DamBuildShit

@AlertesInfos on peut pas trop lui en vouloir...

🇫🇷 Emmanuel Macron aurait entretenu durant plusieurs mois une "relation platonique" avec l’actrice iranienne Golshifteh Farahani, avec des "messages qui seraient allés assez loin", provoquant des tensions au sein du couple présidentiel, qui auraient conduit à la gifle. (via @Florian_Tardif)

@StateDept If Elon Musk didn't buy X, this post would've never been allowed to exist

@KaiXCreator Clo founder ?

Can you call yourself a founder if your entire product was built by Claude?

@cjzafir The better the plan, the less the refactor 😎

My current workflow: 1. I have an idea. I open Codex desktop app to plan (without plan mode: overcomplicated). I use Codex 5.5 High (fast). 2. Once I get v1 of the plan, I use this hack: "Are you 100% confident in this strategy? If not, find all possible loopholes, suggest proper fixes, and run this loop until you are factually 100% confident in the new strategy." 3. This finalizes my plan, schema, and file tree, rules and quality gates. Then I use DeepSeek V4 Pro and Kimi 2.6 as executors. So Codex acts as the orchestrator, and these two act as executors. 4. Codex uses computer use to test in the browser, run deep quality checks, and only pass high-quality outputs to production. 5. I make Codex autonomous so it can plan, execute, audit, fix, and continue executing each task. Similar to what /goal is right now. That's it. I just oversee reports, current status, and final outputs. I trust Codex 5.5 when I have robust specs attached. Also, a few tips: - Tell Codex: keep folders, subfolders, and files neat and clean. Well-organized, with no dead code or unused files. - Always make a task list for every item you work on. (This fixes the Codex quitting-in-the-middle/context-loss issue.) - Use the "measure twice, cut once" policy so you get things right the first time. - Don't overcomplicate your workflow, and don't overlook important things. This flow is running brilliantly. Super cheap because of DeepSeek V4 API costs, while the intelligence comes from Codex 5.5. And yes, I don't use Opus 4.7/4.6 because that model is nerfed now. It hallucinates its work, is always in a rush to wrap up the session, and gets stuck in loops while debugging. So try this simple Codex × DeepSeek/Kimi workflow and thank me later.

@arseniycodes Tried yesterday to do some design, then reinstalled Figma… It’s useful to mockup website, and reiterate fast, then hands off to Claude code. But pure design wise, no thank you

anthropic released Claude design about a month ago. is anybody using it?

@shipper_now Im sure Capcom is shaking right now.

Today, we've ended game development forever. I just watched my Mac one-shot a football game in 2 minutes 58 sec. This is just insane.

@adonis_singh It’s been like this since codex. Only CC advantage has been tool calling and agentic feel. But for real coding tasks. codex has been a league ahead

consensus is pretty clear; codex is killing cc right now it will take a while for the normies to catch up, most still think claude is some unbeatable God that is stomping gpt in 'technical stuff'

@levelsio This is something that should not change. Many clients are now pasting services proposal in Claude or gpt, if the model starts to tell them “hey no this can be build in 2h and 20 prompts, we are cooked.

My Claude keeps saying "that's a day of work" when it's like done in 5 min 😂

@gregisenberg Postiz self hosted is a bridge, it does not let you post, you still need to get the full approval from FB, LinkedIn, TikTok…

startup idea for you use postiz (20k+ github stars project) to sell AI social media content/management to 1 niche of SMBs. what's postiz? it's an open source social media scheduler with AI built in. basically buffer + AI and free to download. 1. self-host postiz. use codex/claude code to help you figure this out in an afternoon. 2. pick one niche. dentists, realtors, lawyers. can even go a subniche like orthodentists vs dentists. family law over of lawyers. 2. wrap it in their language. "AI social media for dental practices" 3. add "we write your captions with AI" as the hook. that's what they're actually paying for. 4. plug it into n8n, make, or zapier so posting, scheduling, and approvals run on autopilot. the client approves with one tap. everything else is handled. 5. charge $50/mo-$100 per seat. that's nothing to a business paying $2,000/mo for a social media freelancer. you're 25x cheaper and 10x more reliable because the system runs whether you're awake or not. win-win for everyone. 6. build one landing page. run one onboarding call. that's the whole sales motion. 7. build media to attract customers. post tips for that niche on X, tiktok, youtube. become the "social media for dentists" person. 8. reinvest profits to build other tools that serve that same niche. scheduling, reviews, patient intake. build those tools or plug in more open source projects. now you own the vertical. these businesses KNOW they need to post. they hate doing it. they will never find postiz on github. they will google "someone please handle my social media." that's you open source is the new wholesale. the code is free. the customer relationship is where the margin lives. you can do this as one person. you can do this as a two person team. you don't need funding. you don't need an office. you need a laptop, a niche, and the willingness to start. someone is going to do this. might as well be you.

5.4 was still better than opus 4.7 to me. Just asked 5.5 to review a spec that Opus 4.7 did yesterday...and 5.5 found many gaps. Opus is great don't get me wrong, what I have observed is that if you give him a doc, and he can't find what its looking for too easily, he will just guess and it ends up implementing something broken. The biggest gap is the fact that 5.5, even codex from 5.2, they rarely guess, they just ground up in facts period.

Anyone tried GPT-5.5 yet? Is it comparable with Opus 4.7?

@OpenAI Every time I want to have a quiet evening, they release a new model to test. Ai never sleep slop.

Introducing GPT-5.5 A new class of intelligence for real work and powering agents, built to understand complex goals, use tools, check its work, and carry more tasks through to completion. It marks a new way of getting computer work done. Now available in ChatGPT and Codex.

@amaanbuilds That’s so smart

You love to see it. Wake up and see that Codex have been working almost 7hours non stop on my dataset. good start of the day.

Seems more like Anthropic is loosing the AI frontier war, and they are throwing a dart at every vertical to try to catch up. Future will tell…

“Ai content don’t rank” they said. Me …Hold my beer.

@vasuman The 'It's Over' convinced me.

Claude Mythos just refactored my entire codebase in one call. 25 tool invocations. 3,000+ new lines. 12 brand new files. It modularized everything. Broke up monoliths. Cleaned up spaghetti. It worked.

@jnowland @OpenRouter I forgot, the export OPENROUTER_API_KEY="" first, my bad.

I'm using the main Claude Code, but you can use a different model inside. Just get the API key from @OpenRouter export ANTHROPIC_BASE_URL="openrouter.ai/api" \ export ANTHROPIC_AUTH_TOKEN="" \ export ANTHROPIC_API_KEY="" \ export ANTHROPIC_MODEL="qwen/qwen3.6-plus:free" claude Then it will recognise Qwen straight away and display 'APi billing'. Works fine, Lmk

I feel like I'm cheating like in a video game. Using Claude Code with Qwen 3.6 Plus for free via @OpenRouter is terrific.

It seems Anthropic start to listen the community. I believe this does not make back the waste of time of the last 15 days, but it's a first step. If Claude Code's limits are now back as before. I will most likely resubscribe.