Rigario (@Rigario) header
Rigario (@Rigario) profile picture

Founder @holoweave. I mostly post about agents and a bit of investing. Built product orgs at CoinMarketCap, Binance, Chainlink and Zendesk.

Joined April 2012
Replying to @HandsomeHank_
I'm not sure it has ever been fixed. And this is after I've used it quire sparingly.
1
1
66
There is something up with Astra/Sol. Colleagues agree it is a lot worse last few days. Hada bug, I wasted a couple of hours on both spending >25m tokens in total, and nothing was fixed. Grok took over, spent 17m fixed it, with testing and review, solving the problem.
22
Replying to @jasonoakes
Single day use on the legacy super grok heavy plan haha. It was a bit better right after they gave their reset. Now we are back to guzzling quota again.
15
It got better right after usage was reset manually by the team. But yesterday it returned to chewing up tokens like nobody's business. Am I the only one?
1
1
60
Talked to a friend earlier today. His subscription tokens feel quite enough for him, and he genuinely doesn't understand how some people manage to completely exhaust their limits. That mystery is what prompted this post. Once you start using agents seriously to deliver software (not just as a chatty developer proxy), the tokens spread across a lot of supporting work: - Agreeing on the work (research, reading APIs, understanding what's already in the product) - Producing the artifact (code or writing) - Review - Architecting (for bigger tasks) - Testing - Daily rollup report - Updating internal docs - Memory store and recall All of this is in service of delivering the software. The actual production step is only a small fraction of the total tokens. It is a bit like a software company where most people aren't pure developers. Once more people move past lightweight use, demand is going to go through the roof. We are still very early.
1
48
Replying to @mdnlabs
On the SuperGrok Heavy legacy thing, I had to stop using it for work and just let routines run the last day or so. And I don’t even code with it haha. I have some ideas around optimizing and will have to try it out next window I guess.
1
1
60
Replying to @SamE1311025
Looks like mine is back exactly to the 67% that I was at right before the issue. Looks like my guesses were right.
1
Well at least for this isolated incident, it seems they reverted the usage limit, it might still finish twice as fast as last time, but the way this happened, it seems more bug than policy change.
6
Grok Bot is back! It reverted exactly to where my usage was before the issue happened. Seems like my generous interpretations were true.
2
2
142
After testing Grok Bot, Muse, Hermes Agent, Hark, Instinct, and OpenAI Dots on real personal assistant work, shopping, and agent coordination through Holoweave Weave... Hermes on its own computer/VM is S-tier once you customize it. For the best balance of capability, always-on access, and actually finishing jobs, Grok Bot is my top pick right now.
1
2
1
3
384
Give this to your agents now. I was mid talking to my bots about an issue and decided this explained issues better than I did. Hope it works!
how do you trust your agents' work more? copy this post/link and give it to your @bot or agent! 1. codebase improvements: this is just good software engineering - better architecture, stronger types and invariants, clear boundaries. agents love to copy what exists and take the shortest path, so make the easy thing the right thing. categorically eliminate problems through code and you won't need to think about it again. 2. static analysis: lint rules, tests, CI, verification (eg TLA+). very token efficient ways to catch issues ahead of time. 3. prose: comments, rules, AGENTS.md, skills - anything that can't be enforced and requires agent judgment. use it minimally, but do use /create-verification-skill. 4. human review: the hardest to scale. at the rate agents land code, it's pretty much impossible to thoroughly review every PR, so spend that effort on the highest leverage point, designing an environment where agents do the right thing by default. this forms an inverse pyramid: you want most of your effort at the top, least at the bottom. codebase improvements are deterministic, making it more token efficient, and lets you sleep more soundly at night. install github.com/cursor/plugins/tr… and create a new Project: 1. look through my slack/chat messages and code review comments where i've given feedback on PRs, code, architecture 2. use /recall on my past transcripts to learn how i steer agents 3. /poteto-mode use /correct and /architect on past commits to find the most common pitfalls agents fall into, then propose a plan to rearchitect the code i own so it's more agent friendly. answer open questions with prototyping rather than defer to me, and back the plan with real data. 4. before you begin, use /sharpen + /in-your-own-words and confirm this prompt with me
21