MaDdWiz

@Voxyz_ai If you need better memory for your OpenClaw check me out 🤓github.com/maddwiz/NovaSp…

@thsottiaux The ability to control everything by mobile. Have a mobile dashboard that can control your codex and openclaw on your other computers in one place on your phone

What are we obviously not getting right with Codex?

@ziwenxu_ @sama The knock out blow imo lol

@sama Nicee!!! That's what we talking about!

you can sign in to openclaw with your chatgpt account now and use your subscription there! happy lobstering.

@sama The knock out blow

@thsottiaux I’m currently building an OS kernel I haven’t been able to to get it to work more than 30 mins at a time what am I doing wrong ?

You can now keep codex going for days. With GPT-5.5 it will build an entire OS kernel for you if you ask, or find critical bugs in a codebase, or optimize your database schemas, or… the options are endless.

@grantcohn Nope . What Jennings was doing on 3rd downs was historic in my opinion and doesn’t get enough credit for how elite he is on 3rd and whatever.

Will third and De'Zhaun be a thing?

@ziwenxu_ 😭😭😭 so true

how vibecoding looks at you at 2:30am right when you said "one more fix" 3 hours ago

@HeyAbhishek Why do all the models use that hideous tan color in all ui . I can’t stand it

@bridgemindai And yet you went full anti OpenAI without fully testing that aspect . Seemed like anthropic was cutting you a check it was so biased

GPT 5.5 has higher per-token pricing than Claude Opus 4.7. But it uses far fewer tokens to do the same work. Cost to run the full Artificial Analysis Intelligence Index: Claude Opus 4.7: $4,811 GPT 5.5: $3,357 GPT 5.5 is 30% cheaper to actually finish the job. The headline price isn't the real price.

@bridgemindai Lmfao nobody believes this . It’s called token efficiency

GPT 5.5 is now the most expensive frontier model in the world. $11.30 per million tokens. Claude Opus 4.7: $10. DeepSeek V4 Pro: $2.20. Kimi K2.6: $1.70. A few months ago Sam said Anthropic was the expensive product for rich people. Today Anthropic is 13% cheaper than OpenAI's flagship. The expensive product is yours now, Sam.

@thsottiaux The most liked man in the Ai industry

Don't just reset Codex rate limits for fun, it costs money. Don't just reset Codex rate limits for fun, it costs money. ... but the vibes are good ... I have reset Codex rate limits for ALL paid plans to celebrate a good week and allow everyone to build more with GPT-5.5. Enjoy

@cb_doge These are horrible examples lol

Ex-board member of OpenAI calls Sam Altman a liar. He lied to the board for years, hid ChatGPT launch, lied about owning Startup Fund, falsified safety info, and lied to oust her after her paper. Board lost all trust → fired him. Sam Altman is a liar.

@WatcherGuru @PeterSchiff Oh like his bank ?

JUST IN: Peter Schiff says Bitcoin $BTC will crash "close to zero."

@LombardiHimself 😭

John Lynch: "We've got consensus in this building. That's the consensus I care about."

@Taurock Can’t wait till someone beats the brakes off this guy

Security told Chud to move. He calls them Nig**** & walks off. White woman hears him and asks to walk him back over to say it to there face. "You don't wanna say it to there face, scary ass"

@boldclips Streamers are fuckn annoying

Ed Matthew's team gets a GUN PULLED ON THEM over a Tesla charger dispute & Jay Cartwright has a HUGE CRASHOUT & GETS ARRESTED 👀🚨

@Coach_Yac This will go down as one of the worst drafts of all time by any team

The 49ers trade with the Ravens: The 49ers receive: Pick 154 2027 6th-round pick The Ravens receive: Pick 133

@jgrover1533 Because they draft all the guys way too early . And the biggest hole of all is Offensive line and decided not to go for the top prospects. The wr won’t see the field and the odds of a rookie rb most likely won’t make an impact anytime soon . A waste

Fans calling this a bad draft. Why? We all knew they’d go Edge, WR ect. Is it because it’s not the names ESPN or your favorite podcaster told you about. Again it’s crazy we have to repeat this but your favorite podcasters board doesn’t match the teams board #49ers

@Rasmic Said no one ever

not impressed with gpt 5.5 back to opus

@49ersDepression lol how do u get a d+ when all the grades are below a D 🫠

In case you’re wondering how the 49ers draft is going

@ziwenxu_ Would love to compare the two on some benchmarks. is it open source memory ?

@ziwenxu_ I was actually attempting to build up the courage to propose a partnership with my longterm agent memory stack I built 😩🤦🏽‍♂️. Did you build this memory yourself?

I finally gave my AI agent a brain that doesn't reset. Finished the Knowledge LLM implementation today. Most agents are goldfish-they forget the entire architecture the second you close the terminal. Not this one. I've transformed Hyperclaw from "run and forget" into a persistent system that actually learns your codebase. It doesn't just execute tasks; it builds a living library of how you build. What changed: > v2 now retains context across sessions. The more you use it, the less you explain. > Instead of stuffing the context window and praying, the Knowledge LLM pulls exactly what the agents need to see. One step closer to unleashing this thing. Can't believe we're almost there: the Hyperclaw workspace for all agents-Hermes, Claude Code, Codex, and OpenClaw. Stay tuned.