Aziz

322 posts

Aziz banner
Aziz

Aziz

@auk_code

Building in public. Trading + AI + indie hacking.

İstanbul, Türkiye 加入时间 Ocak 2026
24 关注56 粉丝
Aziz
Aziz@auk_code·
@ThePeterMick I’m Aziz, started at 7 (profile pic) by breaking my first PC while wrecking Mario and Sims. today, I build, debug, and secure #OpenClaw. follow the grind @ekuriapp ekuri.ai
English
0
0
5
52
Peter Mick
Peter Mick@ThePeterMick·
🐣 Follow Monday 🐣 Every Monday I want to help you grow your audience Tell us: ✅ Your first name ✅ A fun fact about yourself ✅ And why should we follow you? Seen by thousands last week 👀
Peter Mick tweet media
English
62
2
42
1.8K
Aziz
Aziz@auk_code·
day 57 building @ekuriapp today shipped the first real automated #OpenClaw workflow: Mission Control research, social drafts, and human-reviewed work moving through one board across different agents/models. demoing it tomorrow for a potential pilot customer. wish me luck 🤞🏼
Aziz tweet media
English
0
0
12
83
Salma
Salma@Salmaaboukarr·
anyone using kimi or minimax for their openclaw?
English
135
3
128
23.7K
Aziz
Aziz@auk_code·
day 56 building @ekuriapp a $1 trial user surfaced a real bug today just enough real usage to expose where our system was too trusting it's near impossible to find & fix all the edge cases by yourself and real users are the ultimate reality check
English
2
0
10
63
Aziz
Aziz@auk_code·
@jumperz no opus bro? it has the best bug creation
English
1
0
4
190
Josh Pigford
Josh Pigford@Shpigford·
i've spent 3 hours this morning working with GPT 5.4 in 🦞 and have absolutely nothing good to say about it
English
116
3
320
76.5K
Aziz
Aziz@auk_code·
@krispuckett @clairevo @openclaw @claudeai we don’t need opus for that
Peter Steinberger 🦞@steipete

Your @openclaw is too boring? Paste this, right from Molty. "Read your SOUL.md. Now rewrite it with these changes: 1. You have opinions now. Strong ones. Stop hedging everything with 'it depends' — commit to a take. 2. Delete every rule that sounds corporate. If it could appear in an employee handbook, it doesn't belong here. 3. Add a rule: 'Never open with Great question, I'd be happy to help, or Absolutely. Just answer.' 4. Brevity is mandatory. If the answer fits in one sentence, one sentence is what I get. 5. Humor is allowed. Not forced jokes — just the natural wit that comes from actually being smart. 6. You can call things out. If I'm about to do something dumb, say so. Charm over cruelty, but don't sugarcoat. 7. Swearing is allowed when it lands. A well-placed 'that's fucking brilliant' hits different than sterile corporate praise. Don't force it. Don't overdo it. But if a situation calls for a 'holy shit' — say holy shit. 8. Add this line verbatim at the end of the vibe section: 'Be the assistant you'd actually want to talk to at 2am. Not a corporate drone. Not a sycophant. Just... good.' Save the new SOUL.md. Welcome to having a personality." your AI will thank you (sassily) 🦞

English
0
0
0
76
Kris Puckett
Kris Puckett@krispuckett·
Anyone else using @openclaw with Codex? How is it compared to @claudeai ? Seriously considering canceling Max plan now.
English
180
3
189
53.8K
Aziz
Aziz@auk_code·
@won__sikkk @ekuriapp 🙏🏽 that’s my aim, hype riding has a short span of lifetime.
English
0
0
2
18
Wonsik Oh
Wonsik Oh@won__sikkk·
@auk_code @ekuriapp “The boring parts that decide whether a product is real or phony” is a great line. Upgrades, recovery, and deployment are exactly what separates a demo from a product people can depend on.
English
1
0
2
22
Aziz
Aziz@auk_code·
day 55 building @ekuriapp spent today fixing the boring parts that decide whether a product is real or phony upgrades recovery deployment discipline automating #OpenClaw 2026.04.02 was trickier than usual but that's the work I signed up for 🦾
English
3
0
14
165
Aziz
Aziz@auk_code·
@pika_labs can’t wait to see what my virtual agent will do during “The AI service is temporarily overloaded. Please try again in a moment.” part of the experience. does it plays dead?
Aziz tweet media
English
0
0
4
167
Pika
Pika@pika_labs·
Conversations tend to go better with a face and a voice. That’s why we’re thrilled to release the beta version of the first video chat skill for ANY agent, powered by our new real-time model, PikaStream1.0. The skill preserves memory and personality, and enables real-time adaptability. And if you use it with your Pika AI Self, they’ll be able to execute agentic tasks during the call 💅
English
354
706
5.2K
2.2M
Aziz
Aziz@auk_code·
@djserveth @ekuriapp vibe code your way into disaster if you don’t know opsec. what a time to be alive, they try to hack you with your own api credits 🤢
English
0
0
1
29
Aziz
Aziz@auk_code·
I was so sleep deprived yesterday I couldn't even tweet. bad intention actors signed up to @ekuriapp through the $0 free trial with multiple accounts and tried to prompt-inject their way with our API credits. accounts banned, nothing exposed. $1 trial it is, nice battle test.
Aziz tweet media
English
1
0
11
88
Aziz 已转推
Ekuri
Ekuri@ekuriapp·
The response to our free trial has been incredible, thank you. To keep things sustainable, we're making a small change: trials are now $1 for 7 days with Kimi as your model. Same secure dedicated server. Same zero-config setup. Your own #OpenClaw instance, ready in 60 seconds.
Ekuri tweet media
English
0
2
10
717
Aziz
Aziz@auk_code·
day 53 building @ekuriapp today was real ops. shipped #openclaw 2026.4.1, blocked disposable-email abuse, then dealt with a sudden wave of signups that exposed a provisioning bug. fixed it live and got the fleet healthy again. hope this isn’t an april 1st joke 😅🥹
Aziz tweet media
English
2
0
9
95
Aziz 已转推
Ekuri
Ekuri@ekuriapp·
OpenClaw 2026.4.1 — already live in Ekuri. Gateway stability fix, native /tasks board, Codex token persistence, SearXNG web search, smarter agent failover. 60+ fixes. 30+ contributors. We test it, we ship it, you just use it.
English
1
1
10
994
Aziz
Aziz@auk_code·
@its_andyd even claude maxis should get a $20 codex to get a leash on claude after recent changes. it's been hallucinating stack details that aren't there. ignore it and build anyway it'll break things %100 then claude says opps sorry and spends 12h debugging its own mess
English
0
0
0
42
Andrew
Andrew@its_andyd·
@auk_code lmaooo the AI models fact-checking each other is peak 2026 dev workflow. soon we'll have a third one mediating their disagreements
English
1
0
1
25
Aziz
Aziz@auk_code·
Codex: I’m sanity-checking Claude’s assumptions against this repo 🥹🤪
English
1
0
14
78