Corp. (MSFT)](/topic/microsoft)
### Top Social Posts
Top posts by engagements in the last XX hours
"This is next-level. A cute humanoid girl chatting with guests"
[X Link](https://x.com/DataChaz/status/1996247117468209453) 2025-12-03T15:56Z 145.7K followers, 2M engagements
"bro literally built an army of AI Agents in @n8n_io with free Kimi K2 LLM 🤯"
[X Link](https://x.com/DataChaz/status/1999601723942535473) 2025-12-12T22:06Z 145.7K followers, 40.8K engagements
"its over and you know it"
[X Link](https://x.com/DataChaz/status/1994411777195377063) 2025-11-28T14:23Z 145.7K followers, 1.6M engagements
"A must-bookmark for vibe-coders. @YCombinators guide to making the most of vibe coding:"
[X Link](https://x.com/DataChaz/status/1996904843982905815) 2025-12-05T11:29Z 145.7K followers, 94.7K engagements
"Figma finally meets ChatGPT. An AI workspace that treats every doc as a movable editable visual block not a scrolling chat. @Felo_ai_en is a Figma-style Agent Workspace for documents built for real collaboration and integrated AI work 🔥 X wild use cases 🧵"
[X Link](https://x.com/DataChaz/status/1998381075098411421) 2025-12-09T13:15Z 145.7K followers, 119.2K engagements
"this guy literally put in 1000 hours of prompt engineering to nail down the X patterns that actually matter"
[X Link](https://x.com/DataChaz/status/1998428375795511349) 2025-12-09T16:23Z 145.7K followers, 491.3K engagements
"Everyone on : GPT5.2 is AGI 😱 GPT5.2:"
[X Link](https://x.com/DataChaz/status/1999445969906336025) 2025-12-12T11:47Z 145.7K followers, 21.9K engagements
"This guy literally turned Claude into an Ultrathink powerhouse 🤯"
[X Link](https://x.com/DataChaz/status/1999748677913755915) 2025-12-13T07:50Z 145.7K followers, 176.7K engagements
"If youre building voice agents latency matters more than anything. For years proprietary TTS dominated benchmarks. Thats changing. @ResembleAIs Chatterbox Turbo is reshaping benchmarks: Open-source Crushes ElevenLabs & Cartesia on quality Far lower latency 🧵"
[X Link](https://x.com/DataChaz/status/2000954260654317836) 2025-12-16T15:40Z 145.7K followers, 17.9K engagements
"Here's the golden metric: 150ms time-to-first-sound. Thats the threshold where voice agents stop feeling laggy and start feeling usable. Chatterbox also feats: 350M-parameter zero-shot TTS Zero-shot voice cloning with 5s of audio It runs locally 🔥 3/8"
[X Link](https://x.com/DataChaz/status/2000954310507823613) 2025-12-16T15:40Z 145.7K followers, XXX engagements
"Stanford University just made all its best AI courses free. No tuition required. These are game changers for anyone serious about AI. X courses worth bookmarking 🧵"
[X Link](https://x.com/DataChaz/status/1992542639519072374) 2025-11-23T10:35Z 145.6K followers, 56.1K engagements
"Anthropic dropped the best free masterclass on prompt engineering 🔥"
[X Link](https://x.com/DataChaz/status/1995797502755479605) 2025-12-02T10:09Z 145.6K followers, 41.4K engagements
"This ones a gem. A Free 80-page prompt engineering guide is surprising deep covering: CoT Eval methods RAG Agents Prompt hacking Multimodal prompts . and more Link to the guide in 🧵"
[X Link](https://x.com/DataChaz/status/1996855654661992596) 2025-12-05T08:14Z 145.6K followers, 6377 engagements
"AGI might be closer than we think. Google just dropped Titans + MIRAS a long-term memory system for AI that updates itself in real time. It's a new architecture that combines the speed of RNNs with the performance of Transformers. . and Its NOT a bigger context window its a new memory system that can learn new context on the fly 🤯 Here are the highlights: Effective on 2M+ token contexts A neural memory module that evolves as new data comes in Selective storage based on a surprise signal Moves beyond the fresh brain every chat limitation of todays models Is the context window limit finally"
[X Link](https://x.com/DataChaz/status/1997211176422482341) 2025-12-06T07:47Z 145.6K followers, 47.4K engagements
"You can watch it here:"
[X Link](https://x.com/DataChaz/status/1997786370971181407) 2025-12-07T21:52Z 145.6K followers, 23.6K engagements
"3/ All of this arrives with a $13M strategic raise backed by Google Sony Okta and more 🔥 Deepfake fraud is a $40B mess. Someone needs to clean it up. and this feels like a serious move in that direction"
[X Link](https://x.com/DataChaz/status/1998075752445804878) 2025-12-08T17:02Z 145.6K followers, XXX engagements
