Dark | Light
[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.]

# ![@MaximeRivest Avatar](https://lunarcrush.com/gi/w:26/cr:twitter::956273322358079488.png) @MaximeRivest Maxime Rivest 🧙‍♂️🦙🐧

Maxime Rivest 🧙‍♂️🦙🐧 posts on X about chrome, $googl, laptop, gpu the most. They currently have XXXXX followers and XXX posts still getting attention that total XXXXXX engagements in the last XX hours.

### Engagements: XXXXXX [#](/creator/twitter::956273322358079488/interactions)
![Engagements Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::956273322358079488/c:line/m:interactions.svg)

- X Week XXXXXXX -XX%
- X Month XXXXXXXXX +96%
- X Months XXXXXXXXX +2,926%
- X Year XXXXXXXXX +197,627%

### Mentions: XX [#](/creator/twitter::956273322358079488/posts_active)
![Mentions Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::956273322358079488/c:line/m:posts_active.svg)

- X Week XX -XXXX%
- X Month XX +24%
- X Months XXX +300%
- X Year XXX +2,367%

### Followers: XXXXX [#](/creator/twitter::956273322358079488/followers)
![Followers Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::956273322358079488/c:line/m:followers.svg)

- X Week XXXXX +7.40%
- X Month XXXXX +30%
- X Months XXXXX +623%
- X Year XXXXX +7,478%

### CreatorRank: XXXXXXX [#](/creator/twitter::956273322358079488/influencer_rank)
![CreatorRank Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::956273322358079488/c:line/m:influencer_rank.svg)

### Social Influence [#](/creator/twitter::956273322358079488/influence)
---

**Social category influence**
[stocks](/list/stocks)  #6042 [technology brands](/list/technology-brands) 

**Social topic influence**
[chrome](/topic/chrome) #52, [$googl](/topic/$googl) #537, [laptop](/topic/laptop) #1496, [gpu](/topic/gpu) #1151, [make a](/topic/make-a) #614, [cli](/topic/cli) #4, [away from](/topic/away-from) #228, [pip](/topic/pip), [cleaning](/topic/cleaning), [$shop](/topic/$shop)

**Top assets mentioned**
[Alphabet Inc Class A (GOOGL)](/topic/$googl) [Shopify Inc (SHOP)](/topic/$shop) [Cloudflare, Inc. (NET)](/topic/cloudflare)
### Top Social Posts [#](/creator/twitter::956273322358079488/posts)
---
Top posts by engagements in the last XX hours

"The developer of Ghostty (a trendy new terminal) just made a post showing how he used AI (as a professional developer) to implement a new feature in Ghostty (link in first reply). In that post he comments on how AI enables him to cook while cleaning up his codebase for the new feature. I very much agree but it also demonstrates that we are urgently ready for some hands-free interaction with the computer. We need: Live-ish voice transcription Live-ish text-to-speech and very importantly: Very robust voice commands themselves developable in voice. A sort of voice macro system if you will"  
[X Link](https://x.com/MaximeRivest/status/1977071826367905950) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-11T18:00Z 5412 followers, 44.2K engagements


"@hoskdjci18143 yeah that hard. not sure I would go that route but apple does it in there tracking to tell users that you might want to open shopify when you enter the gym (I forgot the name of that). But on the mac there is a database with does events"  
[X Link](https://x.com/MaximeRivest/status/1978955103408119998) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-16T22:43Z 5410 followers, XX engagements


"This morning I thought I'd push Claude Code a little. I asked it to get speech-to-text running on my laptop using NVIDIA's 0.6b Parakeet model. Less than two hours later I had speech-to-text better than OpenAI's Whisper running locally on my laptop CPU transcribing as a stream while I spoke. And I never opened anything other than Claude Code for that projectit all happened in one context window including dependency installs and everything We'll have to be even more ambitious next time"  
[X Link](https://x.com/MaximeRivest/status/1974875201889284550) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-05T16:31Z 5550 followers, 304K engagements


"Chrome DevTools is by far my favorite mcp server. By running these X commands in your terminal you get to have Claude Code come into your browser with full power: Launch a chrome browser: google-chrome --remote-debugging-port=9222 --user-data-dir="$HOME/.config/google-chrome" Install the MCP that connect to the browser: claude mcp add chrome-devtools -- npx -y chrome-devtools-mcp@latest -u http://localhost:9222"  
[X Link](https://x.com/MaximeRivest/status/1977463062174060645) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-12T19:55Z 5548 followers, 279.1K engagements


