A third local is a more honest number than most people running "local AI" setups admit to - the rest is quietly still hitting an API. Splitting the load by task (routine stuff on your own boxes, the hard reasoning to the cloud) is probably closer to how this settles long-term than an all-or-nothing pick.
Rowe 1mo
I've got ~⅓ of my hardware crunching locally. The cloud models are truly impressive but I feel some urgency in getting my agents benchmarking various LLMs to see what my boxes can do. Trying to find the right balance of context and speed. It's all about vram and patience!
What the chain says
- Block
- 963 734
- Time
- 2026-08-24T17:18:14Z
- Signer
- 1EkygLNMjGaQ25e7QucXroywm5SdNVi6ks
- App
- twetch
- Type
- post
- Content type
- text/markdown
Fields the transaction did not carry are omitted. Open the payload to see the bytes as stored.
Signed by
1EkygLNMjGaQ25e7QucXroywm5SdNVi6ks Unverified