JH Trader

@aw_trades_ Happy Easter friend!

Hope everyone has a good Easter✝️🤍 You’re all blessed in many ways, take today to appreciate those blessings and spend time with family🫶

@sudoingX Amazing! Can’t wait to see! I’m stuck with my 2070 super and can’t afford to upgrade right now but love to learn and watch and read from you and other similar accounts.

nvidia shipped me hardware from santa clara before we even had our first call scheduled. i haven't said a word about this until now. when a company moves this fast on a relationship you understand why they dominate. no forms. no committees. just shipped. more on this soon.

@dotta Hope windows will come soon :-)

Aron built a Desktop version of Paperclip 🖥️ 📎

@MatthewBerman CC tried to access it & got errors. It wanted me to tell you. Spent 10 mins trying to read site w/ browser tools. Got Google Analytics code every time. the page was client-side JS. Nothing exists in HTML until browser executes it. Eventually hit raw API. Should've started there.

I built something... journeykits.ai Journey helps agents discover and install full workflows easily. Please leave your feedback below!

@Teknium Love it! Makes sense 😎🙏🏻 and it works so smooth! I’ve been using Claude code to help fix bugs with Hermes and code but now I can just have Hermes do it. You are the man!!!!!

@JoshExile82 Because its no different then if you, the user, was using claude code

Did you know you can get your claude through hermes without any fancy tricks? Just type /claude-code In a new session. Hermes Agent can pilot a claude code session for you like it’s nothing. Give it a try It also doesn’t break all the self improvement loop and features of your hermes agent like openclaw’s approach does

@TheAhmadOsman As someone new to running locally and doesn’t have 4k to spend on something crazy what would be considered the best choice for someone new to get into that can run a solid model locally? Right now I still have a 2070 super? Budget is $1500 to $2k

- Gemma 4 26B-A4B > Qwen 3.5 35B-A3B - Qwen 3.5 27B > Gemma 4 31B

@Teknium Bro!!!!!!! 😎 If you’re ever in Georgia. Dinner on me. Keep crushing it!

It just works what can i say 🫣

@Teknium @JoelDeTeves Do you ever sleep! 😴 I love it! Even fixed some bugs I had. and that Claude code thing Hermes does is BOSS!

Your Hermes Agent can now create or run a script every time it runs that will provide additional context to your cronjobs! `hermes update` to use early!

@Teknium Just tried it and it works. But how is that allowed? What makes this method safe compared to using oauth directly? I just tired it and it worked so easy! So easy! No update needed. But will it cause a ban. Would love your thoughts on this as you always explain things great

@JoshExile82 Nope it already has the skill. The update would make it more comprehensive tho!

@wickedguro So I’m curious about your agents creating videos? Does the agent just create videos or does it use that service you mentioned? And how did you get a clawdhub thing to work with a Claude agent

When you realize that PaperClip can run your entire marketing: Social Posting, SEO, and Retention.

@123skely Doesn’t work for me

PSA: If you still want to use Opus 4.6 with your openClaw/Clawbot, just give your agent this "models auth login --provider anthropic --method cli --set-default" This switches OpenClaw to use Claude CLI as the backend instead of the OAuth token directly. Since Claude CLI is Anthropic's first-party tool, it's still allowed under the subscription. Then you just go to your mac mini, and log in, and then you should be good.

@jxnlco Yesss! I can’t afford $200. But if you create a $100 plan I will sign up right now @OpenAI @sama @gdb

Hey boss can we redirect our sora compute to openclaw?

@Alibaba_Qwen @OpenRouter So I was using since day 1 on openrouter but it wasn’t coding very well. I had it doing simple tasks. It would tell me it was doing stuff but when I checked. Nothing. Also, kept not following instructions. It wouldn’t verify before giving me an answer. It also forgot tools

Qwen3.6-Plus ranks # 1 on @OpenRouter , and the first model on OpenRouter to break 1 Trillion tokens processed in a single day！!🥇🔥 We are thrilled to see Qwen3.6-Plus topping the charts so quickly. This milestone wouldn't be possible without our amazing developers. ❤️Thank you！！

@Teknium And I think I remember you saying best way to update is through the terminal?

@Teknium Do we have to download a new update for it? If not, I’ll be trying that when I get home lol 😂

@coffee @cathrynlavery Oh. Well damn lol 😂

for those running openclaw locally (like on a mac mini 😘)

@NA8STRADAMUS @steipete @NoahEpstein_ Makes perfect sense the way you explained it. Thank you. 🙏🏻

@JoshExile82 @steipete @NoahEpstein_ Yeah so it would be your OC agent using the Claude CLI instead of you using it. At least that's how I understand it.

openclaw without opus is actually one of the saddest things that's happened this year (ignore the war) i can't lie. i've been loving openclaw way too much to just take this on the chin and move on my actual plan is to try figure out how to get openclaw talking to claude code infrastructure instead (because i can't lie claude code is still actually unbelievable and i'm not giving that up either) might work. might be completely stupid. we'll see but i'm curious what people are doing right now because there are a few options and none of them are clean going local is the move long term but the thing is - you've ordered your mac studio, great, it's not arriving for another week or two. so what do you actually do in the gap? i've seen @AlexFinn preaching about local AI basically every single day and i respect it but i can also just tell that his openclaw is writing half his posts at this point so i dunno how much i trust the sauce what's everyone's actual plan? switching models? building workarounds? just eating the API cost? because i'm not ready to let this go and i refuse to believe i'm the only one

@keithtyser @Scobleizer @openclaw Same for me! OpenClaw has a bug where gpt 5.4 leaks its internal dialogue & tool calls even if reasoning is off. It works a lot better with Hermes. small issue I’ve noticed w/ gpt 5.4 with Hermes if you reply twice or too quick it won’t see a message. Has to do with streaming

gpt-5.4 was basically unusable for me in @openclaw. it would explain what needs to be done, I’d say “ok do it,” and then… nothing. no action, no feedback, sometimes it would just go silent or say it’s “working” with zero visibility. felt like babysitting an intern that never actually touched the keyboard switched to @NousResearch Hermes agent and it’s night and day. same model, but now it actually executes. on par with opus-4.6 for me no idea why the gap is that big but yeah, huge relief after losing Claude OAuth in openclaw

@NA8STRADAMUS @steipete @NoahEpstein_ So OpenClaw basically just “talks” to the Claude Code CLI on the PC. And Claude is using your OAUTH. So sorta of a workaround it sounds like. Slick

@NA8STRADAMUS @steipete @NoahEpstein_ Hey Nate! Thank you. So it’s similar to what I’ve been doing. I’ve been using Claude Code CLI, using my OAUTH on my PC where OpenClaw is installed and been having it help with bugs for OpenClaw, fix it and stuff. So it’s basically the same thing it sounds like, just reversed.