食堂干饭王

蹇冨璺

[Carnage @0xCarnagee]

Holy f*ck… I turned Grok Bot into my Jarvis with bots from the SpaceXAI team

it called my internet provider, sat on hold 19 min and got me −$20/mo. answered 36 DMs in my voice and closed a $250 brand deal

cancelled 4 subs I never use. merged 5 PRs while I slept. booked 6 apartment tours

6h 42m of work - 0 minutes from me

the full Jarvis prompt is at the end. Steal it before everyone starts using it

[食堂干饭王 @jenna1417]

@mletho 骑过朋友的，低频确实舒服，不轰人还自带存在感，现在回想那声音还挺上头。

[食堂干饭王 @jenna1417]

@newsyntaxezc0 meper hydration honestly got slower handling when adding water proof yes beyond heavy sticks strange

[whaley @whaleyxbt]

this shouldn't be free...

lauren tan builds grok bot at spacexsi. her pstack guide got 11K bookmarks. the whole skill pack is free

one command installs it. what each one does:

→ /teach: explains any change, diagram by diagram
→ /how: traces how a subsystem runs
→ /why: why it was built that way, from git, PR reviews, slack, sentry
→ /recall: rebuilds your recent context from chat history
→ /technical-writing: readme first, then work back to the code
→ /poteto-mode prototype: 2–3 variants behind a switcher + screenshots
→ /architect: rival designs from different models, judged, scrapped if wrong
→ /interrogate: other models try to break your diff

how to use it:
1. /add-plugin pstack (claude code works too)
2. run /setup-pstack, pick your models
3. start every real task with /poteto-mode. it calls the rest

her rule: plan with code, not abstract plans

save this ↓ her full setup (2,500 PRs in a month) is in the article below

[West Lord @MyWestLord]

This guy is an Artificial Intelligence engineer who took the 6 most powerful AI, connected them, and built CrawlBot.

CrawlBot is one bot that makes 6 AI work together as a team on the same task at the same time.

Grok Bot reads X 24/7 and finds what people complain about.
REA researches every competitor and their prices.
Opus 5.5 plans the product and writes the code.
Jev runs the tests and fixes bugs on autopilot.
Dots writes the landing page and the ads.
Obsidian remembers everything so nothing gets lost.

You give CrawlBot one goal, and it splits it into tasks, sends each task to the right AI, collects the results, and passes them to the next one.

Everything runs live in the terminal, so you see who is working, what is done, and how much it costs.

In the first session it analyzed 4,120 posts, mapped 18 competitors, wrote 2,314 lines of code, passed 64 out of 64 tests, and put the app live in production.

It took 7 hours 40 minutes and $233 while he was asleep the whole time.

A startup team used to mean 5 people and 6 months, and now it is one bot.

Would you let it build your product while you sleep?

[West Lord @MyWestLord]

Grok turned $1,000 into $9,640 in 10 days while I didn't open a single chart.

No signals group. No $997 course. No 3 AM alarms. Just 1 free GitHub repo, 9 AI agents and 1 Grok brain.

I test 3-4 AI trading repos a week. Most die in 48 hours. This one made me close every other tab.

It's called HyperGrok. 9 agents vote on every trade before it fires: scan, research, X sentiment, thesis, risk, sizing, execute, review, kill switch. If 2 sources don't back the thesis, no trade.

Setup took 12 minutes:
1. Clone the repo.
2. Add your Grok API key.
3. Max 15x, max 2% risk per trade.
4. Paper mode on.
5. Walk away.

I went to the gym. Took a weekend trip. Slept 9 hours. Grok ran 9,840 scans.

BTC +$410. ETH −$220. SOL +$860. HYPE +$1,730. DOGE −$310. PEPE +$2,050. BTC +$1,240. WIF +$2,880.

$1,000 → $9,640. 9.6x in 10 days. Your signals group charges $99 a month to lose to a free repo.

The part nobody posts: 1 WIF trade did 33% of the work. Pull it out and the run ends at $6,760. Still 6.8x, with 2 losers. Paper fills, no fees, no slippage.

The bot traded. I lived.

Would you let Grok trade your $1,000, or keep clicking buttons yourself?

[食堂干饭王 @jenna1417]

御姐这个形容有点准，但我觉得它是那种不太主动搭理人的类型

[小芽的懂车小世界 @Lmg_cito]

石家庄今天试MV Agusta街车，像高级时装秀上的御姐，车身线条细得很讲究，停着就已经够抓眼。真正给油以后又多了点不肯迁就人的脾气。唐山、保定、邯郸想看完整动态表现，主页继续。

[食堂干饭王 @jenna1417]

@Maya_Jey 听说这代把骑姿调得更靠前了，所以看着凶但上手没那么吓人

[食堂干饭王 @jenna1417]

@aqwlord 对，越看越有味道，先收藏起来，有机会跟作者去试试看。

[食堂干饭王 @jenna1417]

这条让我对它的低转印象改观不少。

[小橙的爱车小笔记 @noodles_69]

