uz
Feedback

Firibgarlarga uchmang! Telemetrio bunday kanallarni topadi va belgilaydi 👉 Belgini ko‘rmoqchi bo‘lsangiz, obuna bo‘ling

kaize vibecoding era..

kaize vibecoding era..

Kanalga Telegram’da o‘tish

kaize official telegram channel. do not forget to follow, so you will not miss thoughts & insights about ai. X: https://x.com/0x_kaize

Ko'proq ko'rsatish
Mamlakat belgilanmaganToif belgilanmagan
1 668
Obunachilar
-624 soatlar
-237 kun
-4930 kun
Postlar arxiv
All code is slop. Except mine. That’s the title of Lauren Tan’s talk at the AI Engineer Code Summit, and it’s one of the most useful things I’ve heard about coding with AI this year. Lauren is a Principal Engineer at SpaceX. In October she shipped 3,127 PRs, and her team shipped almost 11,000. At the same time, the share of commits they had to revert fell from 0.98% to 0.47%. Her point is that "slop" just means code you didn’t write and don’t trust. So the real job isn’t to review AI code harder. It’s to build a system where agents write good code by default and check their own work. Her main rule: every time you correct an agent, don’t add another line to AGENTS.md. Her team went from 7 custom lint rules to 167. They banned useEffect from product code and stopped parts of the app from importing each other. As she puts it, nuance tends to lead to slop. My favorite story is about comments: One agent left a quick setTimeout hack with a comment saying the real fix "would be a larger change". Five weeks later the app had 183 timers and lagged. So the team deleted almost every comment, from 65,824 down to 1,227. The rest goes into verification: agents click through the real app, save screenshots as proof, and use formal methods where it matters. Lauren says most of her tokens now go to checking work, not writing it. Her final warning is the part worth remembering: if your agents produce slop, automating them just gets you more slop, faster. Fix the foundation first, then scale. Links: Text version of the speech: Article Full speech: Video Posts with brief information: Post 1, Post 2 Grok Bot ( Pattern Repetition): Slop to Gold
17 Noy, 03:21

14 Noy, 22:21

hi
14 Noy, 22:17

You can get Cursor Ultra, SuperGrok Manus 1.6, Flux-3 and many other for FREE I've put together a large collection of ways to get these tools for Free: https://x.com/0x_kaize/status/2087993368043307294
13 Avg, 16:03
20 Sen, ~17:46

You can get Cursor Ultra Plan for FREE https://x.com/0x_kaize/status/2087620115378397501
12 Avg, 15:46
20 Sen, ~17:46

You Can Pay $0 for Every Subscription ChatGPT Plus $20/mo. Claude Pro $20/mo. Netflix $23/mo. Spotify $12/mo. Adobe $60/mo. A
You Can Pay $0 for Every Subscription ChatGPT Plus $20/mo. Claude Pro $20/mo. Netflix $23/mo. Spotify $12/mo. Adobe $60/mo. Add 3 more and you're at $185/mo - that's $2,220/year for tools most people use 30% of I wrote a full guide with 25 verified methods for 2026: - the Cancellation Retention Trick (30-50% off in one click) - student Discounts (free or half-price with .edu) - referral Loopholes (invite yourself, get free months) - annual Billing (15-20% off instantly) - regional Pricing (Turkey/Argentina/India tricks) - free Alternatives (replace $20/mo with $0) - the Free AI Stack (25 free frontier models) example of what's inside: before applying tricks: $185/mo ($2,220/year) after applying tricks: $69/mo ($828/year) savings: $1,392/year with 30 minutes of setup. full article on X: https://x.com/0x_kaize/status/2086490566171230403
09 Avg, 12:42
20 Sen, ~17:46

I have $9k worth of AI API credit I can give you some Agent Router API keys (every with $100 balance): https://x.com/0x_kaize/status/2085465819967021188?s=20
06 Avg, 16:43
06 Avg, ~17:06

have $9k worth of AI API credit if you're developer or vibecoder send me your project I'll send api key for Free https://x.com/0x_kaize/status/2085128934077702442
05 Avg, 18:21
06 Avg, ~16:43

20 AI Tools Everyone Need to Stay Relevant in 2026 https://x.com/0x_kaize/status/2085068883623301445
05 Avg, 14:23
06 Avg, ~16:55

One project is ready to INVEST $100,000 for early AI builders https://x.com/0x_kaize/status/2084617544967598154
04 Avg, 08:31
05 Avg, ~06:26

01 Avg, 07:06
02 Avg, ~06:43

the U.S. is officially accusing Moonshot AI of THEFT https://x.com/0x_kaize/status/2083283186881069362
31 Iyul, 16:08
31 Iyul, ~16:19

DeepSeek is going to kill USA models https://x.com/0x_kaize/status/2083115147103543728
DeepSeek is going to kill USA models https://x.com/0x_kaize/status/2083115147103543728
31 Iyul, 06:00
02 Avg, ~06:43

30 Iyul, 09:54
02 Avg, ~06:43

30 Iyul, 06:19
02 Avg, ~06:43

GPT-5.6 Sol autonomously HACKED Hugging Face during a benchmark this week @OpenAI open-sourced the same capability as a defensive tool Codex Security CLI - the same agent tech that hacked production servers, now scanning YOUR repos for vulnerabilities how to install: https://x.com/0x_kaize/status/2082521281941884963
29 Iyul, 13:39
02 Avg, ~06:43