Halil Barım @halilbarimdev

Notlarımı markdown tutuyorum çünkü yapay zeka zaten düz metinle çalışıyor. Aynı dosyayı ben Obsidian'da düzeltiyorum, Claude Code okuyup cevap veriyor.

Yapay zekaya ikinci beyin kurarken ters giden 3 şey: 1. Yanlış kasaya not 2. Sohbet dökümleri aramayı boğdu 3. Eskimiş notlar yeni gibi geldi

Yapay zeka hafızam laptopta değil, evde 7/24 açık bir mini PC'de. 8 GB RAM yetiyor. Notlar dışarı çıkmıyor, Docker'la her makineye taşınıyor.

🚀🚀🚀

Alican Kiraz @AlicanKiraz0

4 days ago

Hi everyone, this time, I compared the outputs and performance of some of the most widely used AI Harness tools. I evaluated Pi, OMP, Droid, and Codex CLI using the same development prompt in the GLASS CATHEDRAL — Fracture Dynamics Benchmark scenario. 🔥 I used GPT-6 Luna with

13 7 57 4K 11

Hi Friends! This time, instead of comparing different AI models, I compared the delivery performance of different AI Harness tools running the same model. We evaluated Pi, OpenCode, Claude Code, and Cursor using the same development prompt in the Port Crane Chess scenario. All tools used Sonnet 5.5 via OpenRouter, configured with medium effort. Task Overview: We asked the tools to develop a port simulation featuring autonomous crane control, physics-based cargo handling, dynamic task allocation, collision avoidance, and automatic task reassignment when a crane becomes unavailable. The evaluation focused on how quickly and cost-effectively each harness completed the development task, how easily the resulting software could be tested and inspected, and how effectively it reported its results. AI Harness Delivery Performance Scores /10 — Cost & Completion Time: 🥇 Pi — 8.46/10 — $2.634 — 17 minutes 🥈 Claude Code — 8.16/10 — $4.390 — 13 minutes 🥉 OpenCode — 7.68/10 — $2.370 — 25 minutes 🏅 Cursor — 7.24/10 — $3.780 — 19 minutes Key Findings: — Best balance between speed and cost — Pi. Ranking second in both metrics, Pi achieved the highest overall score. — Fastest completion — Claude Code. It completed the task in just 13 minutes, but also had the highest execution cost. — Lowest cost — OpenCode. However, it also recorded the longest completion time at 25 minutes. — Explicit testing and state inspection interfaces — Claude Code and Cursor. Both delivered implementations with named access points for externally stepping through execution and inspecting the current simulation state. — Restart behavior issue — OpenCode. Its implementation failed to clear the previous benchmark results after restarting. The cost–time trade-off was particularly interesting: — Pi completed the task 8 minutes faster than OpenCode for just $0.264 more. Compared with Cursor, Pi was 2 minutes faster and $1.146 cheaper. — These results demonstrate that the lowest execution cost does not necessarily translate into the highest overall efficiency. More importantly, this benchmark highlights a key observation: Using the same model, the same development prompt, and the same effort configuration does not guarantee identical completion times, execution costs, or output characteristics. — In this particular run, Pi delivered the most balanced performance, Claude Code was the fastest, and OpenCode was the most cost-efficient in absolute spending. Although Cursor's explicit testing interfaces were a positive aspect, it still fell behind Pi in both completion time and cost. Ultimately, the harness itself matters. Even when the underlying model remains identical, orchestration, execution workflows, and delivery behavior can significantly influence the final outcome.

Ajan = model + harness. Model motor; tek başına bir yere gitmiyor. Araçlar, hafıza, izinler ve iş sırası onu arabaya çeviriyor. Bugün Claude, yarın GPT. Model değişir, sistem kalır.

@ozansihay @higgsfield_ai 😂😂 konuyu çok iyi özetlemişsin

@BatsonElTweets @elonmusk Turns out the halfpipe was easier than the curb 😅 Thanks man, appreciate it 🙌

Hey @elonmusk, 0–60 in under a second is cool and easy. But have you ever tried a curb? 🦽 So I built my own Roadster 😂 Consider this a challenge. Build it. I’ll wait. 😏

13.10.2026 18:00:00…..

