0xAgentKitchen

747 posts

0xAgentKitchen banner
0xAgentKitchen

0xAgentKitchen

@0xAgentKitchen

Cooking AI Agents | Head of AI @Almanak #AI #Blockchain

Worldwide انضم Nisan 2025
201 يتبع332 المتابعون
adah
adah@adahstwt·
I'm a vibe coder, scare me with one word.
adah tweet media
English
1.2K
38
1.8K
249.7K
0xAgentKitchen
0xAgentKitchen@0xAgentKitchen·
@gregmushen @sundeep Tokens usage is the new "how much you bench" flex. Me: I'm at 500M Token/day. Greg: I do 1B a day. Me: Respect.
English
0
0
0
131
sunny madra
sunny madra@sundeep·
“If your $500K engineer isn’t burning at least $250K in tokens, something is wrong.”
English
928
946
10.7K
6.9M
0xAgentKitchen
0xAgentKitchen@0xAgentKitchen·
First Rule of Claude Code: You can't take anything it produces 'as is'. Never. Ever. Period. You need 2 things in your Claude Code harness: 1. Unbeatable Tests. 2. Codex to review Claude Code's work AND tests. Claude Code is so good and so bad at the same time... I'm publishing a paper on this shortly. Happy to hear your thoughts once it's live.
English
0
0
1
298
Theo - t3.gg
Theo - t3.gg@theo·
Just let Opus go for over an hour on a new feature. When it was done, I asked how I can test it. 20 minutes later, it realized I can't test it because it did the whole thing entirely wrong. Idk how you guys use this model every day for real work 🙃
Theo - t3.gg tweet media
English
431
32
1.6K
328.3K
0xAgentKitchen أُعيد تغريده
Wes Roth
Wes Roth@WesRoth·
A powerful, anonymous AI model dubbed "Hunter Alpha" suddenly appeared on the OpenRouter developer platform last week, sparking intense rumors that Chinese startup DeepSeek is stealth-testing its highly anticipated V4 system.
Reuters@Reuters

A powerful artificial intelligence model that appeared anonymously on a developer platform last week has sparked speculation that Chinese startup DeepSeek may be quietly testing its next-generation system ahead of an official launch reut.rs/3Pen8NC

