The State of Context Engineering(dbreunig.com)
227 points by pchristensen | 57 comments
Slides and transcript of Drew Breunig's AGNTCon talk "Context Fails & Fixes," reviewing the history, failure modes, and future of context engineering for LLMs.
18 stories on the front page, newest first. Scroll down to watch the site change over time.
227 points by pchristensen | 57 comments
Slides and transcript of Drew Breunig's AGNTCon talk "Context Fails & Fixes," reviewing the history, failure modes, and future of context engineering for LLMs.
31 points by dbreunig | 13 comments
A blog post on dbreunig.com arguing that audio augmented reality, delivering the right information at the right time without looking at a screen, is on the rise.
531 points by dbreunig | 197 comments
Blog post by Drew Breunig arguing that with LLMs like Anthropic's Mythos, cybersecurity becomes a contest of spending more tokens than attackers, akin to proof of work.
330 points by dbreunig | 289 comments
Blog post by Drew Breunig asking why Anthropic's Claude desktop app uses Electron if AI coding agents make writing native apps nearly free.
74 points by itzlambda | 22 comments
75 points by dbreunig | 66 comments
162 points by dbreunig | 79 comments
444 points by dbreunig | 139 comments
Blog post by Drew Breunig arguing that DuckDB's spatial extension has made geospatial data accessible to far more people than specialized GIS tools.