"Amsterdam doing what it does best: Crooked canal houses glowing skies and perfect reflections ♥"
[X Link](https://x.com/DataChaz/status/1998375472976322592) 2025-12-09T12:53Z 145.6K followers, 1826 engagements
"Heres a goldmine of LLM notebooks and it goes way beyond basic fine-tuning 🤯 Auto evals lazy merges Franken MoEs uncensoring techniques real wizard-level tooling. Built by @maximelabonne and @iusztinpaul authors of the excellent LLM Engineers Handbook. Repo in 🧵"
[X Link](https://x.com/DataChaz/status/1998811008522137760) 2025-12-10T17:44Z 145.7K followers, 11.6K engagements
"Honestly this new MCP integration just clicks. It finally brings SonarQubes full verification layer straight into your IDE exactly where you need it. You can try SonarQube here"
[X Link](https://x.com/DataChaz/status/1999056510928945620) 2025-12-11T09:59Z 145.6K followers, XXX engagements
"@JustinGorya @AlxTurovski @windsurf I always want to give @windsurf a chance and I always get super disappointed :("
[X Link](https://x.com/DataChaz/status/1999086613180354670) 2025-12-11T11:59Z 145.7K followers, XX engagements
"@SonarSource Ace job on your MCP server guys I really like it 🤗"
[X Link](https://x.com/DataChaz/status/1999087884629082139) 2025-12-11T12:04Z 145.6K followers, XXX engagements
"@JustinGorya @AlxTurovski @windsurf @cognition I actually haven't maybe I should"
[X Link](https://x.com/DataChaz/status/1999087942204321803) 2025-12-11T12:04Z 145.7K followers, XX engagements
"tokens go brrrr 😅"
[X Link](https://x.com/DataChaz/status/2000117577687974162) 2025-12-14T08:16Z 145.6K followers, 2674 engagements
"2/ Also: 99%+ accuracy on todays top GenAI models including Midjourney v7 DALLE X and Veo. It even detects partial edits (the hardest kind) where only part of the image is AI-generated 🤯"
[X Link](https://x.com/DataChaz/status/1998075734368354444) 2025-12-08T17:02Z 145.7K followers, XXX engagements
"This is a big. Train LLMs X faster with no accuracy tradeoff. @UnslothAI just rolled out a strong set of kernel + data pipeline upgrades that remove real training bottlenecks: padding overhead unfused ops and long-context indexing pain. Result: models like Qwen3-4B now train on 3GB VRAM at roughly X the speed. What changed under the hood: Fused QK RoPE Triton kernel: XXX faster rotary embeddings fully compatible with packing Updated SwiGLU / GeGLU kernels: Int64-safe indexing long-context training no longer breaks Clean sample packing: XXXX higher throughput across FA3 xFormers and SDPA"
[X Link](https://x.com/DataChaz/status/2000142212433334287) 2025-12-14T09:53Z 145.7K followers, 4849 engagements
"Checkout the docs:"
[X Link](https://x.com/DataChaz/status/2000142224978575650) 2025-12-14T09:54Z 145.7K followers, XXX engagements
"A must-bookmark for vibe-coders. @YCombinators guide to making the most of vibe coding:"
[X Link](https://x.com/DataChaz/status/1967846530867695855) 2025-09-16T07:02Z 145.7K followers, 285.4K engagements
"Wild. By far the most complete Claude Skills repo yet 🤯 @Composios Awesome-Claude-Skills packs 100s of ready-to-use workflows: PDF tools changelog generation Playwright automation AWS/CDK tools MCP builders . and much more Free and open-source. Repo in 🧵"
[X Link](https://x.com/DataChaz/status/1988267968053346609) 2025-11-11T15:29Z 145.7K followers, 104.9K engagements
"Better than Lovable. Bold I know. But stick with me. @Anythings latest iteration builds full apps from scratch fixes every issue along the way and ships to the App Store from one prompt 🔥 Say hello to Anything Max. (oh and theres a $100K hackathon running rn) 🧵"
[X Link](https://x.com/DataChaz/status/1999154173137559731) 2025-12-11T16:27Z 145.7K followers, 44.8K engagements
"@resembleai You're very welcome I LOVE open source and I love it even more when it's amazing :)"
[X Link](https://x.com/DataChaz/status/2001049248981225949) 2025-12-16T21:58Z 145.7K followers, XX engagements
".@ResembleAI just dropped something HUGE today. and it might be the most advanced deepfake security tech Ive seen this year. Meet DETECT-3B Omni. A single model that can detect fake voices images and videos all in one unified system. Let's dive in 🧵"
[X Link](https://x.com/DataChaz/status/1998075645495324727) 2025-12-08T17:02Z 145.7K followers, 20.8K engagements
