Kodie Dower

Words guy at @coderhq.

Tweets on tech. Catch me outside in the PNW.

Former @Anacondainc, @NinjaOne, @LaunchSquad, @GG_Advisors | @UW alum

[Kodie Dower @KodieDower]

@benlimner @businessbarista Which version of whisper are you using? I used it recently and it did not get time stamps from the video, only the transcript.

[Kodie Dower @KodieDower]

@aryanXmahajan LINKEDIN

[Kodie Dower @KodieDower]

@tomcrawshaw01 SKILL

[Santiago @svpino]

English is the hottest programming language in the world!

MongoDB just released its MCP server, and literally anyone can now query data without knowing anything about databases.

Out of everything you can do with this MCP server, there are two specific reasons I'm very excited about it:

First, it's the ability to give an AI assistant access to the context stored in your database.

This is huge for those of us using Claude Code or Codex to write code, because these assistants can now access your MongoDB database to process and understand your data as it is.

Second, you can now write natural language queries. This allows everyone and their mom to query data without knowing anything about databases!

If you know English, you are all set.

By the way, you can use scoped service accounts and granular permissions to control which tools get read-only or write access to your data. This is critical, and I wish more companies would do the same.

Here is a link to the MCP server GitHub repository: https://t.co/xeDmidlLl4

Thanks to the @MongoDB team for collaborating with me on this post.

[Kodie Dower @KodieDower]

@blvckledge product

[Kodie Dower @KodieDower]

@jasminelocalseo LOCALRANK

[Kodie Dower @KodieDower]

@JulianGoldieSEO YES

[Samruddhi Mokal @samruddhi_mokal]

This AI Video Factory Generated 2M+ Views in 30 Days

While you were spending 8 hours editing one video, this N8N automation was creating 25 POV videos that made viewers feel like they were living the experience themselves.

It doesn't just make videos. It becomes a content empire.

Here's what this N8N beast does:
- Takes one topic and generates 5 POV scene sequences
- Creates hyper-realistic images using Flux AI
- Transforms images into cinematic video clips with Kling
- Generates matching ambient soundscapes with ElevenLabs
- Merges everything into professional videos with Creatomate
- Auto-uploads to YouTube with optimized titles/descriptions
- Tracks production pipeline in Google Sheets
- Runs completely hands-free while you focus on strategy

This isn't Canva or CapCut with basic templates.

It's a weaponized POV content factory that works 24/7.

While others pay $10K/month for video teams, you'll own this system forever for zero cost.

Just import the JSON into your N8N instance and watch your content empire grow.

If you're tired of inconsistent posting and want videos that make viewers feel like they're part of the story, this changes everything.

Comment "N8N" + RT + Like
I'll DM you the complete automation
(Must be following for my AI agent to DM you)

Skip this and go back to posting once a week with 12 views.

[Kodie Dower @KodieDower]

@samruddhi_mokal N8n

[Kodie Dower @KodieDower]

I'm sorry, but 1-2 weeks per YEAR + is insanely sad for this generation. Don't normalize this madness. 1 week off is a normal amount of time a corporate employee would take per quarter.

[Merriam-Webster @MerriamWebster]

'Vacations.'

The word is 'vacations.'

[Javier Corrales @jcorrales2011]

All my life I have studied democratization and autocratization. My 1st field trip was to newly democratic Argentina. I then added autocracies to my portfolio: Cuba, Ven, etc. I think I can recognize the stages of transition to authoritarianism. Here are the boxes checked off.

[Kodie Dower @KodieDower]

This sucks. I used it last year and it literally saved me $200. Worked perfectly and was easy and straightforward.

[Brian Allen @allenanalysis]

Interesting timing, isn’t it? Musk’s “Department of Government Efficiency” rolls out a plan, and suddenly NASA’s future is on the chopping block—right as SpaceX stands to gain.

This isn’t about efficiency; it’s about funneling public resources into private pockets.

[CQ @coketweet]

Tim Walz is the dad an entire generation wish they had instead of the one they lost to Fox News.

