runesleo

vip
Active for: 8.7y
Peak Tier 6
No content yet
Did you claim those $100 from the Grok bot?
I originally just wanted to connect the X paid API to Grok Bot for searches / timelines / mentions.
I added $25 to try it, but total showed approximately $123.
Only after breaking it down did I understand:
• prepaid ≈ $23.7 → the remainder of what I added
• free ≈ $99 → the starting credits granted when connecting (expires in about 1 year
Official statement on 8/29: Paid Grok Bot users get free X API credits to start
The official amount wasn’t fixed; the image above shows my actual test. Check free before connecting, and don’t be tricked by total int
post-image
  • 1
Ever since I got MCPX, I’ve genuinely had this feeling lately:
It’s like I’ve unlocked “unlimited usage” for ChatGPT.
Of course, it isn’t actually unlimited.
The Chat mode itself already has a pretty generous quota, and after installing and configuring MCPX, many things that originally required me to switch software, find tools, or run commands myself can now be done directly in Chat.
And I think the best thing about MCPX isn’t that it “adds another new tool.”
It’s precisely that once it’s installed, you can even forget MCPX exists.
You can keep talking to ChatGPT normally, just like before:
H
post-image
Lately, everyone on X has been joining the Thin Muscle Club
I’m checking in too
post-image
I recently ran into a very strange problem:
I was clearly using a regular Chat, and after connecting an MCP tool I had been using for a long time, the same conversation would somehow turn into Work midway through.
It wasn't a new Work session, nor was “Work” part of the name of one of my own background tasks. The original conversation really did gain a “Work” label in ChatGPT's sidebar.
At first, I suspected that mechanisms such as remote execution, asynchronous tasks, or long-running tasks had triggered some kind of automatic upgrade in ChatGPT. So I went ahead and broke the problem down, ope
post-image
When a robot is about to fail, humans temporarily take over to correct a few steps. Are those few steps really worth teaching the model?
@axisrobotics A single-task simulation experiment report published on August 19 included the following results.
The task was to place a piece of tofu on a plate. The project team tested on the same batch of 480 new starting states:
• Original model: 40.0% success rate
• Directly learning the complete human correction process: 36.7%
• Training on filtered short correction segments: 48.3% (average across three training seeds)
At least in this comparison, direct
Today I used up the entire GPT-6 quota included with ChatGPT’s $200 Pro plan.
At first I thought there might be some kind of bug, but after checking OpenAI’s newly updated official documentation and digging through the quota status in my account, I realized:
Although GPT-6 Astra is called GPT-6 Pro in ChatGPT, the $200/month Pro subscription actually only includes 200 messages / week.
Not 200 messages per day—200 messages per week.
My account has now directly hit limit=200, GPT-6 Pro has been restricted, and ChatGPT has automatically fallen back to GPT-5.6 Thinking.
More interestingly, the $20
After AI makes execution cheaper, what a one-person company lacks most is not hands, but attention that hasn’t been consumed by operations.
Writing code, revising drafts, creating visuals, and running analyses are rapidly becoming general-purpose capabilities.
This can easily create an illusion: since AI can do everything, one person should do everything themselves.
But execution capacity has expanded, while attention has not expanded with it.
Building more systems, chasing more tools, and turning every step into something “enterprise-grade” may ultimately just give yourself more things to mai
I turned my X bookmarks into an Agent inbox that processes them automatically.
From now on, when I see something worth saving, all I need to do is bookmark it.
The Agent handles the rest:
1. Periodically read new bookmarks
2. Remove duplicates and determine whether they have value
3. Assign them to research, content, product, tasks, or no action needed
4. Have downstream workflows actually produce results
5. Record an acceptance receipt
6. Once explicitly enabled, automatically remove bookmarks that have been fully processed
7. Reopen the original post to confirm that the bookmark was actually
Recently, I’ve been working on a very specific experiment: letting an AI Wallet manage LP positions on Robinhood Chain by itself.
What I want to build is not an APR leaderboard, nor something that automatically rushes into whichever pool has the highest yield, but an Agent that can answer a more realistic question: which pool is this money most worth being in right now after all costs are deducted?
Robinhood Chain now has more than just US stocks / USDG. There are also Meme / USDG, US stocks / Meme, different v3 / v4 pools, new pools, and different fee tiers. The biggest problem with manually
USDG+0.02%
MEME+2.87%
HOOK+0.45%
I may have genuinely pushed ChatGPT Pro into territory most people never reach.
I've had a question for the past two weeks:
Exactly how much capacity does ChatGPT's Chat have?
Because my Codex / Work can often burn through the weekly allowance down to 0, while Chat keeps working normally.
I searched online for a while, but the answers were all over the place: some said Pro was unlimited, some said dozens of messages every few hours, some treated figures obtained from plugin statistics as official limits, and others assumed that once Work was used up, you could switch to Codex and keep getting
CODEX-9.51%
OPENAI+2.45%
I seriously calculated the August bill for my “AI × Crypto one-person company” for the first time.
Right now, it’s basically just me + AI handling:
research, development, product, content, operations, business development, and automated execution.
So I’m also quite curious:
Is this whole AI setup actually helping me make money, or is it simply burning through subscription fees every month?
August operating revenue: $1,791.70
Mainly from:
- Prediction market products / paid content I created: $697
- Business partnerships / content bounties: $850
- Affiliate / Referral: $120
- X Creator Earnings
post-image
A sudden surge in website traffic is not necessarily good news.
During a weekly audit, I found:
The traffic dashboard looked great, but Headless browser and traffic from anomalous regions had increased significantly, while clicks in Google Search Console had not increased in sync.
This means:
UV ≠ real people
Real people ≠ valid readers
Increased traffic ≠ website growth
Now I only perform 4 layers of reconciliation:
1. Browser UA: What percentage is Headless?
2. Geography: Is it unusually concentrated?
3. Referrer / UTM: Where is the traffic coming from?
4. GSC: Are search impressions and cli