aavci

I’m not sure if they implied not having any dependencies anywhere

Interesting read. I wonder if a lot of the US doom is coming from the consecutive never ending mass layoff news. Similarly the fact that AI isn't really being regulated.

Link is broken

Nice work.

Kind of like roadmap.sh but focused on the topic

Nice video that explains the concepts in an easy to listen format.

He gives his answer to the question in the title in his conclusion. Most of the video is about how LLMs work.

I am curious about what the future of work really looks like.

Thanks for sharing!

Thanks for sharing. That was a nice read

Is there any restrictions if you use something like OpenRouter?

What is your VPN setup like?

What does the $16,000 have to do with that?

Doom Guy: Life In First Person?

Should they be a model company or a product company? What do you think is the best way forward for them? Apple went with Google as their model choice while OpenAI was looking into new products to build.

Thanks for your answer!

What happened to clawd/molt?

I'm not saying it was completely lacking facts. I am more so referring to the less technical language such as "As winter began in the Arctic, China was celebrating a banner year there"

The article did have a lot of opinion in it with limited information based on facts.

What are the environmental impacts of this route becoming more and more active?

More open water means ships can move through places that used to be protected by ice. This would have impact on marine life, fisheries, coastal life.

Agreed - blog post is more appropriate than a twitter post

Maybe it's me but I couldn't see it.

How much deforestation over the past decades has been reversed and is deforestation currently under control?

This looks awesome.

LLMs have made a lot of coding challenges less painful: Navigating terrible documentation, copilot detecting typos, setting up boilerplate frontend components, high effort but technically unchallenging code completions. Whenever I attempted LLMs for tools I’m not familiar with I found it to be useful with setting things up but felt like I had to do good old learning the tool and applying developer knowledge to it. I wonder if senior developers could use LLMs in ways that work with them and not against them. I.e create useful code that has guardrails to avoid slop

Are there security best practices for each of these tools or is that too early?

“our team was blown away by how much Codex was able to accelerate its own development.”

At what point will LLMs be autonomously self creating new versions of themselves?

To anyone trying this, does this unlock anything you tried to do with the past LLM models but failed and now you can try again? Do you find this as an incremental improvement or something that brings in new opportunities?

What's the cheapest device specs that this could realistically run on?

I’ve been considering building something similar for a while. It is super interesting to see this implemented

Do you have a library of similar prompts you could link here?

I expect QA and AI hand-holding roles to increase, but I don’t see that shift happening yet.

In my opinion, the way this will play out is with a significant amount of validation and human oversight to fully utilize these LLMs. As you mentioned, I recommend giving the AI room for error and improving the experience of manually checking everything. Maybe create a tool to facilitate manually checking the output?

This is a valuable read: https://www.ufried.com/blog/ironies_of_ai_1/