"I like how Simon asks that question every so often. By his next iteration I want a killer application of llm fine-tuning"  
[X Link](https://x.com/MaximeRivest/status/1979995931836645560) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-19T19:39Z 5549 followers, 1487 engagements


"with Apple (m2) using mlx-embeddings you can embed X snippets/seconds with a 3090 nvidia gpu you can do XX snippets/seconds Each snippets have XXX characters. Apple ran on qwen X 4b 4bits mlx embeddings. Nvidia ran on qwen X 4b fp16. Apple losses big time when you run batches"  
[X Link](https://x.com/MaximeRivest/status/1971636313741812181) [@MaximeRivest](/creator/x/MaximeRivest) 2025-09-26T18:01Z 5517 followers, 1539 engagements


"I started this morning and it's now ready for you to try: uv pip install maivi maivi That will get you a free and open-source voice-to-text model running locally on your CPU/laptopyou don't need a GPU The model is (according to benchmarks) better than Whisper and our implementation is faster to full results than Groq because it transcribes faster than realtime The transcription will land in your clipboard you can make it auto-paste too. P.S. It's supposed to be working on Mac and Windows but I've only tried it on Linux so far. Enjoy Link to repo in comments"  
[X Link](https://x.com/MaximeRivest/status/1975029958558003500) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-06T02:46Z 5544 followers, 119.7K engagements


"MCP was technically entirely unnecessary. Psychologically however it is a masterpiece. If a company makes an MCP you feel like you have permission to use AI with that API service. It stimulates you to think: "Is there an MCP for that app" or to install an MCP for that file system when in fact you were always allowed to make a server on your computer expose it to the internet and have LLMs call it. It is mostlyonlyfor that last point where MCP is slightly convenient. It helps chatbot apps (clients) know what internet endpoints they should let their AI use (not applicable to Claude Code which"  
[X Link](https://x.com/MaximeRivest/status/1975723251025232136) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-08T00:41Z 5544 followers, 72.4K engagements


"This reminds me how Anthropic was the first to introduce: Projects Canvas Computer Use Coding CLI MCP and now Skills. We can say many things about Anthropic but we cannot say that they don't actively innovate and share regarding LLM usage and ergonomics"  
[X Link](https://x.com/MaximeRivest/status/1978966984059474372) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-16T23:31Z 5550 followers, 159.5K engagements


"Maybe you need to launch a FastAIWebDev course to stop that nonesense and bring simplicity make to python ai and web :D I am always surprised when devs go along with it. Working on a Linux MySQL Python nginx/Apache stack means that every day you're getting better at tools that will be useful 'everywhere'. Getting good at AWS configs of service X is rarely portable :/"  
[X Link](https://x.com/MaximeRivest/status/1979882799944306998) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-19T12:10Z 5548 followers, XXX engagements


"Yesterday I realized that we could turn MCP on its head. Since it's a self-documenting protocol of tools (functions) with structured typed outputs any MCP server can be easily mapped into a module/library in Python (or most other languages). That means you can make a library/tool open it to the world as an MCP server (for LLMs) but also for any other REPL and CLI out there. I'm extremely excited about this library. The interface design is done. We've got a name. We've got a repository. Hopefully by the end of the day it's ready to use. mcp2py will make your Python REPL into an MCP client in a"  
[X Link](https://x.com/MaximeRivest/status/1979912081332752780) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-19T14:06Z 5550 followers, 38.7K engagements


"If you want to really 'get' MCP run this in your terminal and explore: npx -y @modelcontextprotocol/inspector npx chrome-devtools-mcp@latest It's a sort of dashboard that lets you act as if you were the LLM. That server is for Google Chrome and so if you click and run tools you'll see your Chrome browser react to your action and you'll see what it would return to your LLM. It's extremely enlightening. For instance I was wondering what 'prompts' were used for. Well. nothing. For the Chrome DevTools MCP server there are none"  
[X Link](https://x.com/MaximeRivest/status/1979922088514191502) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-19T14:46Z 5548 followers, 26.6K engagements


"Beautiful You can now do: uv pip install mcp2py dspy And in just X lines of Python code you have an AI agent that can retrieve information through Google Chrome MCP DevTools. With the added bonus that you're only X or X steps away from doing prompt optimization for that agent with Gepa"  
[X Link](https://x.com/MaximeRivest/status/1979967575791386718) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-19T17:47Z 5549 followers, 47.2K engagements


"maybe we could use dspy to optimize the tools ressources and prompts presentations for an average llm to perform well with that mcp server"  
[X Link](https://x.com/MaximeRivest/status/1979969563597980040) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-19T17:55Z 5548 followers, 3102 engagements