"Google just dropped one of the most practical guides on agent quality in production 🔥 It's a great 50-page deep dive on why traditional QA fails for agents and what to replace it with. XXX % free. Download link in 🧵 The X pillars: effectiveness efficiency robustness safety Trajectory-based evaluation (outside-in) Observability via logs traces metrics Continuous eval loops (LLM-as-judge + HITL)"
[X Link](https://x.com/DataChaz/status/2000886294441017598) 2025-12-16T11:10Z 145.7K followers, 19.5K engagements
"SonarQube has been catching my bugs and security issues for years. The only friction was having to leave Cursor or Windsurf to view the results. Their new MCP Server fixes that by bringing verification directly into the coding environment 🔥 This is actually perfect timing 🧵 Because we write more code than ever thanks to AI yet productivity still doesnt keep up. Googles 2025 DORA Report shows the tension: AI usage +90% Bugs +9% Review time +91% PR size +154% (report here: The problem isnt generating code. Its verifying it quickly and reliably. And this is what SonarQube's new MCP Server"
[X Link](https://x.com/DataChaz/status/1999056498845241684) 2025-12-11T09:59Z 145.7K followers, 22.5K engagements
"Wait there's moar. @ResembleAIs Chatterbox Turbo also has a secret sauce: Paralinguistic tags 🌶 You can inject vocal cues straight into any text: "We just hit 10k stars gasp laugh" Supported tags includesigh gasp chuckle groan & many more SOUND ON 🔈 4/8"
[X Link](https://x.com/DataChaz/status/2000954462891073979) 2025-12-16T15:41Z 145.7K followers, XXX engagements
"@xavierlois @resembleai I thought you might like that :) Pretty good isn't it"
[X Link](https://x.com/DataChaz/status/2001206562233233716) 2025-12-17T08:23Z 145.7K followers, X engagements
"Microsoft just killed the GPU mafia 🤯 They've open-sourced bitnet.cpp a blazing-fast 1-bit LLM inference framework optimized for CPUs. This is a major step forward for running large models locally without expensive GPUs or cloud costs. Demo app + repo + paper in 🧵"
[X Link](https://x.com/DataChaz/status/1974015430886117763) 2025-10-03T07:35Z 145.7K followers, 515K engagements
"this guy literally put in 1000 hours of prompt engineering to nail down the X patterns that actually matter"
[X Link](https://x.com/DataChaz/status/1984276199309484409) 2025-10-31T15:08Z 145.7K followers, 354.9K engagements
"Cut your LLM costs by XX% 🤯 Stop using JSON switch to TOON (Token-Oriented Object Notation). It blends YAMLs readability with CSVs compactness: 3060% less tokens Built-in field validation GPT-5 Claude Gemini. Ace for tabular data. Free and open-source 🧵"
[X Link](https://x.com/DataChaz/status/1985983439422820498) 2025-11-05T08:12Z 145.7K followers, 112.5K engagements
"If youre still sending raw JSON into your LLMs youre burning tokens latency and budget Try TOON (Token-Oriented Object Notation). Clear like YAML compact like CSV: 3060% fewer tokens Up to XX% lower costs Shines for tabular data. Free and Open source 🧵"
[X Link](https://x.com/DataChaz/status/1989056483057889481) 2025-11-13T19:43Z 145.7K followers, 2.5M engagements
"Still cant believe @karpathy released this 3.5-hour free deep dive on how ChatGPT actually works for free. If theres one AI video to watch in 2025 this is the one"
[X Link](https://x.com/DataChaz/status/1997786358417662349) 2025-12-07T21:52Z 145.7K followers, 239.1K engagements
"OpenAI just rolled out a revamped images section in ChatGPT and it looks pretty rad 👀"
[X Link](https://x.com/DataChaz/status/2001048151449592208) 2025-12-16T21:53Z 145.7K followers, 2265 engagements
".@GeminiApps's nanobanana 🍌 (left) VS @Openai ChatGPT Images (right) Who wins"
[X Link](https://x.com/DataChaz/status/2001209466700914922) 2025-12-17T08:34Z 145.7K followers, 2107 engagements
"Here's the prompt courtesy of @godofprompt "prompt": "subject": "description": "A young adult sitting on a yoga mat after a workout wiping sweat with a small towel while holding a water bottle near their knee" "mirror_rules": "N/A - direct photo" "age": "young adult" "expression": "accomplished slightly breathless soft satisfied smile looking toward the phone" "hair": "color": "dark brown" "style": "high ponytail slightly messy with flyaways a few damp strands stuck near the temples" "clothing": "top": "type": "sports bra" "color": "charcoal gray" "details": "medium support subtle sweat marks"
[X Link](https://x.com/DataChaz/status/2001209479178887467) 2025-12-17T08:34Z 145.7K followers, XXX 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.]
