
Pierre Aube Jr
1.8K posts

Pierre Aube Jr
@paubejr
Chief Operations Officer at TekSavvy and Owner of https://t.co/qfGR4kDwMq Love Tech, Love People, Always have fun! -- How good can it get!?
Windsor, Ontario Katılım Nisan 2009
2.8K Takip Edilen2.1K Takipçiler
Sabitlenmiş Tweet

If you follow me, consider following @ChasmsCom this is the site I run on the side to support contact centers worldwide. It’s a busy one too, and truly worldwide!
English

@PaulyShore @SpaceX @StephenBaldwin7 Omg @PaulyShore I just re-watched this on Sunday.. classic! I support it! Let’s go! #2
English

hey guys, since @SpaceX is surging, what do you think we ride that heat to a sequel? Bio-Dome 2. Bud and Doyle go up to the moon, doodzzz.
@StephenBaldwin7

English

🚀 🚀🚀🚀🚀🚀🚀🚀🚀🚀🚀🚀🚀
Morgan Stanley@MorganStanley
Today, @SpaceX (Nasdaq: SPCX) makes its public market debut with a $75Bn offering (pre-greenshoe) at $135 per share, marking the largest IPO in history. Congratulations to the SpaceX team. We are honored to serve as joint lead bookrunner and sole stabilization agent.
ART

Coding from my phone has officially replaced doom scrolling.
Thanks @NousResearch
English

@ctnzr Exciting to see it faster, I tested it out a while back and my issues was definitely speed. Loved the intelligence of it, but speed was def an issue.
English

Hermes Agent v0.15.0 is out now!
747 PRs by 321 Contributors - thank you all for the work on this release!
Some Highlights:
- NFTY Platform added to gateway channels
- Skill Bundles and MCP Catalog
- Krea 2, Opus 4.8, Qwen 3.7 and more models supported
- Deep xAI Integrations
Huge performance optimizations and code cleanup:
- Load times 50% faster
- Session Search 750x faster
- No more godfile scripts
- Kanban redux
Security Updates:
- Bitwarden native integration
- Brainworm prompt injection defense
- Auto supply chain defense
And a whole lot more, check it all out below

Nous Research@NousResearch
Hermes Agent v0.15.0 - “The Velocity Release” Changelog below
English

@elonmusk Been using grok build for the last few hours, amazing tool
English

Instantly add 5G connectivity to any UniFi Gateway for only $99. Completely license free and carrier unlocked.
Learn more at ui.com
English

@bradmillscan Agreed it’s been running rock solid for me. Been switching between OpenAI and Grok. OpenAI crapped out a while ago but was solid all day.
English

Starlink is making legacy airline Wi-Fi look painfully obsolete
New Ookla data just released, and Starlink-powered airlines are completely destroying older satellite systems in real-world performance
Every single airline averaging 100+ Mbps download speeds is using Starlink
Half of those are already pushing massive 300+ Mbps speeds
And it’s not just speed..
airBaltic, WestJet, and Hawaiian Airlines are now leading the industry in connection consistency too - giving passengers reliable internet from gate to gate
The craziest part is Ookla found that even Starlink’s slowest users are still getting faster internet than the average passenger trapped on an older GEO satellite network
The industry is waking up fast
36 major airlines have already committed to Starlink, and over 5,700 aircraft are now contracted to be fitted with it......roughly 20% of the entire global commercial fleet
The era of paying for slow, broken in-flight Wi-Fi is officially over
Starlink is not just an upgrade. It’s turning airplanes into fully connected flying offices and theaters, anywhere on Earth

English


(2x DGX Sparks) + MiniMax M2.7 NVFP4 = 16 local AI agents running simultaneously 👀
mr-r0b0t@mr_r0b0t
16 local AI agents streaming at once! MiniMax M2.7 NVFP4 — 2x GB10, no cloud APIs.
English


@gigant_theo "A bunch of nerds making progress" has a nice ring to it...
English

Every AI agent today has the same problem.
It forgets everything the moment the session ends.
Your workflow.
Your preferences.
The fixes it learned yesterday.
All gone.
Hermes Agent is one of the first projects pushing in a completely different direction.
Instead of treating AI like a temporary chat window, it treats it like a system that should:
• remember
• evolve
• reuse experience
• and improve over time
That’s why developers are suddenly paying attention to it.
The architecture behind it is genuinely interesting:
• self-evolving skills
• multi-layer memory
• cross-session recall
• autonomous agents running 24/7
• GEPA optimization loops
• persistent personalities & workflows
The result feels less like “using an AI tool”
and more like building a long-term AI operator that compounds with usage.
Made this infographic to simplify how the whole system actually works because this is easily one of the most interesting open-source AI agent projects right now.

Nainsi Dwivedi@NainsiDwiv50980
English















