🇪🇸 (Professionally Online since 94) Serial Entrepreneur, Investor & Founder, Soft Engineer, Lawyer, Freethinker, Contrarian & Autodidact.
Earth
- Tweets 31,610
- Following 373
- Followers 1,220
- Likes 3,207
Pinned Tweet
Awesome episode with @KrisHolten on the SEO Show hosted by @servicescaling
🔥Casino SEO Secrets
( BTW if you want to test the Organic Rankings Boost via Virality Signals mentioned at the end of the podcast... is also available on @Ctrify_com together with the ultra-relevant and high authority websites generation for exclusive backlinks 🚀📈)
theseoshow.co/episode/090/
1
1
18
3,334
📈 ChatGPT 6.1 Sol Max 48h usage:
It is not smarter than Astra but is less dumb.... Also is 40-68% slower ☠️☠️
‼️Is not all savings! @OpenAI reduced the tokens per second for 6.1
On same 2 threads working non stop:
4
9
1,430
Alberto M. Rubio retweeted
Our MCP significantly reduces OpenAI API usage by 500% to 1000% compared to any Agent or Harness. This is achieved through our ultra-optimised API usage and custom models.
test it in:
ctrify.com
🥶NEW OPEN AI PRICING!!!!
💀The new $200 USD ChatGPT subscription won’t be 20X anymore
‼️New 50% API cost policy means:
The new 20X is just a 10X
AKA:
Same usage per dollar as the old 5X
2
5
98
🥶NEW OPEN AI PRICING!!!!
💀The new $200 USD ChatGPT subscription won’t be 20X anymore
‼️New 50% API cost policy means:
The new 20X is just a 10X
AKA:
Same usage per dollar as the old 5X
Hi,
Tomorrow we are re-opening the Pro $200 subscriptions to new subscribers, but together with it we are also changing how we calculate the usage for it. In effect, if you do the math, it will net out at half the dollar in API spend compared to the old Pro $200 plan.
Now that it's said, let me explain why this is happening and why you will still get more work done than if you were on the Pro $200 subscription one month ago.
(a) We didn't want to compromise in other ways and are committing to not reintroducing the 5h limit, so that you can fully use the weekly usage when you want.
(b) On the subscription, we guarantee that over time you always get more work done and with an increasing level of quality. This means that you will continue to get more value per dollar spent as a result of models getting more efficient and us passing down the improvements in the form of API price reductions.
(c) We don't want to put an incentive on ourselves to artificially inflate the API list prices to make it look like you are getting a lot (and workaround it through discounts, etc). Instead we want to continue to both rapidly reduce prices and increase capabilities of models on the API. This week we introduced GPT-6 Sol and GPT-6 Luna at 50% of their previous price. Over time, we see prices go low enough that it makes sense for most to buy usage as needed without there being a significant gap between what you get in a subscription and what you get in the API for a dollar spent.
(d) Tomorrow, we are adding more things to the subscription that won't draw on the usage, I won't reveal what that is yet.
I wanted to be transparent before all the big announcements tomorrow. Lots of new exciting things are coming to the subscriptions that will make it super compelling, but I wanted to make sure to share this change ahead of time so you can all understand it before we shower you with good news.
Codexingly,
Tibo
1
1
7
271
🟠How many people can still become Bitcoin wholecoiners?
Once you realise Bitcoin is limited and fungible 24/7/365 for fiat money in many banks and exchanges worldwide, you know it won’t be enough whole coins for everyone.
Many people underestimate how close it is to 1 BTC reaching 1 million USD.
It’s also useful as collateral. Currently, you can secure a loan or mortgage backed by Bitcoin, eliminating the need to sell your BTC and pay capital gains to access funds.
This is essentially the same financial trick employed by CEOs and investors worldwide to avoid selling their valuable stocks for some cash.
Wealthy individuals understand the game but are unaware they can apply the same strategy to Bitcoin. Once they grasp this, an unprecedented Bitcoin bull run fuelled by FOMO and a gold rush will commence!
Made with AI
2
3
12
4,154
Bitcoin is better than “gold.”
Compare Bitcoin to what people actually buy when they say they own gold:
🟠 Bitcoin (self-custody)
🟡 Tokenized gold (PAXG, XAUT)
⚪ Paper gold: ETFs & stocks (GLD, IAU, miners)
BTC is 100% verificable asset.
The other two types of "gold" are a third-party promises of they having Gold.
Made with AI
3
2
7
238
How I transitioned from many hours of typing in tunnel coding sessions to writing autonomous and timeless coding loops.
2
1
8
302
ICodex 5X account!
It’s only 50% left after exactly 4 hours of single-tasking in Astra Max. 🤦♂️
8
71
Hot Take:
You’re a brilliant Vive coder working in your dream SaaS.
Have you already considered how it will scale?
1) Will the server handle the load?
2) Do you understand load balancing and how it works?
3) If you need multiple servers working with a load balancer, how will you maintain sessions while switching between servers for each payload or Ajax request?
4) Do you know the difference between front-end and back-end development and how each type of code needs to rest and communicate?
5) Are you familiar with XSS, Ajax, PUT, POST, and GET requests?
6) Is your database hosted on the same application server? If so, how do you plan to scale it?
These are just a few questions to get you started.
1
7
61
A hot take:
AI can transform anyone into an app developer. 💯
However, it also elevates junior programmers to 10x their original level and senior developers to 20x.
And If you were once considered a 10X Full Stack Developer, you’re now equivalent to a 100X developer.
8
61
Second-best advice for Condex (and any AI Coding tool)
🔎Read the generated code
🧠Read the thinking!
especially at the beginning and occasionally afterwards, to ensure it aligns with your plan.
You’d be surprised how often they lose the North!
8
75
My best Codex tip is that subagents can be more harmful than helpful especially if you use less intelligent ones.
( Even if you have a detailed and consistent development and implementation Plan)
Lock the project to one model and selected effort in the Agents.md file. And explicitly Forbid the use of subagents!
Parallelising work is better achieved by using different threads within the same project, each with its own work tree but sharing a common main project worktree.
This is my modular development approach for large projects.
1
9
88
I have four 5X Codex accounts and none have been able to upgrade.
However, one account offered me a couple of resets for $40.
Those who’ve managed to upgrade to 20X might be fibbing or are simply incredibly lucky bastards😅
8
82
I’m curious... 🤔
Who began Vive Coding without any prior programming experience?
How has your journey been?
8
43
🪐Astra Max Astronomical Expend!
My ChatGPT Codex X5 account weekly usage on a single non-stop task with Astra Max lasted exactly 12 hours💀💀💀
However, my other two 20x accounts reset within a few hours. I expect each of those to last me exactly 48 hours of non-stop work on a single thread.
I’ve managed to buy a couple of resets for $40, but they’re only available in one of my X5 accounts (which is no longer the case only been able to buy 2).
I can confirm that they reset for a new 12 hours of work.
(I haven’t even counted the tokens, but all measurements have been taken by my local agent on my 5090 to ensure no interference with the process.)
8
210