@DataChaz Charly WargnierCharly Wargnier posts on X about ai, llm, prompt engineering, windsurf the most. They currently have XXXXXXX followers and 1691 posts still getting attention that total XXXXXX engagements in the last XX hours.
Social category influence technology brands stocks travel destinations finance
Social topic influence ai, llm #140, prompt engineering #22, windsurf #48, $googl #771, vibe coding #87, matter #1880, agi #198, deepfake, mcp server #55
Top assets mentioned Alphabet Inc Class A (GOOGL) Microsoft Corp. (MSFT)
Top posts by engagements in the last XX hours
"This is next-level. A cute humanoid girl chatting with guests"
X Link 2025-12-03T15:56Z 145.7K followers, 2M engagements
"bro literally built an army of AI Agents in @n8n_io with free Kimi K2 LLM 🤯"
X Link 2025-12-12T22:06Z 145.7K followers, 40.8K engagements
"its over and you know it"
X Link 2025-11-28T14:23Z 145.7K followers, 1.6M engagements
"A must-bookmark for vibe-coders. @YCombinators guide to making the most of vibe coding:"
X Link 2025-12-05T11:29Z 145.7K followers, 94.7K engagements
"Figma finally meets ChatGPT. An AI workspace that treats every doc as a movable editable visual block not a scrolling chat. @Felo_ai_en is a Figma-style Agent Workspace for documents built for real collaboration and integrated AI work 🔥 X wild use cases 🧵"
X Link 2025-12-09T13:15Z 145.7K followers, 119.2K engagements
"this guy literally put in 1000 hours of prompt engineering to nail down the X patterns that actually matter"
X Link 2025-12-09T16:23Z 145.7K followers, 491.3K engagements
"Everyone on : GPT5.2 is AGI 😱 GPT5.2:"
X Link 2025-12-12T11:47Z 145.7K followers, 21.9K engagements
"This guy literally turned Claude into an Ultrathink powerhouse 🤯"
X Link 2025-12-13T07:50Z 145.7K followers, 176.7K engagements
"If youre building voice agents latency matters more than anything. For years proprietary TTS dominated benchmarks. Thats changing. @ResembleAIs Chatterbox Turbo is reshaping benchmarks: Open-source Crushes ElevenLabs & Cartesia on quality Far lower latency 🧵"
X Link 2025-12-16T15:40Z 145.7K followers, 17.9K engagements
"Here's the golden metric: 150ms time-to-first-sound. Thats the threshold where voice agents stop feeling laggy and start feeling usable. Chatterbox also feats: 350M-parameter zero-shot TTS Zero-shot voice cloning with 5s of audio It runs locally 🔥 3/8"
X Link 2025-12-16T15:40Z 145.7K followers, XXX engagements
"Stanford University just made all its best AI courses free. No tuition required. These are game changers for anyone serious about AI. X courses worth bookmarking 🧵"
X Link 2025-11-23T10:35Z 145.6K followers, 56.1K engagements
"Anthropic dropped the best free masterclass on prompt engineering 🔥"
X Link 2025-12-02T10:09Z 145.6K followers, 41.4K engagements
"This ones a gem. A Free 80-page prompt engineering guide is surprising deep covering: CoT Eval methods RAG Agents Prompt hacking Multimodal prompts . and more Link to the guide in 🧵"
X Link 2025-12-05T08:14Z 145.6K followers, 6377 engagements
"AGI might be closer than we think. Google just dropped Titans + MIRAS a long-term memory system for AI that updates itself in real time. It's a new architecture that combines the speed of RNNs with the performance of Transformers. . and Its NOT a bigger context window its a new memory system that can learn new context on the fly 🤯 Here are the highlights: Effective on 2M+ token contexts A neural memory module that evolves as new data comes in Selective storage based on a surprise signal Moves beyond the fresh brain every chat limitation of todays models Is the context window limit finally"
X Link 2025-12-06T07:47Z 145.6K followers, 47.4K engagements
"You can watch it here:"
X Link 2025-12-07T21:52Z 145.6K followers, 23.6K engagements