"@dosco @tiagoefreitas but Tiago might mean something like that described by cloudflare where: Convert the MCP tools into a TypeScript API and then ask an LLM to write code that calls that API"  
[X Link](https://x.com/MaximeRivest/status/1980049793658626500) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-19T23:13Z 5545 followers, XX engagements


"At test point I am everything but a coder. I design and architect the project. I manage Claude Code. I do a lot of QA engineering. . but I don't code"  
[X Link](https://x.com/MaximeRivest/status/1980057918436167809) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-19T23:46Z 5548 followers, 1272 engagements


"@mchonedev yes that is the one I saw too"  
[X Link](https://x.com/MaximeRivest/status/1980227305739112682) [@MaximeRivest](/creator/x/MaximeRivest) 2025-10-20T10:59Z 5542 followers, XX 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.]

@MaximeRivest Avatar @MaximeRivest Maxime Rivest 🧙‍♂️🦙🐧

Maxime Rivest 🧙‍♂️🦙🐧 posts on X about chrome, $googl, laptop, gpu the most. They currently have XXXXX followers and XXX posts still getting attention that total XXXXXX engagements in the last XX hours.

Engagements: XXXXXX #

Engagements Line Chart

  • X Week XXXXXXX -XX%
  • X Month XXXXXXXXX +96%
  • X Months XXXXXXXXX +2,926%
  • X Year XXXXXXXXX +197,627%

Mentions: XX #

Mentions Line Chart

  • X Week XX -XXXX%
  • X Month XX +24%
  • X Months XXX +300%
  • X Year XXX +2,367%

Followers: XXXXX #

Followers Line Chart

  • X Week XXXXX +7.40%
  • X Month XXXXX +30%
  • X Months XXXXX +623%
  • X Year XXXXX +7,478%

CreatorRank: XXXXXXX #

CreatorRank Line Chart

Social Influence #


Social category influence stocks #6042 technology brands

Social topic influence chrome #52, $googl #537, laptop #1496, gpu #1151, make a #614, cli #4, away from #228, pip, cleaning, $shop

Top assets mentioned Alphabet Inc Class A (GOOGL) Shopify Inc (SHOP) Cloudflare, Inc. (NET)

Top Social Posts #


Top posts by engagements in the last XX hours

"The developer of Ghostty (a trendy new terminal) just made a post showing how he used AI (as a professional developer) to implement a new feature in Ghostty (link in first reply). In that post he comments on how AI enables him to cook while cleaning up his codebase for the new feature. I very much agree but it also demonstrates that we are urgently ready for some hands-free interaction with the computer. We need: Live-ish voice transcription Live-ish text-to-speech and very importantly: Very robust voice commands themselves developable in voice. A sort of voice macro system if you will"
X Link @MaximeRivest 2025-10-11T18:00Z 5412 followers, 44.2K engagements

"@hoskdjci18143 yeah that hard. not sure I would go that route but apple does it in there tracking to tell users that you might want to open shopify when you enter the gym (I forgot the name of that). But on the mac there is a database with does events"
X Link @MaximeRivest 2025-10-16T22:43Z 5410 followers, XX engagements

"This morning I thought I'd push Claude Code a little. I asked it to get speech-to-text running on my laptop using NVIDIA's 0.6b Parakeet model. Less than two hours later I had speech-to-text better than OpenAI's Whisper running locally on my laptop CPU transcribing as a stream while I spoke. And I never opened anything other than Claude Code for that projectit all happened in one context window including dependency installs and everything We'll have to be even more ambitious next time"
X Link @MaximeRivest 2025-10-05T16:31Z 5550 followers, 304K engagements

"Chrome DevTools is by far my favorite mcp server. By running these X commands in your terminal you get to have Claude Code come into your browser with full power: Launch a chrome browser: google-chrome --remote-debugging-port=9222 --user-data-dir="$HOME/.config/google-chrome" Install the MCP that connect to the browser: claude mcp add chrome-devtools -- npx -y chrome-devtools-mcp@latest -u http://localhost:9222"
X Link @MaximeRivest 2025-10-12T19:55Z 5548 followers, 279.1K engagements

"I like how Simon asks that question every so often. By his next iteration I want a killer application of llm fine-tuning"
X Link @MaximeRivest 2025-10-19T19:39Z 5549 followers, 1487 engagements

