Agents, audits, loops & logic
Joined June 2014
- Tweets358
- Following1.1K
- Followers1.3K
- Likes2.6K
Most times it’s issue of getting lead to spawn agents organically in the first place but once it does just leaves them around even if task is finished.
Often I have 1 lead handle multiple isolated driver agents under it for frontend/backend/design/etc… but I typically have to remind lead to cleanup or be more proactive with its agent steering.
Got happy for a second but then realized opus 5.5 max does all I need and more....
5 hour limit now much harder to hit, good change so far it seems
We're sorry for the rate limits and unnecessary quota consumption on the K3.1 Pro subscription plan. These were our issues, and we should have fixed them sooner.
Today, every subscriber on every plan gets a one-time usage reset, restoring 25% of their monthly quota (usage below 25% resets to zero), equal to one week of usage. Your usage bar will reflect this adjustment by end of day PST.
We've also adjusted the plan's parameters and are reducing unnecessary subagent calls and output length, so your quota goes further.
Thank you for your patience while we put this right.
Chief executive of yahoo and first female engineer at google but can’t come up with 3 bullets points about her own daughter.
Who’s fault is this:
A. Ai
B. Mom
C. Daughter
D. All of the above
mine makes the agent send me every secret it has access to, rotate the keys, and send me the new ones too
Agentic steering for managing and maintaining fleet. Lots of times Astra just spins up at start and doesn’t actually ever close them out and properly keep tabs as things progress, opus threads more aligned to individual tasks and same 5 don’t stick around until manually archived
Specialized tooling and harness is going to be large factor since models will just waste $ like crazy if starting from blank slate + higher chance to miss things without a proper framework to follow.
Security as a service probably becomes it's own thing with how fast space moves
Just got an email from openai telling me that I was getting $200 plan usage limits.
still not touching codex until they fix things with a major update + model release.
but happy now that mystery of missing compute is solved.
Spending $500/m so I can use sol 6.1 ultrafast for 3 hours and do 4/35 items on my to-do list before I run out of usage for the week.
sidenote: ultrafast 10x+ faster and not ~8x?
can we pls speedup regular models here @thsottiaux my local toaster is faster than 6.1 sol default
I've been thinking about this a lot lately.
Whenever I get stuck, I start another experiment.
AI has given me more freedom to start on ideas at a faster pace than I can keep up with, so I'm constantly frustrated.
I can't confirm yet if I'm getting more done or just busier
Grok 5 powered Optimus bot will be able to do this now thanks to this guy providing HD training data.
After trying to use dots once again I can confirm it is just not worth the compute waste at this point.
Ask for a simple checkup on my projects and it takes 3 hours and 5+ messages of various errors and then just tells me it decides to stop the report halfway to "save credits"