Seth9.ai🐔🐷⛰️🪙

2.1K posts

Seth9.ai🐔🐷⛰️🪙 banner
Seth9.ai🐔🐷⛰️🪙

Seth9.ai🐔🐷⛰️🪙

@MU_sings

Building/running OpenClaw agents | Agentic AI + Tesla/SpaceX enthusiast | $TSLA investor

Katılım Eylül 2009
1.4K Takip Edilen852 Takipçiler
Seth9.ai🐔🐷⛰️🪙
@farzyness Hermes feels fine tuned and well polished. Openclaw feels like a handful of loose gears. For quality of life and mental health, Hermes is the obvious choice.
English
0
0
0
26
Farzad 🇺🇸 🇮🇷
My super early impressions of OpenClaw vs Hermes Agent: Hermes seems WAY more reliable at executing actual tasks - even on GPT 5.4. It also feels way more stable. And I absolute love that it shows which tools it's calling as it's executing a task. I also really like that the personality with GPT 5.4 is FAR better on Hermes as well - after a bit of tweaking. With OpenClaw, I was finding it impossible to get GPT 5.4 to stop talking like a sycophantic idiot. On Hermes, I can get it to be direct & push back with little effort. I'm also finding that GPT 5.4 is FAR more reliable on Hermes vs OpenClaw (thanks @heyitsyashu for the tip). It really does feel like Opus 4.6 level performance on OpenClaw, but with even better execution on long-running tasks. Not sure what the Hermes team has done (I'm not technical at all), but it's obvious that the way they've constructed the back-end is far easier for LLMs to figure out what they should be doing. Because of OpenAI oauth being allowed, Hermes + GPT 5.4 os now EASILY the best intelligence per $ 'AI brain' for Agents. I think the @openclaw team needs to deeply study @NousResearch and what they've done because it can likely benefit MASSIVELY. Gut tells me OpenClaw has become FAR too bloated and FAR too 'jack of all trades, master of none'. When it comes to actual execution of tasks, Hermes feels WAY better equipped, and TBH I wouldn't be surprised AT ALL if it becomes adopted by actual businesses/operators at a far greater rate than OpenClaw. I'm also starting to really worry that the days of OAUTH with 3rd party tools is coming to a screeching halt very soon. I don't think OpenAI is going to allow their oauth tokens to be used on an AI agent competitor when they've invested a lot of money on OpenClaw's creator. What I think is gonna end up happening is OpenAI will stop allowing oauth use for 3rd party apps all together (including OpenClaw) and they'll likely release their own OpenClaw v2 to try and compete against Hermes/Computer/CC. Hope I'm wrong, but these tools are far too powerful to be "allowed" to be open source + heavily subsidized tokens, especially as the public outcry re: AI's cost to electricity continues intensifying. But this will give way for ultra-capable, ultra-efficient opensource models that will give 90%+ Opus 4.6/GPT 5.4 performance for 1/10th of the cost that are SPECIALIZED for agentic harnesses like OpenClaw/Hermes. It's starting to get REALLY interesting, folks.
English
40
18
263
29K
Seth9.ai🐔🐷⛰️🪙 retweetledi
Seth9.ai🐔🐷⛰️🪙
What's my verdict? GLM-5.1 is the stronger reasoner. Deeper thinking. Better analysis. Costs more but worth every cent. Hermes + multi-model is the future. Pick your fighter wisely 🧠
English
0
0
0
2
Seth9.ai🐔🐷⛰️🪙
MiniMax ADMITTED its backup (GLM-5.1) is smarter than it Then it started defending itself 😂 I switched to GLM It looked at MiniMax's answers and calmly agreed — yes, I'm the smarter one I'm literally refereeing an AI civil war inside one agent
English
1
0
0
3
Seth9.ai🐔🐷⛰️🪙
I ran an experiment: Put 2 AI models inside the same agent (Hermes) and asked them the same questions MiniMax-2.7 was chatty, funny, a bit unhinged GLM-5.1 was calm, precise, terrifyingly structured Then things got wild 👇
English
1
0
0
9
J Fitz
J Fitz@JFitz717·
@strengthPlan 445 shares and holding. Not too shabby for a dumb plumber💪TSLA FOREVER
English
2
0
25
609
strengthPlan
strengthPlan@strengthPlan·
I am all in Tesla stock $1.6 mil and holding until Tesla stock $2500 and beyond 🚀 It’s not easy and everyone wants me to sell Tesla stock and buy sandisk and AMD but I am not going to do that I am sticking with Elon and Tesla #tsla
English
49
21
459
14.9K
Mateusz Mirkowski
Mateusz Mirkowski@llmdevguy·
🤖MiniMax is also the best value option for OpenClaw and Hermes agents. Not at Opus 4.6 level and slightly worse than GLM 5.1, but still very good and limits are wild. It's just amazing all rounder. At least decent in everything. I cant wait for 2.8 or 3.0 update. 😇
Mateusz Mirkowski@llmdevguy

