> running things in production/self hosting is more annoying than just paying like 20-200/month

This is an important point. As people rely more on AI/LLM tools, reliability will become even more critical.

In the last two weeks, I've heavily used Claude and DeepSeek Chat. ChatGPT is much more reliable compared to both.

Claude struggles with long-context chats and often shifts to concise responses. DeepSeek often has its "fail whale" moment.

> In the last two weeks, I've heavily used Claude and DeepSeek Chat. ChatGPT is much more reliable compared to both

Which reliability problems did you face? I heard about connection issues due to too much traffic with Deepseek, but those would go away if you self-host the model.

Obviously the reliability problems would go away if you self-host but the "point" is most people rely on external providers because they can't locally run models of similar quality. So what do you do if deepseek cuts you off? For most getting 12? H100s (for the 671b) is essentially impossible.

You use a Deepseek model not hosted by Deepseek, but another provider (e.g. DeepInfra currently). Hopefully a robust provider market will emerge and thrive, even if open models start thinning out.

Have people tried using R1 for some real-world use cases? I attempted to use the 7b Ollama variant for my UI generation [1] and Gitlab Postgres Schema Analysis [2] tasks, but the results were not satisfactory.

- UI Generation: The generated UI failed to function due to errors in the JavaScript, and the overall user experience was poor.

- Gitlab Postgres Schema Analysis: It identified only a few design patterns.

I am not sure if these are suitable tasks for R1. I will try larger variant as well.

1. https://shekhargulati.com/2025/01/19/how-good-are-llms-at-ge... 2. https://shekhargulati.com/2025/01/14/can-openai-o1-model-ana...

This is the same approach we took when we added LLM capability to a low code tool Appian. LLM helped us generate the Appian workflow configuration file, user reviews it and make changes if required, and then finally publishes it.

I also built something similar using yt-dlp and llm CLI and wrote a post about it https://shekhargulati.com/2024/07/30/building-a-youtube-vide.... Script here https://github.com/shekhargulati/llm-tools/blob/main/yt-summ...

I am author of this post. Let me know if I can answer any question related to the post.

I did something similar in 2016 where I wrote tutorial on new technologies almost every week https://github.com/shekhargulati/52-technologies-in-2016. You learn a lot but as you don't end up using them you forget them .

Cool idea but I noticed you stopped after week 43.

What caused you to 'break the chain'?

Was it getting a chore just to come up with technologies to explore?

I will not start with programming but will focus on:

1. Learn how to build a good understanding on a subject. As I am growing old, I feel I am in hurry to grasp more rather than deeply learning stuff

2. Second important area for me will be how to effectively communicate my point point of view and listen to other.

In short, I will work on my soft skills more.

I also ran couple of such series:

2013: 30 technologies in 30 days https://shekhargulati.com/30-technologies-in-30-days/

2016: 52 technologies in 2016 https://github.com/shekhargulati/52-technologies-in-2016

I am author of this series. This series has been a great experience for me to learn new things and apply the learnings in professional projects.

Same here this is a very bad blog. I don't see what you can learn from this tutorial. If you want to learn Java I wrote a series https://github.com/shekhargulati/java8-the-missing-tutorial covering new features of Java 8.