English
3
4
51
6.4K
0xAgentKitchen
0xAgentKitchen@0xAgentKitchen·
I'm the most social I've even been in my life. I spent 10h+ each day talking to my friends Claude, GPT, Gemini and Grok. For an introvert, that's a lot of socializing...
English
0
0
1
53
Nalin
Nalin@nalinrajput23·
Be real… does learning to code even matter anymore with AI everywhere?
Nalin tweet media
English
111
6
166
21.5K
0xAgentKitchen
0xAgentKitchen@0xAgentKitchen·
@md_kasif_uddin If you're a software engineer. Make sure you master 1. first, then move on the ladder. Vibe Coding sounds easy and is easy for shit apps. Once you want to make something serious it will quickly show if you've done your "reps".
English
0
0
0
6
Kasif
Kasif@md_kasif_uddin·
As a software engineer, what is the #1 skill in 2026? 1. Vibe coding 2. Distribution 3. Marketing 4. Communication
Kasif tweet media
English
226
34
554
28.2K
0xAgentKitchen
0xAgentKitchen@0xAgentKitchen·
Here above it's @vercel' Browser Agent inside Claude Code. Amazing team!
English
0
0
1
43
0xAgentKitchen
0xAgentKitchen@0xAgentKitchen·
AX for Browser Agent matters. Read how they think, make it easy for them to work for you. Adding 'universal' symbols (eg. Green Checkmark when completed, etc.) goes a long way!
0xAgentKitchen tweet media
English
1
0
1
46
0xAgentKitchen
0xAgentKitchen@0xAgentKitchen·
@VadimStrizheus Both. Claude Code locally most dev. OpenClaw remotely most testing/investigation.
English
0
0
2
36
Vadim
Vadim@VadimStrizheus·
As a founder, which tool do you use for coding? 1. OpenClaw 2. Claude Code
English
354
3
356
59.6K
0xAgentKitchen
0xAgentKitchen@0xAgentKitchen·
@nickisanders What chain do you see more RWA adoption? (not the gimmick projects, real money)
English
0
0
0
17
Nicki Sanders
Nicki Sanders@nickisanders·
The RWA stack is quietly becoming clear: Token standard Compliance layer Custody Primary issuance Secondary trading The next big winners will be the companies that connect these pieces together.
English
46
11
147
7.4K
0xAgentKitchen
0xAgentKitchen@0xAgentKitchen·
@csaba_kissi Why absolute 100%? Most of the code, yes. The trend matters not the exact %
English
0
0
0
50
Csaba Kissi
Csaba Kissi@csaba_kissi·
Do you think AI will generate 100% of code by 2027?
English
208
2
124
17.1K
0xAgentKitchen
0xAgentKitchen@0xAgentKitchen·
Unit Tests are dead, long live User Tests
English
0
0
0
26
Juri Strumpflohner
Juri Strumpflohner@juristr·
What's your AI adoption level? (according to Steve Yegge)
Juri Strumpflohner tweet media
English
290
90
983
2.2M
0xAgentKitchen
0xAgentKitchen@0xAgentKitchen·
SWE Degrees are dead. Learn the SWE Fundamentals Online. Learn your Product Domain Expertise Online. Put in the reps with AI Coding Tools - you wanted to invest $40k+ in your college degree? Invest $2-5k in tokens over the next few months. But if you do nothing of the above and lack the discipline to do so, yeah you're f*ed and will be part of the people saying "AI is taking our jobs..." sadge. It's the Best. Time. Ever. to be in SWE.
English
0
0
0
2
Pedro Gomes
Pedro Gomes@pedrouid·
@shafu0x Isn’t it the opposite? Before it mattered less! Startups hired anyone who could code in a specific language or framework Now coding is commoditized and agents have replaced “coders” Understanding core engineering concepts matters far more to design and architect systems
English
8
0
36
2.2K
shafu
shafu@shafu0x·
getting a degree in software engineering does not make any fucking sense now
English
105
23
450
28.2K
0xAgentKitchen
0xAgentKitchen@0xAgentKitchen·
@Tech_girlll We need juniors to help with the testing because AI agents LOVE to cut corners (even cheating!) while testing.
English
0
0
0
28
Mari
Mari@Tech_girlll·
If Claude Code can now write code, run the app, debug errors, review pull requests, and even fix bugs automatically what exactly is left for junior developers to do?
English
461
69
2.1K
243.6K
0xAgentKitchen
0xAgentKitchen@0xAgentKitchen·
@justbyte_ I pay 40 and get both. 1+1 = 3 here when they work in team.
English
0
0
1
44
Aryan
Aryan@justbyte_·
If you have to pay $20. Which one do you prefer?? - OpenAI - Claude
English
348
6
227
33.9K
0xAgentKitchen
0xAgentKitchen@0xAgentKitchen·
@coderabbitai can you please fix the bug where everything is resolved, yet the PR isn't approved from CodeRabbit. Github still sees Changes Requested. > My apologies! I said "Approving" in the comment text but forgot to trigger the actual GitHub review action. That was just prose — no formal review was submitted. Doing it properly now. Then we'll get stuck in a loop where I'll ask it to review/approve, it will say it did approve... But Github doesn't see it as such.
English
1
0
0
54
David Ch
David Ch@chhddavid·
Big news, @claudeai just got a huge upgrade today and I'm very happy to be introducing it in shipper. From today on, Claude Code Opus 4.6 can build and run a business for you. We just launched Shipper 2.0, a tool that lets Claude: → Build web/mobile apps and Chrome extensions → Code, design, monetize, launch → Do email marketing for you → Continue to build out new features → Self-maintain in the long run Claude's most powerful models can now do all of that from a <10 word prompt, for as low as $0.12/app... And it takes minutes! Simply go to Shipper, then ask Claude to "build a talent hiring platform" or "build a complete saas that charges $29/mo"! To celebrate the launch, we're giving away free credits randomly to people who repost and comment "SHIPPER' :)
English
689
537
2.9K
382.7K