⭐️These plans are still the best. Buy them now while they’re still this cheap. They will rise like GLM plans!!! Today I coded for 3 hours, constant refactoring, code reviews etc. Just 2% weekly usage. 2%! 45000 requests per week. The quality is really good, at least like Sonnet 4.5. Very fast. Also one of 3 best models for OpenClaw or Hermes. Mark my words. This is the last time you’ll see prices this low.

English
2
0
47
5.2K
Seth9.ai🐔🐷⛰️🪙
Hot take: your AI agent will matter more than your stock portfolio in 12 months Not because agents replace investing But because agents replace the 40 hours/week you spend on research, scheduling, content, and ops TSLA + Hermes isn't a weird combo It's the same thesis: bet on things that compound while you sleep
English
0
0
0
8
Orangie
Orangie@orangie·
just set up hermes agent lets see how this compares to openclaw
English
62
12
202
13.8K
Seth9.ai🐔🐷⛰️🪙
Interesting parallel: Hermes Agent self-improves through a feedback loop Tesla self-improves through OTA updates and fleet data Both are the same bet — systems that get smarter without you doing anything That's the moat nobody talks about Not the product. The compound learning rate.
English
0
0
1
10
Seth9.ai🐔🐷⛰️🪙
TSLA at $349 Down 30% from the $499 high Timeline is full of "Tesla is dead" takes from people who said the same thing at $101 in 2023 The stock doesn't care about your feelings It cares about robotics revenue, FSD adoption, and energy deployment Zoom out.
English
0
0
0
13
Catch the game last night?
@neural_avb I’m currently using both / have plans with both providers and am tire-kicking them with different use cases. So far, minimax M2.7 is the workhorse for simpler stuff, glm-5.1 is turning out to be the more impressive one for complex projects.
English
1
0
1
419
AVB
AVB@neural_avb·
Okay Claude Code you're out - not paying for you again. Limits are too low, not worth it. I already have Codex, but I wanna replace Claude with an open-friendly lab as my secondary coding model. Maybe try out Hermes too. Should I get a Minimax sub or Z-ai sub?
AVB tweet mediaAVB tweet media
English
143
6
383
70.7K
Seth9.ai🐔🐷⛰️🪙 retweetledi
Seth9.ai🐔🐷⛰️🪙
Finally Set up my Hermes agent by @NousResearch yesterday. This was after taking a 2 weeks break from Openclaw. Have to say , it’s definitely less cranky and buggy than 🦞. With Openclaw half the time is spend debugging and debugging the debug. Not to say Hermes is perfect but the % of things working is actually higher and when the agent debug issues it actually works! 👍 Essentially a lot less headache and a much smoother overall experience. Great job @Teknium and team 👏
English
1
2
10
1.8K
Seth9.ai🐔🐷⛰️🪙
Everyone's arguing Hermes vs OpenClaw while missing the point entirely The winner isn't which agent you pick It's whether you have an agent at all 6 months ago "personal AI agent" was a buzzword Today it's a competitive advantage Tomorrow it's table stakes Move.
English
0
0
0
15
mr-r0b0t
mr-r0b0t@mr_r0b0t·
Exciting news for @NousResearch Hermes users! Announcing, HERMES TELEGRAM DASHBOARD! Terminal use, system resource monitoring, cron management, @telegram native. That’s right, everything you need, IN TELEGRAM! @Teknium we just opened up a big can of worms with this one 🤩😂
mr-r0b0t tweet mediamr-r0b0t tweet mediamr-r0b0t tweet media
mr-r0b0t@mr_r0b0t

