My new track MEGAWAVE is out now 👾 Built around #8bit synths and #16bit samples, it sounds like the soundtrack to a game that never existed, somewhere between Mega Man, Sonic the Hedgehog, and The Great Giana Sisters.
Listen here: https://t.co/offC7WflmY
I am new to Opencode / oh-my-opencode. I told Sisyphus that bigger coding jobs should be handled by Hepaestus and when it got the task, it said "Now let me delegate the backend implementation to Hephastus" and starts Sisyphus-Junior instead. Help please.
📣 Open call to agent builders: Let's read agent skills from `.agents/skills`, so people don't have to manage separate folders per agent.
Today we pulled the trigger for Codex to read `.agents/skills`. Goal is to deprecate `.codex/skills`.
Pls like/tag/RT for momentum.
The UX of the future won't be terminal tabs.
I'm a very visual person - I want to manage my agents from a UI.
Building this for @openclaw . Will open a PR if it's interesting @steipete
I used every AI harness so you don't have to, I go over Claude Code, Cursor, Zed, Droid, Codex, Opencode, Pi, and more..
I hope this helps you explore
https://t.co/dhUHZ7EXzQ
@f1 Is there a deadline for a team to complete the safety tests, if so what happens if a team doesn't get the car safe before season start? DQ for all of the season or?
🔥 Codex 0.9.0 is out, and with it, a bunch of new changes. Some of these updates are exactly what you've been waiting for 🫵.
Starting with Codex's new Plan Mode! There's been some improvements since my last tweet. This is going to be a long one, so buckle up. 👇
My latest track 'Overdrive' is a homage to the era of early 3D graphics and classic PlayStation vibes 🎮 Available now on all major music platforms: https://t.co/Qch6RWwjf6
You can now run GLM-4.7-Flash locally on your device!🔥
GLM-4.7-Flash is the best performing 30B model on SWE-Bench and GPQA. With 200K context, it excels at coding, agents, chat & reasoning.
Run local with 24GB RAM.
Guide: https://t.co/FvktWODg61
GGUF: https://t.co/t3xNcKRjJp
Introducing GLM-4.7-Flash: Your local coding and agentic assistant.
Setting a new standard for the 30B class, GLM-4.7-Flash balances high performance with efficiency, making it the perfect lightweight deployment option. Beyond coding, it is also recommended for creative writing, translation, long-context tasks, and roleplay.
Weights: https://t.co/uzhvLmHDoI
API: https://t.co/bl6YxjOzzC
- GLM-4.7-Flash: Free (1 concurrency)
- GLM-4.7-FlashX: High-Speed and Affordable
@alexhillman Guessing they are circling this now because the ”Web 3 Games” never took off and VC’s don’t want to invest in that so they are now trying to go for ”web 3 AI” I am guessing.
New track 'Overdrive' is out now! Listen here: https://t.co/Qch6RWwjf6
This one is a salute to the era of early 3D graphics and classic PlayStation vibes 🎮 #ps1
Artwork: Victor Estrella