
Founder @S2olutions and Spectre Spaces. I build Skillz.
Ohio, USA
Joined June 2011
- Tweets86K
- Following2.3K
- Followers4.9K
- Likes18.4K
there is a much more simplified route if you have @Cloudflare @CloudflareDev maybe I will post the video after all
Let your Grok Bot / Muse talk to your Claude Code / Codex or any other agents
Introducing Reason Network,
Free, peer to peer and Open-Source Engine
Loop in your teammates too so no live agents work collides when coding.
Try it for free: reasonmachines.com/network
one click install and setup!
The fair is $42 for a 2 mile drive?
When you thought you took care of everything for the launch video 🤦♂️
HERMES CAN NOW CONTROL YOUR PHONE. 🤯📱🔥
A new Phone Harness plugin gives Hermes the ability to actually operate an iPhone or Android.
We're talking real phone control:
• See what's on the screen
• Open apps and navigate menus
• Tap, swipe, scroll, and type
• Read the results and continue working
• Handle multi-step tasks inside mobile apps
And here's what makes this so interesting...
Hermes doesn't need a dedicated API integration for every app. It can interact with the same interface you use.
Supports iPhone through Mac mirroring, Android through ADB, and cloud phones.
Think about how many new workflows this opens up for Hermes.
Repo + setup in the first reply. 🔥
@phone_harness
Charles Spectre retweeted
We are excited about the future. The work and advancement has been surreal.
Opus 5.5 is the highest grade of any intelligence on the planet at this moment.
It is so important to be knowledgeable in AI, the future is being shaped right now.
AGENT WARS
We asked 5 top AI models to design, engineer and 3D print a bridge to with the goal of holding the most possible weight.
🇺🇸 Anthropic: Claude Opus 5.5 (High)
🇨🇳 Kimi: Kimi K3 (High)
🇺🇸 Meta: Muse Spark 1.3 (High)
🇺🇸 OpenAI: GPT 6 Astra (High)
🇺🇸 SpaceXAI: Grok 4.7 (High)
Each bridge had specific parameters. It had to span 2 feet, use a maximum 500 grams of filament, and it had to be under 18 hours of printing time. We specified what type of weight and where we would place it on the bridge.
The Score:
• Claude Opus 5.5 held an estimated 130 lbs! It took 9 hours and 11 minutes to print 17 parts and used 441 grams of filament.
• Meta Muse Spark 1.3 held 26.5 lbs. It took 13 hours and 12 minutes to print 49 parts and used 478 grams of filament.
• OpenAI GPT-6 Astra held an estimated 17.5 lbs. It took 15 hours and 44 minutes to print 29 parts and used 442 grams of filament.
• SpaceXAI Grok 4.7 did not finish. On assembly it could not stand up by itself. It took 12 hours and 22 minutes to print 29 parts and used 460 grams of filament.
• Kimi K3 did not finish. It wasn’t engineered correctly so the bridge could not even be assembled. It took 11 hours and 19 minutes to print 35 parts and used 446 grams of filament.
That means our champion for this episode is Claude Opus 5.5. Not only did it hold the most weight (by FAR) it also took the least time to print, used the least amount of parts and used the least amount of filament.
This was episode 02 of Agent Wars, stay tuned for episode 03.
Gemini 3.8 Flash TTS turns voice generation into your full creative studio.
Design original character voices from scratch across 100+ languages, stage two-speaker dialogue, and tailor every performance line by line with natural laughs, sighs, whispers, and more.
Charles Spectre retweeted
Asked Opus 5.5 for a video on data centers.
The result is beyond what I could've imagined 🤯
Insane what models can do with a reference video and permission to pull or generate any footage they want.
This right here. Never give up. Pursue your dreams so you can't say you didn't.
FYI: We build dreams over ---> @S2olutions ---> s2olutions.com 🛑👍
Charles Spectre retweeted
Replying to @CharleSpectre @jasonlk
Companies fat lining their pockets —> Companies Flatlining their livelihood —> Spectre Spaces makes it all good 👏🏼 🥂
#WorkFlows #S2olutions
Spaces.s2olutions.com S2olutions.com
What a beautiful time to be alive, other companies gouge, Spectre Spaces gets to wear the cape 🦸♂️
Have you seen it yet 👀
So almost every pre-AI B2B product we use has told us they are raising prices for agent access.
Salesforce and HubSpot are two of the latest, albeit differently (the price increases at HubSpot seem to be mainly for their own agents, while Saleforce is increasing prices for third party agents). But it’s not just them. Another niche CRM we’ve used for 5+ years just told us we have to pay extra for agent use of API. Another niche product we use just deprecated the API we were using for 10K.
Maybe the only apps not doing this … are the ones that started agentic.
What I worry is the vendors aren’t thinking this through.
The immediate reaction of our agents to agentic price increases is … How Can We Work Around Them.
Not cheat. But literally to move data off all these platforms so there is no API tax for the agents to use them.
And the humans naturally will want to stop having their agents use apps that raise steep prices to use them.
So I do worry these vendors are inadvertently creating an agentic death spiral. Usage will drop, new agents will move off the platforms as much as practical, and these API tools will lead to less usage, less stickiness, and … less of a moat.
Your next workspace isn’t a desk.
It’s a SPACE. 🧠⚡️
AI agents.
Real-time production.
Your team.
One workspace.
SPECTRE SPACES.
Built for your next move.
#SpectreSpaces #AI #AIAgents #FutureOfWork #Tech #Startup #AgencyLife #Innovation










