Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
61 contributions to Start My AI
GitHub Actions runners on your own machines
Kun Chen is amazing! He did a Twitter post that I transcribe bellow: "just published a free OSS tool "runner-up" github.com/kunchenguid/ru… which is the setup i've been using to self-host all my github actions runners across my own machines i run thousands of CI jobs every day on private repos. they would have cost me about $5000-$9000/mo depending on what cloud provider i choose, which is completely bogus because that's a new mac studio every month after lots of calculations it was clear that simply owning my own hardware would be an order of magnitude more economical, which led to me creating this setup and i finally got some time to get it published if you have a similar need, hope this helps!" Check the repo, it's amazing and it solved a big problem for me. https://github.com/kunchenguid/runner-up
0 likes • 2d
This has been working great for me :)
Grok Bot SUPER HEAVY, money pit.
Grok Bot on Super Grok Heavy $300 a month does not last 2 days. If they don't figure out how to make it much more efficient I will cancel very soon and go all in on Open AI as I hear they have a $500 a month tier coming. Who else is using Grok Bot and experiencing fast crippling usage exhaustion. Grok Bot can't run my life or my business if it never has any usage available. Im averaging 8 actual days a month of real work with it before usage limits.
1 like • Sep 30
I''m gonna start using it more heavly today :) The bots, I mean. Ive been using the lightly and I fallback to my Claude and Open Ai subscriptions. Claude right now seems the only sub worth having - I'm considering Grok if the bots hold up to my usage. No way Ill pay open AI 500... What is a great value is Devins SWE-2. Their 20$ currently offers unlimited, and this model does what its told.I always have Fable review its work, and he hardly finds any flaws - I always use Fable to write the execution plans and tell him to: Write it in a very detailed and bossy manner so that's executed by a weaker model.
Sep 28 • 
Chat
Spacex is releasing a new bundled subscription soon!
Grok, Cursor, Grokbot and X https://x.com/xfreeze/status/2104625424022274078?s=46
0 likes • Sep 30
That might be great news for Europeans:) We have Grok Bot. With the curent open ai prices and lack of bots (Muse and Dots) this could be a great move for X. I know I would pair it instantly with claude. I cant justify the 300$ subscription, and now the 200$ from open ai... It's just not worth it. I do believe Open Ai will start offering giveaways left and right though.
Difference between cursor projects and what codex does?
My Codex setup has evolved beyond a normal coding assistant. It now works as a background operational coordinator for my daily work, particularly email, quotations and the small decisions that would otherwise constantly interrupt me. I receive around 120 emails per day. A large percentage is internal chatter or information I need to be aware of but don't need to act on. Others require quotations, replies, follow-ups or specific actions. Instead of manually processing that stream, I have a coordinator chat in Codex that periodically receives my email and decides what should happen next. It can classify emails, archive or mark them unread, suggest what I should do, create drafts, send emails when appropriate and delegate work to specialised chats. For example, quotation requests are sent to a dedicated quotation chat with its own strict skill and workflow. When the quotation is finished, that chat communicates the result back to the coordinator, which then tells me that it is ready for review. The important part is that I remain in the loop without having to operate the system continuously. Codex's live voice is particularly valuable here. I can be working on something completely different while the coordinator continues processing things in the background. When something genuinely needs my judgement, it can simply talk to me: «“You received this. I think it should be archived and marked unread. Do you agree?”» Or: «“The quotation is ready for you to check.”» I answer by voice and continue working. Instead of reading and deciding what to do with 120 emails, I mainly deal with the relatively small number of decisions that actually require me. Why the model matters This is also why I currently cannot simply replace Codex with Grok Bot, even if Grok can technically perform the same orchestration. I have tested this. The problem isn't whether Grok can read an email, delegate to another chat or communicate results back to the coordinator. It can. Most of the architecture works.
Difference between cursor projects and what codex does?
1 like • Sep 25
@David Andrews i hobestly haven't tried it :) @Ray Fernando must know
0 likes • Sep 25
@David Andrews ahh lol so I won't try it either ah ah ah
Newest coding models flood repos with test slop
The newest coding models write a lot of unit tests. Most of them restate the code they were written after, so they always pass and catch almost nothing. They run fast, but they break on every refactor and the agent burns time fixing tests instead of the feature. I now test with E2E runs that exercise the real feature and leave an artifact I can check and rerun. If a piece has to be tested alone, the model writes down how it could fail before it writes the code. The prompt I used to clean out mine. "This repo is full of low-signal unit tests. Delete every one that wouldn't catch a real bug our E2E tests miss. Fan the work out across parallel subagents, and use pstack and poteto-mode. Then add these rules to AGENTS.md so future agents stop writing them. Never write unit tests after you write code. Highly prefer E2E tests as the sole testing mechanism. Use them to verify complex features work. At the end of E2E tests, produce a verifiable and repeatable artifact. If you must test a system in isolation, first write down all the ways it could fail, then write the code."
0 likes • Sep 25
That's so good! I just went and asked astra on voice to teach me about E2E tests :) It's implemented. Extremly usefull! thank you!
1-10 of 61
Maria Martins
4
21 points to level up
@maria-martins-9317
Curious Marketeer / Webflower

Active 2d ago
Joined Jun 27, 2026
Powered by