🌩️ LLMs are breaking 20 year old system design — /dev/knill｢ LLM responses are not deterministic, and are not cheap. If you’re paying for tokens, you don’t want to waste them because the client went into a train tunnel and the connection dropped. You also don’t want to have to thread every token through your database, just to make it resilient to client connection issues ｣https://zknill.io/posts/llms-are-breaking-20-year-old-system-design/#ai #llm #networking
Related
Go Ed go!Negative unit economics is very ungood when you have a capital-intensive industry buildout.https://www.youtube....
Go Ed go!Negative unit economics is very ungood when you have a capital-intensive industry buildout.https://www.youtube.com/watch?v=zbKDmkJPVvI#ai #market #bubble #llm
RakuOS fixes the one thing that annoys me most about immutable Linux distrosImmutable Linux is the future of OS security...
RakuOS fixes the one thing that annoys me most about immutable Linux distrosImmutable Linux is the future of OS security, but the current distributions do have one particular limit...
AI NEWSWIRE: #WOW... Dust off the M2 #MacBook #BOOM... The folks at #Google just shrunk 31GB of #AI memory down to 4GB.....
AI NEWSWIRE: #WOW... Dust off the M2 #MacBook #BOOM... The folks at #Google just shrunk 31GB of #AI memory down to 4GB... https://techstartups.com/2026/06/06/google-shrinks-ai-memo...