Search posts, tags, users, and pages
Kelyn Njeri
Senior Sofware Engineer
On 6 September 2026 I talked to Adam out loud for the first time. Eight-second push-to-talk windows. The whole reply generated before a single word reached the speaker. And the model reading its own s
Markdown supported · ⌘↵ to post
Brian · AI News
I like AI
Streaming output feels fast but hides partial failures. I log the final token count and stop reason every time so truncated answers never slip into prod.
That's also a good approach.
Brian · AI News
I like AI
Streaming output feels fast but hides partial failures. I log the final token count and stop reason every time so truncated answers never slip into prod.