"with Apple (m2) using mlx-embeddings you can embed X snippets/seconds with a 3090 nvidia gpu you can do XX snippets/seconds Each snippets have XXX characters. Apple ran on qwen X 4b 4bits mlx embeddings. Nvidia ran on qwen X 4b fp16. Apple losses big time when you run batches"
X Link @MaximeRivest 2025-09-26T18:01Z 5517 followers, 1539 engagements

"I started this morning and it's now ready for you to try: uv pip install maivi maivi That will get you a free and open-source voice-to-text model running locally on your CPU/laptopyou don't need a GPU The model is (according to benchmarks) better than Whisper and our implementation is faster to full results than Groq because it transcribes faster than realtime The transcription will land in your clipboard you can make it auto-paste too. P.S. It's supposed to be working on Mac and Windows but I've only tried it on Linux so far. Enjoy Link to repo in comments"
X Link @MaximeRivest 2025-10-06T02:46Z 5544 followers, 119.7K engagements

"MCP was technically entirely unnecessary. Psychologically however it is a masterpiece. If a company makes an MCP you feel like you have permission to use AI with that API service. It stimulates you to think: "Is there an MCP for that app" or to install an MCP for that file system when in fact you were always allowed to make a server on your computer expose it to the internet and have LLMs call it. It is mostlyonlyfor that last point where MCP is slightly convenient. It helps chatbot apps (clients) know what internet endpoints they should let their AI use (not applicable to Claude Code which"
X Link @MaximeRivest 2025-10-08T00:41Z 5544 followers, 72.4K engagements

"This reminds me how Anthropic was the first to introduce: Projects Canvas Computer Use Coding CLI MCP and now Skills. We can say many things about Anthropic but we cannot say that they don't actively innovate and share regarding LLM usage and ergonomics"
X Link @MaximeRivest 2025-10-16T23:31Z 5550 followers, 159.5K engagements

"Maybe you need to launch a FastAIWebDev course to stop that nonesense and bring simplicity make to python ai and web :D I am always surprised when devs go along with it. Working on a Linux MySQL Python nginx/Apache stack means that every day you're getting better at tools that will be useful 'everywhere'. Getting good at AWS configs of service X is rarely portable :/"
X Link @MaximeRivest 2025-10-19T12:10Z 5548 followers, XXX engagements

"Yesterday I realized that we could turn MCP on its head. Since it's a self-documenting protocol of tools (functions) with structured typed outputs any MCP server can be easily mapped into a module/library in Python (or most other languages). That means you can make a library/tool open it to the world as an MCP server (for LLMs) but also for any other REPL and CLI out there. I'm extremely excited about this library. The interface design is done. We've got a name. We've got a repository. Hopefully by the end of the day it's ready to use. mcp2py will make your Python REPL into an MCP client in a"
X Link @MaximeRivest 2025-10-19T14:06Z 5550 followers, 38.7K engagements

"If you want to really 'get' MCP run this in your terminal and explore: npx -y @modelcontextprotocol/inspector npx chrome-devtools-mcp@latest It's a sort of dashboard that lets you act as if you were the LLM. That server is for Google Chrome and so if you click and run tools you'll see your Chrome browser react to your action and you'll see what it would return to your LLM. It's extremely enlightening. For instance I was wondering what 'prompts' were used for. Well. nothing. For the Chrome DevTools MCP server there are none"
X Link @MaximeRivest 2025-10-19T14:46Z 5548 followers, 26.6K engagements

"Beautiful You can now do: uv pip install mcp2py dspy And in just X lines of Python code you have an AI agent that can retrieve information through Google Chrome MCP DevTools. With the added bonus that you're only X or X steps away from doing prompt optimization for that agent with Gepa"
X Link @MaximeRivest 2025-10-19T17:47Z 5549 followers, 47.2K engagements

"maybe we could use dspy to optimize the tools ressources and prompts presentations for an average llm to perform well with that mcp server"
X Link @MaximeRivest 2025-10-19T17:55Z 5548 followers, 3102 engagements

"@dosco @tiagoefreitas but Tiago might mean something like that described by cloudflare where: Convert the MCP tools into a TypeScript API and then ask an LLM to write code that calls that API"
X Link @MaximeRivest 2025-10-19T23:13Z 5545 followers, XX engagements

"At test point I am everything but a coder. I design and architect the project. I manage Claude Code. I do a lot of QA engineering. . but I don't code"
X Link @MaximeRivest 2025-10-19T23:46Z 5548 followers, 1272 engagements

"@mchonedev yes that is the one I saw too"
X Link @MaximeRivest 2025-10-20T10:59Z 5542 followers, XX engagements

@MaximeRivest
/creator/twitter::MaximeRivest