"3/ All of this arrives with a $13M strategic raise backed by Google Sony Okta and more 🔥 Deepfake fraud is a $40B mess. Someone needs to clean it up. and this feels like a serious move in that direction"
X Link 2025-12-08T17:02Z 145.6K followers, XXX engagements
"Amsterdam doing what it does best: Crooked canal houses glowing skies and perfect reflections ♥"
X Link 2025-12-09T12:53Z 145.6K followers, 1826 engagements
"Heres a goldmine of LLM notebooks and it goes way beyond basic fine-tuning 🤯 Auto evals lazy merges Franken MoEs uncensoring techniques real wizard-level tooling. Built by @maximelabonne and @iusztinpaul authors of the excellent LLM Engineers Handbook. Repo in 🧵"
X Link 2025-12-10T17:44Z 145.7K followers, 11.6K engagements
"Honestly this new MCP integration just clicks. It finally brings SonarQubes full verification layer straight into your IDE exactly where you need it. You can try SonarQube here"
X Link 2025-12-11T09:59Z 145.6K followers, XXX engagements
"@JustinGorya @AlxTurovski @windsurf I always want to give @windsurf a chance and I always get super disappointed :("
X Link 2025-12-11T11:59Z 145.7K followers, XX engagements
"@SonarSource Ace job on your MCP server guys I really like it 🤗"
X Link 2025-12-11T12:04Z 145.6K followers, XXX engagements
"@JustinGorya @AlxTurovski @windsurf @cognition I actually haven't maybe I should"
X Link 2025-12-11T12:04Z 145.7K followers, XX engagements
"tokens go brrrr 😅"
X Link 2025-12-14T08:16Z 145.6K followers, 2674 engagements
"2/ Also: 99%+ accuracy on todays top GenAI models including Midjourney v7 DALLE X and Veo. It even detects partial edits (the hardest kind) where only part of the image is AI-generated 🤯"
X Link 2025-12-08T17:02Z 145.7K followers, XXX engagements
"This is a big. Train LLMs X faster with no accuracy tradeoff. @UnslothAI just rolled out a strong set of kernel + data pipeline upgrades that remove real training bottlenecks: padding overhead unfused ops and long-context indexing pain. Result: models like Qwen3-4B now train on 3GB VRAM at roughly X the speed. What changed under the hood: Fused QK RoPE Triton kernel: XXX faster rotary embeddings fully compatible with packing Updated SwiGLU / GeGLU kernels: Int64-safe indexing long-context training no longer breaks Clean sample packing: XXXX higher throughput across FA3 xFormers and SDPA"
X Link 2025-12-14T09:53Z 145.7K followers, 4849 engagements
"Checkout the docs:"
X Link 2025-12-14T09:54Z 145.7K followers, XXX engagements
"A must-bookmark for vibe-coders. @YCombinators guide to making the most of vibe coding:"
X Link 2025-09-16T07:02Z 145.7K followers, 285.4K engagements
"Wild. By far the most complete Claude Skills repo yet 🤯 @Composios Awesome-Claude-Skills packs 100s of ready-to-use workflows: PDF tools changelog generation Playwright automation AWS/CDK tools MCP builders . and much more Free and open-source. Repo in 🧵"
X Link 2025-11-11T15:29Z 145.7K followers, 104.9K engagements
"Better than Lovable. Bold I know. But stick with me. @Anythings latest iteration builds full apps from scratch fixes every issue along the way and ships to the App Store from one prompt 🔥 Say hello to Anything Max. (oh and theres a $100K hackathon running rn) 🧵"
X Link 2025-12-11T16:27Z 145.7K followers, 44.8K engagements
"@resembleai You're very welcome I LOVE open source and I love it even more when it's amazing :)"
X Link 2025-12-16T21:58Z 145.7K followers, XX engagements
".@ResembleAI just dropped something HUGE today. and it might be the most advanced deepfake security tech Ive seen this year. Meet DETECT-3B Omni. A single model that can detect fake voices images and videos all in one unified system. Let's dive in 🧵"
X Link 2025-12-08T17:02Z 145.7K followers, 20.8K engagements
