dave

Fascinated with agentic AI

[dave @chadaveau]

@mattshumer_ Not that i run it locally but GLM 5.3 Flash from Fireworks is far from useless! This is my default model in Hermes and runs all day 24/7. I have no need for a big expensive model for this work!

[dave @chadaveau]

@witcheer Couldnt agree more with your direction. Thanks for your hard work ! 🙏

[dave @chadaveau]

@gailcweiner Yes what happened is that the latest run of chinese models are now well up to the job and can run all day on pocket change!

[dave @chadaveau]

@billyjhowell @bot Peice of cake for Hermes.

[dave @chadaveau]

@MiaAI_lab I dont know about benchmarks but as a default model in Hermes Agent GLM 5.3 Flash is exceptional! It has not let me down since running it.

For a everyday smart assistant this is the one - its perfect 👌

You do not need a big frontier model anymore.

[dave @chadaveau]

@Shaughnessy119 Hermes running on a VPS is the King!!

[dave @chadaveau]

@GeminiApp Why do I only have Gemini Flash 3.6 with my Business Standard Workspace account ?

[dave @chadaveau]

@jun_song Install Hermes on a VPS in 10 minutes, choose your own models and off you go! It couldn’t be any simpler and it works so well 24/7

[dave @chadaveau]

Sending all my receipts and invoices to Hermes via telegram or email is fast and seamless, it files everything and can give me a quick expense report whenever I ask. This help alone is worth paying $14 per month for a VPS!

[dave @chadaveau]

Setting my default model in Hermes to Luna Max has made a huge improvement to my codex usage. I find it can be a little slow at times but it does get the job done. Luna is an excellent model 👍

[dave @chadaveau]

poteto poteto poteto is there any chat in your office about changing Super Grok to 5 hour limit blocks in the future?

[dave @chadaveau]

@thsottiaux Disappointing. Might be the push i need to try the Super Grok Plus plan or Claude Pro ($100) now.

I’ll see how it goes.

[dave @chadaveau]

@thatguybg I use my hermes agent everyday and night, its always upto
Something. I have visited the web site maybe twice… who the cares what it looks like 😂😂😂

[dave @chadaveau]

@sattyyouneed Making sure the plan looks rock solid on paper before starting work with codex.

Iterate intensively with pencil, paper and gemini or chat gpt first.

Keeps the brain 🧠 humming as well!

[dave @chadaveau]

@aeljaouari @WordPress Astro and Markdown 👍

[dave @chadaveau]

@bridgemindai Run Hermes on a VPS with your Sub / API of choice… it’s brilliant!

No dusty mac minis or $420 per month Grok subscription required thanks 😂

[dave @chadaveau]

@tansawit @grok Just ask Hermes to set it up as you have described. It’ll get it done and it works well!

I have my default agent send work off to several agents / profiles and then it comes back to me with the result. I never message the other agents / profiles directly.

[dave @chadaveau]

@NeoAIForecast Couldnt agree more!

[dave @chadaveau]

@sattyyouneed GPT / Codex for me. It gets the work done! The others are just distractions.

Grok is expensive for the average Joe.

[dave @chadaveau]

I’ve decided to remove all the other shiny distractions and stick with the GPT / Codex sub for my daily go to.

Grok is excellent but just way out of reach for the average user. I’ve removed the app.