Full Width [alt+shift+f] Shortcuts [alt+shift+k]
Sign Up [alt+shift+s] Log In [alt+shift+l]
8
Large language models have gotten much better at thinking in the past few years. Billions of dollars have been spent to study how they think…
6 days ago

Improve your reading experience

Logged in users get linked directly to articles resulting in a better reading experience. Please login for free, it takes less than 1 minute.

More from seangoedecke.com RSS feed

Using LLMs effectively isn't about prompting

When people talk about using language models effectively they mainly talk about prompting: sharing great prompts, or lists of tips for…

12 hours ago 2 votes
To avoid being replaced by LLMs, do what they can't

It’s a strange time to be a software engineer. Large language models are very good at writing code and rapidly getting better. Multiple…

6 days ago 8 votes
Engineers who won’t commit force bad decisions

Some engineers think it’s a virtue to remain non-committal in technical discussions. Should our team build a new feature in an event-driven…

a week ago 12 votes
Good engineers are right, a lot

Amazon infamously has a leadership principle where they say “good leaders are right, a lot”. It’s unclear to me how useful it is about…

2 weeks ago 12 votes

More in AI

Using LLMs effectively isn't about prompting

When people talk about using language models effectively they mainly talk about prompting: sharing great prompts, or lists of tips for…

12 hours ago 2 votes
AI #104: American State Capacity on the Brink

The Trump Administration is on the verge of firing all ‘probationary’ employees in NIST, as they have done in many other places and departments, seemingly purely because they want to find people they can fire.

21 hours ago 2 votes
GenAI in two words: ”Success Theater”

Success Theater

17 hours ago 1 votes
Go Grok Yourself

That title is Elon Musk’s fault, not mine, I mean, sorry not sorry:

2 days ago 3 votes
Grok 3 Beta in Shambles

Maximal Truth still seems far away

2 days ago 3 votes