deno
Joined 17 years ago
Joined 17 years ago
Subagents can spawn with other profiles e.g. scout (uses @smol) and reviewer (@slow). You can set SOTA with higher thinking for @slow and Deepseek with lower thinking for @smol or something even faster/cheaper.
There's also weirdly named /vibe mode that gives explicit instructions to the main model to act as an orchestrator but I find this unnecessary if your main is SOTA, they are already super eager to spawn subagents by default.
I still use SOTA for the main model though, but also I'm perfectly aware it's mostly out of FOMO.
Deepseek is more than enough for default subagents though. Any well defined and verifiable task and there's absolutely zero difference between SOTA and good-enough models. Used to be just speed, but Deepseek is fast.
Sol and Opus both are quite eager to use subagents and since the subagent tasks are often well specified and then verified by the main model there's hardly any advantage to using anything better for the subagent anyway, so IMO it's a no-brainer.
For me switching the main model to Kimi K3.1 Pro would put me towards 100% open, but I don't know if it uses subagents effectively. Any other open models I noticed just don't utilize them very much.
But who knows what the agent was trying to do. It could really have decided the TV show was so bad no one should see it. There's no details.
Or it's bad and it's tax evasion.
I would also advise against buying Gemini if you have any other Google services, because you get banned across board if they don't like something. To use Google it's best to first migrate off of Google.
Otherwise great product, I really like and would recommend Gemini. The usage is also very generous, at least Flash models.
FTFY
At least that's the conclusion I've arrived at at some point, but I don't remember what was the exact use case anymore.
However there are still several global IPv4 ranges that are not local reserved ranges but are effectively reserved and you could use them if you really want to without any issues.