github.com/pekth/meterusage @intenttrade26 Reviving YimYim Play- soon Build with me buymeacoffee.com/pekth
- Tweets 400
- Following 357
- Followers 33
- Likes 539
Looking for testers if anyone interested.
Most traders quit journaling because logging trades in Excel feels like punishment.
Screenshot your MT4 or MT5 ticket, drop it in, and intent trade logs your entry, exit, lot size, and PnL automatically.
Watch how it works in 30 seconds. DM for beta access.
23
So this is it. Instead of bumping the price. X reduced the price and pack more.
One plan for X, Grok, Cursor and Grok Bot.
It's called Xpass.
Premium $8
• Grok Lite + X Premium
• Shared quota
• Cursor included, Grok API
Plus $30
• SuperGrok + X Premium+
• 4x Premium
• Grok Bot, Cursor cloud agents, Bugbot
Super $100
• SuperGrok Plus + X Premium+
• 15x Premium
• 1080p, faster replies, priority access
Ultra $200
• SuperGrok Heavy + X Premium+
• 50x Premium
• Fastest replies, earliest access
A launch promo is in there too: 50% off the first month, dated Oct 9.
4x / 15x / 50x usage is still unconfirmed.
1
44
I tried to burn them too.
Gave Astra and Sol 6.1 identical tasks. Astra acted dumb and just quit halfway through, while Sol actually completed the work.
Hard to burn credits when the agent quit halfway on you. Switched back to Sol.
Every 20x user got 62,500 credits. Worth $2500USD.
I decided to test Astra High fast, to see how many credits it would use.
I was VERY shocked.
24
open source here if you want to track quota on macOS notch: github.com/pekth/meterusage
1
14
About 15 years ago, I tried to cancel my YMCA membership after not going for five months. I was locked into an annual plan, and after trying to cancel multiple times with no luck, I finally called my credit card company to dispute and block the charges.
NYC now legally requires companies to make cancelling a subscription as simple as signing up, the first US city to do so
"If you can sign up with a click, you must be able to cancel with one," Mayor Zohran Mamdani said
1
1
41
When you're making multiple trades a day, it's super easy to lose track if you're trying to do it all manually. This will totally help you keep everything together!
Your trading month, in view.
Keep your trade history, daily P/L and review stats together with Intent Trade.
Explore: intent-trade.com/app/
Simulated walkthrough using sample data. Not investment advice.
11
Every shift in developer pricing creates winners and losers.
Last month everyone thought open weight releases would drive prices down and force AI companies to subsidize us even more. Instead limits tightened and subscription value got recalculated.
Some users are thrilled because open weights give them local privacy and full control. Other users are frustrated because subsidized cloud compute is no longer a free lunch.
Everything in tech cuts both ways.
18
Ran 9 concurrent threads of Sol 6.1 xhigh for an hour straight.
Total API usage dropped from 64k down to 62k. Only 2k consumed across nine active tasks.
Sol 6.1 xhigh efficiency is surprisingly solid for heavy background workloads. Being able to run that much parallel compute without vaporizing your quota is a huge win for me.
1
29
Building for the App Store Kids category forces you to cut all the growth hacking nonsense.
No external tracking SDKs, no ad banners, no dark patterns, and no social feeds.
Just a clean offline bundle with instant audio and playful touch cards. The platform restrictions for kids ages 2 to 8 actually result in better software.
1
19
Splitting your pipeline between planning and execution is the only way to run heavy agent workflows sustainably.
Using high reasoning for the initial roadmap and fast execution models for code edits keeps your daily token spend under control.
The mistake most people make is using maximum compute for routine file changes.
thoughts on sonnet 5.5 after a day of real use
sonnet and opus 5.5 are clearly taught by the same teacher model (which i can only guess to be mythos 5.5 or even 6). their behaviors and personality are highly similar this time
but sonnet is definitely NOT “same as opus just 50% cheaper” - that’s true only for problems that don’t need much wisdom
there’s a clear difference when they are asked to propose plans for ambiguous product problems. you should be able to repro this by asking them to plan a complex enough feature whose direction is unclear
opus is able to approach problems with more strategic thinking “what’s the real goal here” while sonnet is more just looking at tactically “how do i get this done”
i also tested heavily using sonnet 5.5 as my firstmate and it’s working super well! i even prefer it over opus, because it’s faster, cheaper, and smart enough to understand my intent and handle the orchestration
my overall approach now is -
- opus plans
- sonnet implements
- once haiku 5.5 is here, i’ll use haiku for “fixes”
- if anything’s not going well, fable advises
sometimes i’ll go straight to fable for plans that i know requires its wisdom but this is becoming more and more rare in my experience (perhaps fable 5.5 will change it!)
i must say, anthropic’s latest line-up is incredibly compelling both in terms of quality and efficiency. we’ll see what openai cooked soon but they definitely have their work cut out for them
1
1
47
