codex is on it! if this works, we can ship this as an official plugin 🙂
CODE
-
AI crosses the threshold of recursive self-improvement
By
–
AI has just crossed a threshold: recursive self-improvement. Models write the code that trains them, discover the algorithms that will make them better, design the chips that run them… The machine improves the machine, which will improve the machine.
-
Why code neural net from scratch for tabular ML when XGBoost exists?
By
–
Why are you, a grown man, still coding a neural net from scratch for tabular ML when XGBoost exists? @trainxgb
-
Hermes Agent distributes tasks between local agents and Claude Code/Codex
By
–
Hermes Agent can do that for your setup.
— Shubham Saboo (@Saboo_Shubham_) 7 juin 2026
Direct small tasks to Local and open-source coding agents and bigger ones stay on Claude Code and Codex.
Hermes handles the handoff and everything is tracked natively in Hermes Kanban board. https://t.co/cR9Ai6l8ga pic.twitter.com/AmrbckT9JpHermes Agent can do that for your setup. Direct small tasks to Local and open-source coding agents and bigger ones stay on Claude Code and Codex. Hermes handles the handoff and everything is tracked natively in Hermes Kanban board.
-
ChatGPT superapp overhaul rolling out in coming weeks
By
–
OpenAI’s ChatGPT "superapp" overhaul could start rolling out in the coming weeks. The first wave likely won’t be one big launch, but a phased redesign pushing users toward Codex, agents, image generation, and partner apps. As one OpenAI employee told the FT: "Chat is dead", the
-
Printer can now print images using Epson FX-86e driver and raw data decoding
By
–
🖨️🖼️ Big progress: it can now print images too
— @levelsio (@levelsio) 7 juin 2026
I had to install a different printer driver, Claude Code recommended Epson FX-86e which supported images
Then I printed an image, it helped me dump a .bin from the printer raw data output, then it decoded the .bin and figured out… https://t.co/S6n7Z5koOa pic.twitter.com/StqNvf8bzuBig progress: it can now print images too I had to install a different printer driver, Claude Code recommended Epson FX-86e which supported images Then I printed an image, it helped me dump a .bin from the printer raw data output, then it decoded the .bin and figured out
-
London event: Codex demos, future plans, and unhinged creations
By
–
Hello London Come hang with us tomorrow and chat about Codex – what it can already do, what’s coming next, and all the slightly unhinged things people are building with it We’ll bring plenty of high-quality GPT-5.5 tokens, some exclusive merch, and banger vibes. Pull up?
-
Vibe Code an Entire Startup in One Afternoon to Build $1B Business
By
–
🚨 BUILD $1 BILLION BUSINESS – VIBE CODE AN ENTIRE START-UP IN AN AFTERNOON
— Abacus.AI (@abacusai) 7 juin 2026
– one prompt to build both web and mobile apps
– accept payments with one click
– no coding required
Abacus AI agent uses top frontier models like Opus 4.8 and GPT 5..5 xHigh to build complete software… pic.twitter.com/5IBKRDKyHWBUILD $1 BILLION BUSINESS – VIBE CODE AN ENTIRE START-UP IN AN AFTERNOON – one prompt to build both web and mobile apps
– accept payments with one click
– no coding required Abacus AI agent uses top frontier models like Opus 4.8 and GPT 5..5 xHigh to build complete software -
Repo2RLEnv turns GitHub repos into RL training environments
By
–
Turn any GitHub repo into an RL training environment!
— Sumanth (@Sumanth_077) 7 juin 2026
Repo2RLEnv is a new open-source tool from HuggingFace that synthesizes verifiable RL training data from any GitHub repository. Point it at any repo and it automatically generates tasks, verifies them, and pushes datasets… https://t.co/VXqSNNcVNp pic.twitter.com/p0zmmycsZSTurn any GitHub repo into an RL training environment! Repo2RLEnv is a new open-source tool from HuggingFace that synthesizes verifiable RL training data from any GitHub repository. Point it at any repo and it automatically generates tasks, verifies them, and pushes datasets
-
Define Trainer object by specifying training config
By
–
Define Trainer Here, we create a Trainer object by specifying the training config, like learning rate, model, tokenizer, and more. Check this out