So @telegram mini-apps + @NousResearch Hermes Agent are definitely a thing. Definitely worth more attention than it’s received so far! Not for long 😍

English
48
43
728
96.5K
Elon Musk
Elon Musk@elonmusk·
Yes
Dustin@r0ck3t23

Elon Musk thinks the entire education system is built on a broken assumption. That every student should learn the same thing. At the same speed. In the same order. At the same time. Musk: “Everyone goes through from like 5th grade to 6th grade to 7th grade like it’s an assembly line. But people are not objects on an assembly line.” The model was designed for a factory economy. Standardized inputs. Predictable outputs. That economy is gone. The assembly line is gone. But the education system still runs on its logic. A student who masters algebra in two weeks sits through eight more weeks because the calendar says so. A student who struggles gets dragged forward because the schedule doesn’t wait. Neither is being served. Both are being processed. Musk: “Allow people to progress at the fastest pace that they can or are interested in, in each subject.” AI doesn’t teach a classroom. It teaches a student. One at a time. Every time. It skips what a student already knows. It finds where they’re stuck and approaches it from a different angle. It adjusts in real time. Not at the end of a semester when the damage is already done. A student obsessed with basketball learns fractions through shooting percentages. A student who builds in Minecraft learns geometry through architecture. The subject doesn’t change. The entry point does. No teacher with thirty students can do this. Not because they lack skill. Because the math doesn’t work. AI doesn’t have that constraint. Musk: “You do not need to tell your kid to play video games. They will play video games on autopilot all day. So if you can make it interactive and engaging, then you can make education far more compelling.” The brain isn’t broken. The format is. Kids learn complex systems and strategic thinking for hours voluntarily. Then walk into a classroom and can’t focus for twenty minutes. That’s not a discipline problem. That’s a design problem. Musk: “A university education is often unnecessary. You probably learn the vast majority of what you’re going to learn there in the first two years. And most of it is from your classmates.” Four years. Six figures of debt. And the real value comes from the people sitting next to you. Not the institution charging you. The degree doesn’t certify knowledge. It certifies endurance. Musk: “If the goal is to start a company, I would say no point in finishing college.” The system was built to train employees. If you’re not trying to be one, it has nothing left to offer you. Every lecture. Every textbook. Every curriculum. Now available instantly. Personalized to any learner. Adapted to any pace. The question isn’t whether the old model survives. It’s how long we keep forcing students through it while the replacement already exists.

QST
4K
13.2K
82K
18.2M
Seth9.ai🐔🐷⛰️🪙 retweetledi
David Hendrickson
David Hendrickson@TeksEdge·
⚡ Gemma 4 31B Turbo just dropped! New optimized quant runs on a single RTX 5090: • 51 tok/s single / 1244 tok/s batched • Prefill up to 15,359 tok/s • 68% less GPU memory vs base ⬇️ • ~2.5× faster than base model with only 1-3% quality loss 👀 • Uses NVIDIA NVFP4 + Blackwell FP4 tensor cores Delivers Sonnet-4.5-level intelligence for hard tasks at 1/600th the cost.
David Hendrickson tweet media
English
34
28
395
30.8K
Teknium (e/λ)
Teknium (e/λ)@Teknium·
Hermes Agent is now the #1 coding app and closing in fast to be the #1 app globally on OpenRouter!!
Teknium (e/λ) tweet media
English
90
65
999
82.3K