[derek guy @dieworkwear]

Mongolia's Olympic uniforms are lovely. But what's up with the wording on this tweet? Is the insinuation that we don't do the same? Let's talk about how the USA Olympics uniform connects to our heritage, culture, and history. 🧵

[Kodie Dower @KodieDower]

Favorite part of a vacation is finding the local print news and zines at the coffee shop.

[Kristin Merrilees @kristnmerrilees]

local news is good

[Sophia Yang @sophiamyang]

Corrective RAG with @langchain LangGraph and @MistralAI.
- Grade documents for relevance relative to the question.
- If any are irrelevant, then we will supplement the context used for generation with web search.
- For web search, we will re-phrase the question and use Tavily API.
- We will then pass retrieved documents and web results to an LLM for final answer generation.

Thanks so much @RLanceMartin @hwchase17 for providing such an amazing notebook in our Mistral Cookbook: https://t.co/9sBJbR229u

[Rowan Cheung @rowancheung]

OpenAI released their own Prompt Engineering Guide.

The guide is useful for anyone trying to maximize LLMs. I'd recommend it.

Here's the 6 strategies they outline for getting better results from GPT-4:

[Patrick Loeber @patloeber]

Want to run LLMs locally on your Laptop?🤖💻

Here's a quick overview of the 5 best frameworks to run LLMs locally:

1. Ollama
Ollama allows you to run LLMs locally through your command line and is probably the easiest framework to get started with.

Just use the installer or the command line to install it. Then you can type `ollama run modelname` and it starts an interactive session where you can send prompts.

It supports all important models like llama2, mistral, vicunia, falcon, and many more. And trying out new models is as easy as running `ollama pull modelname`.

🔗https://t.co/xFJTdcLKWn

2. GPT4All
A free-to-use, locally running, privacy-aware chatbot. This is kind of a ChatGPT clone that comes with a nice UI and installers for every major operating system.

You can also download embedding models and upload local documents that the model can use to retrieve information.

🔗https://t.co/dISWhv0IwN

3. PrivateGPT
Similar to GPT4All, PrivateGPT also comes with a nice UI to chat with LLMs. Its focus does not lie on trying out many different models, but rather on interacting with your own documents 100% privately.

It provides a nice @Gradio frontend where you can easily upload your files and then query the documents.

🔗https://t.co/SXYDiGTdlI

4. Llama.cpp
LLama.cpp, created by @ggerganov, is a port of Facebook's LLaMA model in C/C++. This is probably the goat of all local LLM frameworks and to my knowledge was the first project that allowed to run LLMs easily on a MacBook.🐐

Today, it not only supports the first Llama model but also all other major LLMs.

It’s also worth mentioning that thanks to this project there is a new model format - GGUF - that is used in all previously mentioned frameworks, too. So this project enables the other frameworks.

It is a bit more tricky to get this running since you have to clone the repo and build it from source, and also have to obtain the model weights separately and run some scripts to convert it to the correct format.

The easiest way I’ve found to get started is to download these already converted and quantized Llama 2 models from @huggingface, thanks to @TheBlokeAI: https://t.co/2zkoy7kKsJ

🔗https://t.co/iRKG1SYASb

5. LangChain @langchain
LangChain is a framework for developing applications powered by LLMs and is not focused solely on running LLMs locally.

But among its many features it also provides a whole guide about running LLMs locally. It shows how to import Ollama, Llama.cpp, and GPT4All into Langchain to build more complex applications on top of it.

This approach involves more coding but it also offers the most flexibility.

🔗https://t.co/FZhZh2zn6u

---
If you enjoyed this thread, I also have a video version with a short demo of every framework: https://t.co/PfLUaxwq4q

[Anaconda @anacondainc]

Looking for help getting started on your own gen AI apps? 🪄

Our own @JessHaberman is joining friends at @SnowflakeDB & @streamlit for an in-person meetup in Boston designed to help launch your AI journey.

📆 The meet-up is Dec. 5, 6-8pm ET!

Learn more below! 👇