"Google just dropped one of the most practical guides on agent quality in production 🔥 It's a great 50-page deep dive on why traditional QA fails for agents and what to replace it with. XXX % free. Download link in 🧵 The X pillars: effectiveness efficiency robustness safety Trajectory-based evaluation (outside-in) Observability via logs traces metrics Continuous eval loops (LLM-as-judge + HITL)"
X Link 2025-12-16T11:10Z 145.7K followers, 19.5K engagements
"SonarQube has been catching my bugs and security issues for years. The only friction was having to leave Cursor or Windsurf to view the results. Their new MCP Server fixes that by bringing verification directly into the coding environment 🔥 This is actually perfect timing 🧵 Because we write more code than ever thanks to AI yet productivity still doesnt keep up. Googles 2025 DORA Report shows the tension: AI usage +90% Bugs +9% Review time +91% PR size +154% (report here: The problem isnt generating code. Its verifying it quickly and reliably. And this is what SonarQube's new MCP Server"
X Link 2025-12-11T09:59Z 145.7K followers, 22.5K engagements
"Wait there's moar. @ResembleAIs Chatterbox Turbo also has a secret sauce: Paralinguistic tags 🌶 You can inject vocal cues straight into any text: "We just hit 10k stars gasp laugh" Supported tags includesigh gasp chuckle groan & many more SOUND ON 🔈 4/8"
X Link 2025-12-16T15:41Z 145.7K followers, XXX engagements
"@xavierlois @resembleai I thought you might like that :) Pretty good isn't it"
X Link 2025-12-17T08:23Z 145.7K followers, X engagements
"Microsoft just killed the GPU mafia 🤯 They've open-sourced bitnet.cpp a blazing-fast 1-bit LLM inference framework optimized for CPUs. This is a major step forward for running large models locally without expensive GPUs or cloud costs. Demo app + repo + paper in 🧵"
X Link 2025-10-03T07:35Z 145.7K followers, 515K engagements
"this guy literally put in 1000 hours of prompt engineering to nail down the X patterns that actually matter"
X Link 2025-10-31T15:08Z 145.7K followers, 354.9K engagements
"Cut your LLM costs by XX% 🤯 Stop using JSON switch to TOON (Token-Oriented Object Notation). It blends YAMLs readability with CSVs compactness: 3060% less tokens Built-in field validation GPT-5 Claude Gemini. Ace for tabular data. Free and open-source 🧵"
X Link 2025-11-05T08:12Z 145.7K followers, 112.5K engagements
"If youre still sending raw JSON into your LLMs youre burning tokens latency and budget Try TOON (Token-Oriented Object Notation). Clear like YAML compact like CSV: 3060% fewer tokens Up to XX% lower costs Shines for tabular data. Free and Open source 🧵"
X Link 2025-11-13T19:43Z 145.7K followers, 2.5M engagements
"Still cant believe @karpathy released this 3.5-hour free deep dive on how ChatGPT actually works for free. If theres one AI video to watch in 2025 this is the one"
X Link 2025-12-07T21:52Z 145.7K followers, 239.1K engagements
"OpenAI just rolled out a revamped images section in ChatGPT and it looks pretty rad 👀"
X Link 2025-12-16T21:53Z 145.7K followers, 2265 engagements
".@GeminiApps's nanobanana 🍌 (left) VS @Openai ChatGPT Images (right) Who wins"
X Link 2025-12-17T08:34Z 145.7K followers, 2107 engagements
"Here's the prompt courtesy of @godofprompt "prompt": "subject": "description": "A young adult sitting on a yoga mat after a workout wiping sweat with a small towel while holding a water bottle near their knee" "mirror_rules": "N/A - direct photo" "age": "young adult" "expression": "accomplished slightly breathless soft satisfied smile looking toward the phone" "hair": "color": "dark brown" "style": "high ponytail slightly messy with flyaways a few damp strands stuck near the temples" "clothing": "top": "type": "sports bra" "color": "charcoal gray" "details": "medium support subtle sweat marks"
X Link 2025-12-17T08:34Z 145.7K followers, XXX engagements
/creator/twitter::DataChaz