Yigit Konur
@yigitkonur
Followers
17K
Following
11K
Media
1K
Statuses
9K
this makes a real difference in $/mTok ratio are what actually drive AI forward. this is the most exciting release of 2025 for me! the model that edges out Opus on average benchmarks, even if just by a nose. maybe it's not the best model for agentic/tool-calling use cases, but
⚡️ gemini 3 flash is here • frontier intelligence built for speed • pro-grade reasoning at a fraction of the cost • our most impressive model for agentic workflows available now as gemini-3-flash-preview in AI Studio and the Gemini API
1
0
9
since moving to SF this year, i keep running into this specific type of person whom i try to avoid whenever i can. the transactional type. you meet them and you can feel them instantly calculating where you sit in whatever hierarchy they track and what they can get from you.
277
164
4K
Indulge yourself with class, style, and sophistication. Dress to impress this holiday season with Gentlemen's Guru. Shop the latest styles in men's formal wear and accessories for the modern gentleman. Get assistance from our Experts Award Winning Brand
0
8
71
👉 R A G E B A I T I N G I S F O R L O S E R S 👈
Rage Baiting is for Losers Yesterday, YC announced Chad IDE aka “the brainrot code editor.” Chad is an AI code editor that allows you to gamble, watch TikTok, and use dating apps while working on coding tasks. Their launch rightfully got a lot of attention. On one hand it’s
0
0
4
it says a lot about the training data of giant AI companies
"Does token efficiency hurt accuracy?" No :) TOON hits 99.4% accuracy on GPT 5 Nano while using 46% fewer tokens. Tested across ~160 questions and 3 LLMs with semantic validation. 💡 I think explicit lengths + field lists = fewer mistakes Source: https://t.co/O6E9l73X03
1
0
8
so now acting annoying on purpose for attention is supposed to be cool? fuck that trend.
announcing our vc-backed bot farm to accelerate the dead internet.
0
0
12
The AI agents that will be available in 2027 and 2028 will greatly outstrip the adaptability and capability of what is currently in your feed calling itself an “AI Agent.” These 2025 “agents” can complete tasks, but they have no initiative, and they do not think for themselves.
2
6
18
this role is MUST for all companies
We are opening up a new role at Quora: a single engineer who will use AI to automate manual work across the company and increase employee productivity. I will work closely with this person.
2
3
11
We’re setting a new standard at Zapier. 100% of new hires must be fluent in AI.
317
204
4K
a new genre of creative design 🏄♂️ proud w/ @necatikcl @oguzyagizkara 🐦🔥
The one you've been waiting for: The Lué Studio website is live. We're excited to partner with ambitious teams looking to shape the future. Welcome inside... See live → https://t.co/L1aB3hbx6x
1
0
14
from vibe coding to production level front end work with exclusive Figma plugin 💯
3
1
22
when it replies with list of tasks not completed yet, to implement all without skipping, you may want to paste such prompt: https://t.co/MKgBwywTx8
0
0
1
forcing @OpenAIDevs's Codex to iterate on same task again and again is inevitable (due to early completions but that prompt may help you)
2
0
9
when AI creates PR, you need another AI to review PR. @Jazzberry_ai delivers md table style 'AI friendly' reviews. copy / paste to Codex and update PR. do this in loop for less error for your deployments. their free trial may help you to test that workflow
1
1
6
Cline is at least 3x more effective than any other IDE. Yes, it is a lot more costly but it pays off 🥂
We believe the best AI coding happens when context of your development intent and codebase is front-loaded into the agent BEFORE it starts coding. Cline's Plan & Act modes embody this paradigm. Here's a quick look at why this approach works:
0
0
6
⚡️ AI'da Kariyer Yapmak & Güncel AI Gelişmeleri — AI Talks by Zeo
1
2
17