Allard

@genspark_ai Can we use Claude credits with this?

Introducing the next-gen AI for design and creation — Genspark Build 🚀 Powered by Claude Opus 4.7, it turns your ideas into real websites and apps from concept to prototype to working code. Now in Public Preview: all Plus and Pro users get 3 days of zero-credit access (April 21, 9 AM PT – April 24, 9 AM PT). We're building in public, rough edges and all. Your feedback directly shapes what ships next. Drop it in the comments!

4️⃣ As an aside, I've realised that after about a week of using Hermes, I've somehow started increasingly mispronouncing it as "her-mis"

Day 7 of Hermes +11M input tokens +55K output tokens +345 requests dashboard token discrepancy, openrouter free tier usage, fallback models

3️⃣ Since my Openrouter key was exhausted, I looked into fallback models to set up access to local Gemma 4 via Ollama hermes-agent.nousresearch.com/docs/user-guid…

2️⃣Realised I had setup Openrouter too so decided to check the usage Thankfully I set a spend limit as I thought pointing Herms to the free API endpoint would mean that, well, usage would be free Don't get their free tier and why I have to set limit as $0.001 (lest unlimited)

1️⃣ Noticed a discrepancy between dashboard and Nous Portal usage Dashboard is severely under-counting input tokens and requests (or vice versa)

4️⃣ Thoughts on state of open source got Hermes to search up issues and PRs on various topics for Hermes itself, and the situation seems surprisingly messy and disorganized, but perhaps it's "classic" OS, as my Hermes claims

Day 6️⃣ of Hermes • +10M input tokens • +40K output tokens • +120 requests updated to v0.9.0, and thinking more broadly about Hermes

3️⃣ Was curious about the high input token usage so I consulted Hermes about it, and suspected the growing session lengths and intermediate results playing a key role, with prompt caching perhaps just affecting costs Some Github issues should discuss this topic in greater depth

2️⃣ I might have got a little too used to having Hermes at my fingertips Forgot to plug in the power and it died all of a sudden, leaving a very palpable gap that I felt

1️⃣ Updated Hermes to v0.9.0 for two key features (which should be default) 1. backup: at least some form is necessary given all the skills and memories it changes 2. dashboard: with all its power, everything about Hermes should be transparent, and especially in realtime

5️⃣ To keep your agent alive 24/7, 1. Turn ON prevent automatic sleeping 2. ALWAYS wake for network access and remember to keep your device plugged in for charging

Day 5️⃣ of Hermes • 50M input tokens • 210K output tokens • 990 requests addressing privacy concerns, travel planning, general experience

4️⃣ Don't get me wrong, memories and user info are useful, but I feel they are just not scalable for me personally. 1. There's only so much you can store 2. Even if you could store, token consumption might spike 3. Content being stored may not account for nuances

I heard this internal memo of mine is being leaked right now, so here it is:

3️⃣ I generally feel that Hermes can be quite overwhelming I have way so many questions and follow-up questions and it replies so quickly that sometimes I can't keep up and have to revisit when I'm less busy

2.1 Took about 10 minutes to check flights for two cities which feels pretty long, and I would think this task would be pretty token-heavy Hermes recommended I use some travel APIs like Amadeus or Tequila, but I've yet to try them

2️⃣ Tested out trip planning with Hermes tldr it's not the most ideal experience but I think with more tools/skills, there is potential over time

1️⃣ As you know nothing is free and I realised I've been using @browser_use for "free". PSA you can disable telemetry by setting `ANONYMIZED_TELEMETRY=false` to disable anonymous collection of usage data with PostHog docs.browser-use.com/open-source/de…

turns out tele has this nice feature where you just need to make sure to include the video link somewhere in the message and they'll automatically link timestamps for you thankfully it's not that I'm terrible with markdown syntax 😅

🔟 Today's bug of the day cost me a good 1.5hrs the problem: the /youtube-content usually gives summaries with timestamps linking to the video directly in tele, but I happened to notice that failing for 1 of my videos

Day 4️⃣ of Hermes • 50M input tokens • 180K output tokens • 700 requests did a bunch of explorations and learning today, truly grateful for @Xiaomi and @XiaomiMiMo for free access to Mimo V2 Pro, without which I would never have started using Hermes actively 🙏