English
Mark Smith
64 posts
Mark Smith
@marksmithdotdev
I spend to much time with computers...
London, U.K Beigetreten Nisan 2014
110 Folgt9 Follower
@robinebers I think part of OpenAI's remit is/was to help facilitate the adoption and use of AI across as wide a population base as is possible, you utter cunt... Why don't you pay the higher API pricing which is guaranteed capacity?
English
@thsottiaux @danveloper I love codex and gpt, but it can go off on a tangent and lose sight of the actual goal... I also had it write 120 md documents about how it should do something, rather than it actually do the thing... found changing its persona from concise to more friendly seems to help a bit.
English
@danveloper Tell me more. What do you need from it that you’re not managing to make work?
English
@MiniMax_AI I am a dummy... used:
mmx auth login --method api-key --api-key sk-....
and all good!
English
@MiniMax_AI getting 404 page not found when i run: mmx auth login from my mac and it opens safari after having run both npm install -g mmx-cli and npx skills add MiniMax-AI/cli -y -g I am on the global token plan!
English
Introducing MMX-CLI — our first piece of infrastructure built not for humans, but for Agents.
Your Agent can read, think, and write. But ask it to sing, paint, or show you a world it's never seen — and it falls silent. Not because it doesn't understand, but because it has no mouth, no hands, no camera. Today, that changes.
MMX-CLI gives every Agent seven new senses — image, video, voice, music, vision, search, conversation — powered by MiniMax's full-modal stack, today's SOTA across mainstream omni-modal models.
One command: mmxAgent-native I/O. Zero MCP glue. Runs on your existing Token Plan.
Two lines to give your Agent a voice:
npx skills add MiniMax-AI/cli -y -g
npm install -g mmx-cli
Then tell it: "you have mmx commands available."
It'll learn the rest.
Github → github.com/MiniMax-AI/cli
Token Plan:
platform.minimax.io/subscribe/toke…
English
@steipete Installs update... 'Hey — fresh session, blank slate. Looks like this is our first time talking, or I've been wiped and reborn. Who am I here? And who are you?' wft...
English
We did it, say hi to the $100 plan!
It should be the sweet spot for a ton of you. It comes with a ton of codex usage. And yes we are resetting the limits again too as I mentioned yesterday. Let’s keep building!
OpenAI@OpenAI
We’re updating our ChatGPT Pro and Plus subscriptions to better support the growing use of Codex. We’re introducing a new $100/month Pro tier. This new tier offers 5x more Codex usage than Plus and is best for longer, high-effort Codex sessions. In ChatGPT, this new Pro tier still offers access to all Pro features, including the exclusive Pro model and unlimited access to Instant and Thinking models. To celebrate the launch, we’re increasing Codex usage for a limited time through May 31st so that Pro $100 subscribers get up to 10x usage of ChatGPT Plus on Codex to build your most ambitious ideas.
English
@OpenAI Very pleased you guys have done this, I will be switching from my 3 plus accounts to the new £89 pro account at the end of the month! And big respect for making it £89 rather than 100, every little helps!
English
The Codex promotion for existing Plus subscribers ends today and as a part of this, we’re rebalancing Codex usage in Plus to support more sessions throughout the week, rather than longer sessions in a single day.
The Plus plan will continue to be the best offer at $20 for steady, day-to-day usage of Codex, and the new $100 Pro tier offers a more accessible upgrade path for heavier daily use.
English
We’re updating our ChatGPT Pro and Plus subscriptions to better support the growing use of Codex.
We’re introducing a new $100/month Pro tier. This new tier offers 5x more Codex usage than Plus and is best for longer, high-effort Codex sessions.
In ChatGPT, this new Pro tier still offers access to all Pro features, including the exclusive Pro model and unlimited access to Instant and Thinking models.
To celebrate the launch, we’re increasing Codex usage for a limited time through May 31st so that Pro $100 subscribers get up to 10x usage of ChatGPT Plus on Codex to build your most ambitious ideas.
English
@BlobWarriorUK £60pp! Are you out of your mind? And you are moaning about the discount for people who have got much better things so spend their money on... and probably couldn't even afford the tube fare if they wanted to? You have to be some sort of plant...
English
It costs £59.30 to visit the Tower of London, but worry not hard working Brits! If you're claiming universal credit it's £1 each for up to 6 of you!
Hard work pays...
English
@PatrickChristys Shouldn't the issue be more about the extortionate 'normal' ticket prices... Anyone on UC isn't going to any of these places... would love to see figures on how many UC discounted tickets have actually been freely purchased...
English
I’m sorry but this is absolutely ridiculous
English
@kr0der Xhigh and fast has been used extensively in preparation... I hope Tibo comes through otherwise I am screwed!
English
i'm not gonna use enough for tomorrow's reset, GG
how's everyone's usage looking
Tibo@thsottiaux
I realize yesterday’s Codex reset came in a bit at an unfortunate time given the last one was almost perfectly a week ago. To really celebrate the 3M I’ll reset again tomorrow. Thanks for the feedback!
English
@steipete How you managed to get a job with openai based on this pile o shite is a fucking mystery to me, but well done... would be good if this thing actually fucking worked tho...
English
Some folks try to spin a narrative that I don't like local models, meanwhile I spent a lot of time making it easy to use OpenClaw with them.
Latest release adds support for inferrs, which is a new super efficient TurboQuant inference server:
docs.openclaw.ai/providers/infe…
English
@openclaw this pile o shite drops its config after every update and when using the web interface i never know if its still doing something, done or just crashed out... fuck me....
English
OpenClaw 2026.4.7 🦞
🔮 openclaw infer
🎬 music + video editing
💾 session branch/restore
🔗 webhook-driven TaskFlows
🤖 Arcee, Gemma 4, Ollama vision
🧠 memory-wiki: persistent knowledge, not just vibes
Because “trust me bro” is not a knowledge system. github.com/openclaw/openc…
English
@NousResearch You need a web interface... i want to be able to install on my server and use a browser to work with Hermes... openclaw is dogshit but it has a web interface...
English
Hermes Agent v0.8.0 is here.
Full changelog below ↓
English
@LearnDIY_ All it takes is one mistake and that guy loses a finger or worse... how many mistakes did you make at work today? Feck that!
English
@thsottiaux I think if you reset the codex limits it would symbolise the reserection of Jesus Christ which is very meaningful to over 2 billion people apparently... could be a massive marketing win!
English
Do you want 3 months of Codex Pro?
Comment under the post we are selecting a 5 people very soon
3 MONTHS of Pro. I genuinely think this is the highest leverage sub we have
Sarah Chieng@MilksandMatcha
Giving away 5 Codex Pro plans Each person will get 3 months of free Codex Pro (highest tier). Winners will be selected from comments in 48 hours, comment below why you want it.
English
Our Codex dashboards are showing increased rate of users hitting rate limits and since we don't fully understand why I have made the cautious decision of resetting the usage limits for all plans. Enjoy.
I also wanted to celebrate us finding a pocket of fraudulent accounts that we banned and have helped us regain some compute. The fight against abuse never stops, but it's important to mark the moment and make it a little shared victory.
English
@hiddnest they seem to be ignoring 50/100 plans... - pain in the arse!
English
