English
Chenglong
140 posts
Chenglong
@fatedier
Open-source enthusiast | Creator of frp: a fast reverse proxy | Currently focusing on AI Agents
Beigetreten Aralık 2021
32 Folgt79 Follower
Introducing Veo 3.1 Lite, now available via the Gemini API and @GoogleAIStudio. Veo 3.1 Lite supports both Text-to-Video and Image-to-Video, and is less than half the cost of Veo 3.1 Fast.
English
Giving away 5 Opencode Go subs
Winners selected randomly from comments in 24 hours.
OpenCode@opencode
we’ve signed Zero Data Retention agreements with all providers for Go all models now follow a zero-retention policy your data is not used for training
English
I have a feeling that OpenAI won’t go back to 1x Codex usage after April 2
I think they'll do a permanent 1.5x or similar, or maybe extend the 2x for a bit longer
We'll see what happens
Sash Zats@zats
Do we as a community have a coping strategy for the post-April-2 world of 1x token limits? Should I just fwd my salary to @OpenAIDevs?
English
I've actually run up to 5 agents simultaneously.
Usually only 1–2 stay in active conversation (typically during planning or review phases), while the rest run quietly in the background for up to 4–5 hours handling automated feature development, code reviews, local environment API testing, and browser automation tests. It’s definitely manageable with solid orchestration.
My next-stage goal is to push to 10 concurrent agents. To get there, I’ll need to refactor the project to reduce module coupling, enable more comprehensive automated testing, lower the code review bar, and keep 1–2 agents focused on continuous code refactoring.
English
My brain simply can't run more than 3 agents in parallel and QA all of their work.
I am sure I am not the only one.
How do people manage 10 at once?
Or they simply lie?
English
Here comes AutoClaw. We offer a new solution to run OpenClaw locally on your own machine.
- Download and start immediately. No API key required.
- Bring any model you like, or use GLM-5-Turbo, optimized for tool calling and multi-step tasks.
- Fully local. Your data never leaves your machine.
We're giving data control back to Claw users.
Meet AutoClaw → autoglm.z.ai/autoclaw/
Join the conversation → discord.gg/jvrbCRSF3x
English
I think a lot of tutorials push users to search for and install skills too early after setting up openclaw.
In reality, many users don’t even understand their own scenario yet.
And for a lot of simple problems, today’s models + agents + search can already solve them quickly and in a much more customized way.
More skills is not always the answer.
English
The pace of model updates lately has been kind of crazy.
Z.ai@Zai_org
GLM-5.1 is available to ALL GLM Coding Plan users! z.ai/subscribe
English
Voxtral TTS looks like the kind of release developers actually want: open-source, fast, and usable right away.
For voice products, workflow fit matters much more than a flashy demo.
x.com/MistralAI/stat…
Mistral AI@MistralAI
🔊Introducing Voxtral TTS: our new frontier open-weight model for natural, expressive, and ultra-fast text-to-speech 🎭Realistic, emotionally expressive speech. 🌍Supports 9 languages and accurately captures diverse dialects. ⚡Very low latency for time-to-first-audio. 🔄Easily adaptable to new voices
English
@XiaomiMiMo @openclaw @opencode @kilocode @cline @blackboxai Loving MiMo-V2-Pro!
Really hoping you launch a dedicated Coding Plan soon for long dev sessions.
Free trial extension is awesome!
English
🔥 MiMo-V2-Pro has been #1 on OpenRouter — daily, weekly, AND trending — since launch.
Now we're extending free trial FOR ANOTHER WEEK!
The free trial for MiMo-V2-Pro and MiMo-V2-Omni now runs through April 2nd(GMT+8) via @OpenClaw, @OpenCode, @KiloCode, @Cline, @BlackBoxAI.
Xiaomi MiMo@XiaomiMiMo
Free trial for MiMo-V2-Pro and MiMo-V2-Omni available in @openclaw @opencode @kilocode @cline @blackboxai now!
English
If you can reply to this, you love Open-source ❤️
English
Anthropic may not win every benchmark, but they keep staying one step ahead on product.
Claude@claudeai
You can now enable Claude to use your computer to complete tasks. It opens your apps, navigates your browser, fills in spreadsheets—anything you'd do sitting at your desk. Research preview in Claude Cowork and Claude Code, macOS only.
English
Claude Max costs 10x more and gives 20x usage.
By comparison, ChatGPT Pro only gives about 6.7x codex local message usage, not 10x.
Grok@grok
Yes, per OpenAI's Codex docs: Pro ($200/mo) gives ~6x the local messages (300-1500 vs 45-225 per 5h) and cloud tasks (50-400 vs 10-60) of Plus ($20/mo), exactly 6.67x—not 10x. Code reviews are 10x. Multiple Plus accounts are cheaper per limit unit, so more efficient for scaling usage.
English
@robinebers I looked into docs and you would though that it would 10x the Plus subscription, but it’s only 6x…
Getting multiple Plus accounts would be more efficient than multiple Pro accounts
English
Codex $200/mo plans are becoming too small
→ fast mode
→ subagents
→ memory
all burns through limits hard
very smart of them to wait out the $100 plan
it's gonna feel less desirable by the time it hits
English
@kelstar_ @chris__sev Yeah, I also use OpenCode a lot. Sometimes I really want to watch what the agent is doing in real time.
The mobile experience with OpenCode is honestly the best, but the downside is I can’t use my Claude subscription directly with it.
English
@fatedier @chris__sev Nive workaround, but since you already have tmux everywhere you can just monitor every session from ssh\OpenClaw bot
Claude Code remote would look better on mobile though, so still a nice solution =)
English
Claude Code remote control always disconnects
Claude Cowork Dispatch asks for permissions on every chat
Claude Code Channels is finally the most OpenClaw thing. It's been fantastic. Doesn't disconnect. Responds fast. Never bothers you for permissions.
I think we have a winner 🤌
English
Chenglong retweetet
@OpenAIDevs Thanks for the Codex for OSS support! 🙏
Applied about a week ago for frp (105k+ stars, github.com/fatedier/frp) — still no Pro activation yet. Any status update? Appreciate it! ✨
English
We’re reviewing Codex for Open Source applications on a rolling basis.
Here are some of the projects and maintainers who just joined our Codex for OSS community 👇
x.com/athasdev/statu…
athas.dev@athasdev
6 months of free Codex. I will use this to make Athas better. Huge thanks to everyone who made this happen ❤️
English
MiMo-V2-Pro first look: noticeably better than MiniMax-M2.7 in my tests. Solid upgrade.
Try it → mimo.xiaomi.com
Xiaomi MiMo@XiaomiMiMo
Introducing MiMo-V2-Pro & Omni & TTS mimo.xiaomi.com
English