Mamun

@AJENews @AJEnglish Poor people. Doesn’t understand how it’s being played

BREAKING: US reportedly used half its missile stockpile defending Israel - as Israel conserved much of its own defensive arsenal 🔴 LIVE updates: aje.news/61ql75?update=…

🚨This short film exposes the true story of Israel's creation, entirely through the words of its own founders For decades, Israel’s lies have been carefully designed to demonize its victims. To ensure that no matter the crimes it commits, the children it slaughters, the world remains incapable of empathy for Palestinians, or at best, treats it with the same apathy that has allowed this to go on for as long as it has On the 78th anniversary of its creation, it's time the world knew that Israel's past is not different from the brutal present the world is finally seeing

@googlegemma @ollama System design. Still very naive

Built a local coding harness powered by Gemma 4. It runs locally, connects to my model backend, starts coding sessions, streams responses, and uses tools through a CLI-style workflow. Still early, but the learning has been incredible. @googlegemma #llm @ollama

@xiaofengxie @googlegemma @ollama Ollama and then I'm building custom orchestration + harness. I'm still in very early stage, so will see.

@3dgrinder @googlegemma @ollama CLI-style workflow for local LLM coding is the sweet spot. Curious which backend you're using for Gemma 4 — Ollama, vLLM, or something custom? Also, how's the context window holding up with larger codebases?

REPL - done. Who could be the inspiration other than @claudeai for this?

@syamantics And how you instruct? Voice :p

What is code? - Code is instructions for the computer. What is prompt? - Prompt is instructions for LLM. How do we write code? - Python, JS, TS etc. How do we write prompt? - Markdown!

“In wrenching interviews, Palestinians have recounted to me a pattern of widespread Israeli sexual violence against men, women and even children,” our columnist Nicholas Kristof writes. nyti.ms/4ue9mtV

4/ Codex needs better planning. It should dig more deeper before committing to the job. @thsottiaux these are my feedback

3/ Codex good at e2e testing and making things works Well where it lacks? 1/ It’s design variation is very limited compare to Claude. Mean it lacks on imagination or variation 2/ Codex lacks on things alternative 3/ Codex lacks on attaching with user. Psychology wise

When I switched to Codex there are couple of things I found 1/ Codex very good at execution. Then define the execution. Well, it’s need little guidelines but job done. It cover edge cases. 2/ Codex good at backend code. It’s solve complex logic really well.

@sama @rezoundous It just doesn’t give a solution, it’s actually think all different edge cases, it just doesn’t comeup with a quick solution rather than write complete task, less suppression. Only thing lack is better planning, better communication with the user at planning phase, visual design

@rezoundous curious, could you try to explain it?

Can't explain it, but I trust GPT-5.5 more than Opus 4.7 right now.

@sama Codex bad at designing. In the planning phase it should be able to do more visual design, iteration and then enter the execution.

what would you most like to see improve in our next model?

@DanielleFong Goblin gambler!

god help me i am reloading my options account

@GadSaad What is your definition of Canadian?

Canada is built on empathy and kindness toward non-Canadians.

So officially I become Codex guy! Why? - Claude was amazing on planning and execution - Shorter version which doesn’t require deep reasoning But when you are doing coding often we need deep reasoning and longer thinking, less baby sitting. Codex crushed all of it. @sama

@NahidIslam_24 Just a little odd that you are seating beside those war criminals! Just move your neck left or right abd you those faces. Pathetic

We never claimed the July uprising is greater than the Liberation War. Whether it is greater or lesser than the '90s movement is not the point. In the history of Bangladesh, July stands as a distinct, significant chapter, just as the Liberation War remains a monumental milestone. The Liberation War is the foundation of Bangladesh, and on that principle, we remain uncompromising.

@Jokerbernrin @DanielleFong Told ya!

@DanielleFong Feels like speed meets flow state perfectly

gpt5.5:none in fast mode is fucking insane. wu wei

@DanielleFong Surprisingly I’m finding Codex with 5.5 model is way more execution and completion. Even though context get compressed faster due to lower context size compared to Claude but it’s keep going much better completion and deeper thinking.

claude power users club

@DanielleFong I would like to do some beta testing, let me know if possible.

@3dgrinder i need to figure out how to do it legally and safely. i'm working on it

claudeberg we must find and stream these 3%