luebken.bsky.social
CPO at emma.ms - talks about cloud technologies - http://linkedin.com/in/luebken/
3,846 posts
162 followers
217 following
Prolific Poster
Conversation Starter
comment in response to
post
e.g.
$ youtube_transcript_api bTVavLFH7XQJMN9D9UVZn4 --format text | llm -s "These are the captions of a presentation at KubeCon 2025. Please summarize it."
Michael Krenshaw, a staff software engineer at Intuit and an Argo CD lead, shared the progress and future of Argo CD at KubeCon 2025.
comment in response to
post
wish our’s were on time.
comment in response to
post
you should try cross country train rides ;-)
comment in response to
post
We need a vendor independent SSO bringing context to all tools.
comment in response to
post
"Act as the function designer, the LLM does the work of building the body to my specification."
"Remember it’s a conversation. They’ll never complain at being told to refactor it!"
"LLMs are no replacement for human intuition and experience."
comment in response to
post
@simonwillison.net great post.
In your process, you explicitly put human in the loop. Do you think that is sufficient to gain intuition and experience? Or do we need to adopt some new practices? e.g. using LLMs to quiz us?
comment in response to
post
Reminds me of "Cool URIs don't change". But love it how you take this to the next level. Smart, connected building blocks.
comment in response to
post
If you have uv installed this means you can start chatting with a small model without first installing anything at all - this command will create an ephemeral virtual environment, install the necessary pieces and start a chat UI running in your terminal:
uvx --with llm-smollm2 llm chat -m SmolLM2
comment in response to
post
A colleague stopped because code gen made him lazy.
comment in response to
post
Thanks for encouraging folks to give it a try. It's a new paradigm. It's hard for software engineers to work with the probabilistic characteristics of LLMs.
comment in response to
post
You need to feed the machine. - Agile User-Stories are meant to be a place holder for conversations. I wonder how they need to be adapted when GenAI in place.
comment in response to
post
My hack of 2024: Driving. You can’t look at a screen. But you can listen. And with ChatGPT you can take notes & brainstorm.
comment in response to
post
What about bringing back baby steps? Currently I find myself much more consequential about them. Just to have more control on what’s happening and understanding the impact.
comment in response to
post
The tool building is interesting. Is this a temporary / early adopter phenomenon?
comment in response to
post
I would change Maximize to Manage contextual awareness. I find it useful to be in control on what I send as context. It focuses the area „we pair on“.
comment in response to
post
Thx for the pointer. I'm assuming tidyfirst.substack.com/p/forest-and...
comment in response to
post
I'm only applying AI code tools in areas I'd either know or I explicitly want to explore.
comment in response to
post
I love the audio interface to ChatGPT. Still looking for alternatives to try.
comment in response to
post
Great and insightful post. Thanks.