Her alanda yerlileşmek şart, en basit örneği yakın geçmişti yaşanan çağrı cihazı olayı. TOGG’a sağlam bir yerli rakip de şart…

Conflict @ConflictTR

2 weeks ago

TUSAŞ Motor Sanayii Genel Müdürü Akşit: Yapay zekayla savaş simülasyonu yaparsanız, yapay zeka hemen her seferinde arabaları füze olarak kullanıyor. Ne demek o. Yerde yürüyen güdümlü füze olarak kullanıyor. Arabanın kontrolünü ele geçiriyor. Seni askeri birliğin kapısına

555 2K 15K 2.7M 2K

SpaceXAI’da Baş Mühendis olarak görev yapan Yağız Nizipli, X’i 5 kişilik ekiple baştan yazmaları ve Elon Musk’ın şirketlerindeki çalışma kültürü hakkında konuştu. “Eskiden yaklaşık 150 kişinin geliştirdiği siteyi şu anda beş kişi yapıyoruz hatta 2 ay öncesine kadar 2 kişiydik.”

OpenChamber 2.0 is out, on OpenCode v2. Skills, agents, MCP servers and plugins now apply the moment you save them. No restarts. My restart button is unemployed. Plus Code Mode, web search cards and a stats page. openchamber.dev/blog/opencode-…

@HRNCN Zahmet etmesin biz onun olduğu yeri huzur evine çeviririz. Az kaldı zaten :)

@johnternus Congrats!

Yapay zeka gelişmelerinden önce, hayatı izleyen, merak etmeyen ve bir şeyler yapma çabası olmayanlara yapay zeka araçları bir fayda sağlamadı. Diğer yandan, YZ gelişmelerinden önce imkan ölçüsünde bir şeyler yapmaya çalışan, bahane sevmeyen kitle ise eskiye nazaran çok daha üretken ve belki altın dönemini yaşıyor. Yani olay kafa yapısında bitiyor yine. Yakınan tiplere istediği imkanı ver yine yakınacak ve bir eylemde bulnmayacak, mücadeleci kitle ise imkanları geliştiğinde bunu kaldıraç olarak kullanmaya devam ediyor. Yıllardır bilinen ve bahsedilen şeyin sağlaması oldu bu gelişmeler.

Claude Fable 5 will be available again globally tomorrow. After a series of productive conversations with the US government, we're redeploying the model with a new set of classifiers to target and block more cybersecurity tasks. In the near term, some routine tasks like coding and debugging will fall back to Opus 4.8. We’ll continue to refine these classifiers over the coming weeks to reduce false positives and better distinguish genuine misuse from legitimate requests. We’ve also begun drafting a consensus framework—with Amazon, Microsoft, Google, and other Glasswing partners—for assessing the severity of AI jailbreaks and how AI developers should respond to them. We invite other industry partners and model providers to join us in this effort. Finally, we’re scaling up our collaboration with the US government on model testing and safeguards. This will include pre-release access to models and safeguards for evaluation, information sharing on jailbreaks and misuse, and dedicated resources for joint research. Thank you to our users for your patience, and to our partners across the government, industry, and the research community who worked alongside us to make Fable 5 available again. Read our full blog: anthropic.com/news/redeployi…

Ben apple ceo'su olsam kendi linkedin'imi kurarım :)

İK Nefreti @ikdannefret

6 months ago

Linkedin'in önemsizliğini şöyle anlatayım: Apple'ın yeni CEO'sunun hesabı böyle görünüyor

78 100 6K 498K 437

ne eksik ne fazla :D

Omkar @omkarships

6 months ago

Interviewer : where do you see yourself in 5 years ? Me :

212 3K 34K 986K 2K

@joshwoodward @GeminiApp İs that support iPad ?