wolfaidev 🐺
2.4K posts
wolfaidev 🐺
@wolfaidev
Always striving higher - unpatchable. Building the next $1M ARR SaaS suite. Built ‚npx vibestats‘
💻 /dev/wolf Katılım Nisan 2025
123 Takip Edilen246 Takipçiler
I don't understand vertical tabs. Why would I want less space for the website content I actually want to look at?
Sawyer Hood@sawyerhood
wtf chrome has vertical tabs now. finally
English
@bridgemindai Wonder if it has to do with peak hours or just bugged
English
Update on Claude Code.
Things are back to normal.
30 minutes in.
6 Claude Code agents running Claude Opus 4.6 in parallel.
Only 11% usage on the 5 hour session limit.
Yesterday I burned through 100% in under an hour.
Today the pacing is exactly where it should be.
Back to building. Back to Claude Code.
English
What's stopping YOU from CODING like THIS?
English
If you can reply to this, you love Open-source ❤️
English
@GregKara6 Opus did a fantastic job with 1M context for a few days before shit hit the fan so I believe it must be something else, rather the new auto mode or memory updates or whatever the heck anthropic is doing, opus api down all the time yday, its unusable
English
there we go, would you look at that.
x.com/GregKara6/stat…
Grigori Karapetyan@GregKara6
yea so as this week shows, most people don't know how to manage or even use 1m context.. if you are running out of your claude usage really fast, maybe don't send 800k tokens from 4 terminals at the same time for 2 hours.
English
@reach_vb Thanks for sharing! So it is fully allowed to use codex and headless cli in openclaw, custom dashboards, my own workflows and all? No bans like Claude or Google?
English
Your periodic reminder: Codex App Server is 100% Open Source!!
It allows you to build on codex and build richer experiences all with ChatGPT Auth
Thousands oof projects are built on top of it including our own VS Code Extension - check it out ;)
English
@LLMJunky you proxy your gpt pro through droids? vibeproxy? or just oauth login? is it allowed to do that?
English
@levelsio do you also have the claude bug of usage hitting after 4 prompts like everyone?
English
To give you an idea of how bad the AI bot problem was getting
I muted about 17,500 of them, then started blocking them recently, so another 3,000
99% bots
So I blocked about 2.5% of my follower count and didn't even get close to stop AI replies either
Miguel Piedrafita ✨@m1guelpf
@aadilpickle many such cases
English
many didn't expect MiMo-V2-Pro to be this good
lots of love
both Pro and Omi stay free for another week
OpenCode@opencode
MiMo-V2-Pro and MiMo-V2-Omni are now free in OpenCode many of you have tried them in stealth - Hunter Alpha and Healer Alpha. Mystery solved worth mentioning - MiMo-V2-Pro: - ~1T params - 1M context - optimized for coding
English
@sudo_goreng @FactoryAI which model is your fav? can you please share the current models and X multipliers in droids
English
Just tested @FactoryAI for a couple of hours + adapted my opencode skills & plugins to droid. Will be daily driving it for a couple of weeks.
So far its good, but the only problem is the CLI sometimes lags, Idk if its a zellij/ghostty specific issue or not.
Goreng@sudo_goreng
Anyone tried @FactoryAI before? Is it good or nah? factory.ai/pricing
English
What on earth is wrong with @claudeai
One of the best companions out there straight out rugging loyal folks here
Why is the team not addressing this?
Usage limits hit after 3 prompts and Opus suffering major API outages
@AnthropicAI we need answers
BridgeMind@bridgemindai
Claude Code was nearly unusable yesterday. Major outages all day. Hit my limit on the $200/month Max plan in less than 1 hour. One hour. On a $200 plan. Had to fall back to Codex with GPT 5.4 for the rest of the day. It worked. But it's not the same. Claude Opus 4.6 is still the most reliable coding model when it's actually running. Hoping today is better. I need my Claude Code back.
English
@Craftlingsgame Congrats man! Wow straight up made a GmbH for your first game?
English
Hey there 👋
I’m Ariano, a 42 y/o solo dev, and I recently released my first game, Craftlings!
It’s a game about smart building, resource management, and automated production chains.
Get your copy now — 20% off for a limited time.
English
Team is being silent about usage rugs
This is not a good sign
Thariq@trq212
imessage is now available as a channel!
English
@wolfaidev Composer 2 has a very competitive API price, combined with a standalone usage pool, so should be quite a lot!
x.com/cursor_ai/stat…
Cursor@cursor_ai
It's frontier-level at coding, priced at: - Standard: $0.50/M input and $2.50/M output - Fast: $1.50/M input and $7.50/M output
English
how much composer 2 usage do we get in paid cursor?
havent used in ages, is it any good?
English
We just built the world's best AI SEO audit.
It shows exactly where and how your brand appears across major AI platforms like ChatGPT.
Most agencies charge $2K+ for an audit like this.
But we're giving it away free for the next 24 hours.
Here's exactly what's inside:
1. Branded: How AI talks about you directly
2. Competitive: How you stack up vs competitors
3. Category: Where you appear across your industry
4. Sources: Which ones you're in and missing
5. Action: Plan to close gaps and improve visibility
You're losing deals to competitors simply because they're showing up in AI answers and you're not.
And the worst part is you don't even know it.
This audit fixes that.
Like this post + reply with your website URL and I'll DM your custom audit within 24 hours.
GIF
English
@SIGKITTEN what are the current droid multipliers for sota models? can someone share
English
OpenCode is about to get more powerful with remote sandboxes
I showed a brief demo before, but here's a much more in-depth demo. it's not hard to add basic support for a remote env, but handling all the edge cases like when a remote env gets deleted is difficult. especially if care about good UX
You never want to lose session data. so the choices are: run the session in your env, but run all tool calls remotely. that's too complex and painful.
The other way is to just let the full session run remotely, but sync back all the session data in your env. We chose this path: we built a syncing system which logs all events in a way that we can always recreate your entire session.
That means the remote env could get destroyed, but we can easily restore it. it also opens up other interesting ideas which we'll be exploring
English
GitHub CoPilot seems like a good deal
Anyone tried it out?
Seems to be lots of usage for the buck
English