Alex Xander

@0xSero "Each jump costs 2x more in output tokens" good to know! Is there more info where you found this?

Your sign to use Codex on medium thinking, you'll be able to run 4x the loops compared to xhigh and 2x compared to high. Each jump costs 2x more in output tokens

@araseb_ Natural Smartness ... I had to say it sorry

What's coming after artificial intelligence?

@codevsdev I don't think the developer role is so clearly defined anymore. Roles (QA, PM, PdM, sec) are aggregated and competences matter most. For me? Finding the right target

what's your biggest challenge as a developer today?

@vivoplt Did you benchmark this with Cursor as well? 🙃

Apparently, telling Claude that the code was written by Codex gives it an instant +25 IQ boost.

@AMD @NeowinFeed even the AMD title calls it AI Max+395 ... not 495 ... which would be the same nonetheless sigh

.@NeowinFeed highlights AMD Ryzen AI Halo, powered by Ryzen AI Max+ 395 and designed to give developers and creators the Windows 11 support, ROCm tools and high-capacity memory needed for powerful local AI performance.⚡ Read more here: neowin.net/news/amd-launc…

Use cases: - local agentic development - experiments with AI orchestration for intelligence (this requires batching but it should be the same on both) - robotics research (based on wishful thinking that I'll have time to spare) OpenClaw, Hermes, ... are NOT in scope

Strix Halo vs GB10 //help me choose 128GB Pro Strix - costs 30% less Pro GB10 - nvlink expandability in future (bigger models) - slightly better performance Cons (both) - limited bandwidth compared to PCI cards - thus less future-proof for coming diffusion models

@RyanOlunix How many solo-entrepreneurs with 0$ for marketing read this post?

You have $0 for marketing How are you getting your first 100 users?

@bijanbowen I can already see dealers in shady areas of parks... "You looking for dangerous weights? I got what you need... all the best quantizations"

I think the advice to go into debt to get a GPU is beyond dumb. If anything, buy a physical HDD and store things on it so if the day comes, you have the models and can THEN go into said debt..

Malware authors embedded policy-triggering content in repo comments. Why? To trigger guardrails of LLMs employed for security analysis. This practically blocks LLMs which refuse the evaluation of following malicious code. Full story here: socket.dev/blog/mini-shai…

@petergyang @jxnlco Just noticed that even the poet follows him🔥🔥🔥

Follow @jxnlco y'all he writes some bangers about codex and as you can see below needs social media to validate himself 😂

@MiaAI_lab I see so there's no specific reason for which you prefer XML

@naturalSmartnes You can select output format, including md, xml, and txt. It's to provide relevant context for any llm without looking at the whole codebase/files and waste tokens/efficiancy/speed.

RepoPrompt for Windows Open any project folder → select exactly which files matter → generate clean, LLM-optimized XML output. 📁 Open any project folder ✅ Select exactly which files matter 💰 Set your token budget 📋 Generate clean, LLM-optimized XML output 🪟 Built for Windows 🔒 Local & private 📦 Free Try it out here: github.com/MiaAI-Lab/repo…

@d4m1n @ClaudeDevs I'm wondering why they released the -p option at all if then they ban people using it

@ClaudeDevs in summary: 1. RIP claude -p 💀 and 2. Anthropic hates developers

Starting June 15, paid Claude plans can claim a dedicated monthly credit for programmatic usage. The credit covers usage of: - Claude Agent SDK - claude -p - Claude Code GitHub Actions - Third-party apps built on the Agent SDK

@steipete The idea that we want something, we buy it and after a while you trash it has already gotten out of hand

This shortage of chips is getting out of hand.

@MistralAI do you really want people to install Python just for you?

@Tech2Wild @mr_r0b0t @NVIDIAAI agentic coding is so freakin addictive... even if it's cloud-based... I have to go back to running (fight addi... fight fire with fire)

@mr_r0b0t @NVIDIAAI 🤣🤣🤣 that shit is fucking addicting

So I did a thing 😁

@MatthewBerman Clickbait? Your interpretation is far from what @petergyang said. Otherwise... you've been distilling too 😏

Distillation hacking is real

In 2021 I proposed to my then-employer the idea of giving end-of-life smartphones a second life as aggregated compute resources. Proud and happy for the environment to see this happening! research.google/blog/a-low-car…

@Tech2Wild Yes, basically it's like Cursor: subscriptions give you generous usage of Google models + limited Anthropic. You can also bring in other API keys or install plugins (tested Codex, works fine). Even on paid plans, (all) LLM streaming coming directly from Google had hiccups.

@naturalSmartnes I’m new to Google and how they work because there whole tier shit is weird. Does this equate to usage if you have a subscription ? Or is this all API because that was my biggest issue with Google I never saw a usage bar.

It's interesting to see how for once the negative feedback of the public was able to steer the direction of a frontier lab