back
user profile
OsamaJaber
260karma·80submissions·October 19, 2025
recent activity (80 total)
comment
the bottleneck isn't generation, it's verification
comment
Good to see this exist. Inference providers quietly swap quant levels. Most users never check. A standard verifier from the model maker is the right move, would love to see other labs ship the same
comment
The modified MIT clause is sneakier than people think. Hit 100M users or $20M a month and you have to slap "Kimi K2.6" on your UI. That covers any consumer app worth building. Not really ope…
comment
That's why infra needs stricter internal walls than normal SaaS
comment
Small models in the browser are a different optimization problem than small models on a server.
On server you chase throughput so you batch. In browser you're stuck at batch size 1, which means k…
comment
Appreciate it :)
comment
Keep talking like that and people will colonize space
comment
MCP support is the real story here
Means you're not locked into Claude or Codex
Can plug in whatever agent you want