杭州今天骑凯旋Bonneville，有点成熟女老师的英伦味，长油箱、平座垫，看起来温柔得很有分寸。低速安静，高一点转速又会悄悄活起来。宁波、绍兴、嘉兴，更多驾驶感受去主页看。

[小桃的懂车小世界 @JCButala84]

石家庄今天试川崎Z系街车，像个短发御姐，黑绿车身站着就有距离感，油箱夹起来却很贴。低转还能陪你温柔走，右手再深一点立刻换脾气。唐山、保定、邯郸想看完整动态表现，主页继续。

[食堂干饭王 @jenna1417]

@Purplezmusic 户外学姐这个形容我先笑为敬，画面感一下就来了。

[食堂干饭王 @jenna1417]

@cletus1peanut2 二手无极复古这个价位区间，机械稳比漆面亮更值得关注，同意这个侧重点。

[食堂干饭王 @jenna1417]

@Greshamtrade found a leather jacket for six bucks last weekend, still smug

[Gresham @Greshamtrade]

ex-SpaceXAI engineer shared his best tricks for getting more out of Grok Bot, and this is a f*cking goldmine

his Grok Bot setup went from 100,000 to 12,500 tokens per task. 8x less usage, fewer failed runs, and 10x more usable results from the same budget

20 GitHub repos he used to cut costs and improve his Grok Bot’s results:

01 JSON Repair → fix malformed JSON in code before asking the model to generate the entire response again
https://t.co/YtCiQDmxg3

02 Docling → turn PDFs and office documents into structured content, preserving layout and tables so your bot gets cleaner material to work with
https://t.co/q9QLAUpddg

03 PyMuPDF4LLM → extract PDFs into Markdown, then select the pages and sections your task needs instead of loading the whole document
https://t.co/xBuNivZuko

04 LanceDB → store searchable document chunks and retrieve relevant evidence for each request instead of attaching the entire archive
https://t.co/YF8jz6TkPM

05 FastEmbed → generate embeddings locally with supported models, reducing reliance on paid embedding calls when indexing and searching your material
https://t.co/Hg4VBOPpUT

06 FlashRank → rerank search results before generation so your bot reads the strongest passages rather than every vaguely related match
https://t.co/GpDbGy2Kmv

07 datasketch → detect near-duplicate text with similarity search, helping your pipeline remove repeated material before analysis
https://t.co/cDhzBfyigI

08 joblib → cache expensive Python function results on disk and reuse them when the inputs match, avoiding repeated preprocessing
https://t.co/ZHbDpD7HE3

09 RQ → send background jobs to Python workers so code handles the queue while model calls happen only inside tasks that need them
https://t.co/sdFI4K3aHS

10 Instructor → extract answers into typed fields and validate them automatically. set a retry limit so a failed extraction stays bounded
https://t.co/EcECZnYLLy

11 Outlines → constrain supported model outputs to a defined structure, reducing formatting failures that trigger another generation
https://t.co/3XozyDzMRI

12 Guardrails → apply explicit input and output checks, catching configured failures before a response moves into the next workflow step
https://t.co/chmPriEzfo

13 DSPy → optimize prompts and examples against a defined quality metric, then test whether cheaper calls can meet your requirements
https://t.co/JKFb4x1FqR
14 OptiLLM → test reasoning strategies on connected models and keep the approach that delivers better results within your task budget
https://t.co/4kGqOU0Y04

15 vLLM → serve compatible open models with batching and efficient memory management when you run your own API workers
https://t.co/0WvIReSQV3

16 SGLang → run compatible self-hosted workers with optimized serving and prefix reuse for requests sharing the same starting context
https://t.co/nntaOhi9xy

17 LMCache → reuse stored model attention state on compatible inference servers, reducing repeated processing of shared context
https://t.co/sf0JAPm0P1

18 DeepEval → test cheaper calls and revised prompts against repeatable checks before trusting them with the full workload
https://t.co/uCp2tcAE8v

19 Ragas → evaluate retrieval and generated answers so shorter context doesn’t quietly turn into missing evidence or worse responses
https://t.co/vgCSSQRYNk

20 Laminar → trace instrumented agent runs and inspect the calls behind slow, expensive, or failed tasks before deciding what to change
https://t.co/UjnCDkIoAT

connect the tools through your workflow code, terminal, or supported MCP integration. use serving tools for your own compatible workers and API tools for calls you control

start with one recurring task. remove duplicate inputs, retrieve better evidence, and compare accepted results against the full cost of the run

clean inputs → reusable work → checked outputs → fewer expensive repeats

save this before your next upgrade

the full course below shows 7 fixes to get more finished work out of the same Grok Bot plan ↓

[食堂干饭王 @jenna1417]

@NASCAR @phoenixraceway @TylerReddick Nice work

[食堂干饭王 @jenna1417]

@N01ennn Love this

[食堂干饭王 @jenna1417]

@Asteri_eth Nice work