Geoff Wellman

Why is this news? Software installs software packages. 😱 @DecryptMedia decrypt.co/367060/chrome-…

@gmi_cloud I'm curious, how many tokens did Hermes use 2nd time round?

asked Hermes Agent and OpenClaw to scrape our site and send a report. using DeepSeek V4 from our API. OpenClaw: 15k token, 2min 48 sec. wrote a bash script. Hermes: 36 token, 8 min 06 sec. wrote a SKILL.md. runs itself next time.

@MichLieben Ads

I'm giving away the Claude Code skills we use to manage $300k/mo in ad spend at ColdIQ. 4X ROAS on $1M+ spent. Ivan, our head of growth, built them off 300+ hours running ad campaigns for our clients. They run Google, Meta, and LinkedIn ads from the terminal in plain English: → bulk edits across platforms → custom audiences from CRM lists → creative fatigue detection before CTR dips → bid adjustments at scale → performance audits across periods Reply "ads" and I'll send the full repo. Must be following.

@MichaelGannotti @NousResearch @Teknium You can also do 'hermes -c' to jump back into your last tui session.

@GeoffWellman @NousResearch @Teknium I do the obsidian and hunch but I mean the whole conversation in tui is lost. In my OpenClaw it isn’t. Hopefully updates will fix it

The TUI is the first thing that attracted me to Hermes over OpenClaw, so much faster to work with than Telegram or the web. Can't wait for v2! @NousResearch @Teknium - Trying it now!

@ANT_1515 @NousResearch @Teknium Yea, I've been experiencing that recently too. Seems to give up in the middle of more challenging tasks.

@GeoffWellman @NousResearch @Teknium I’m having constant gateway issues with telegram

@MichaelGannotti @NousResearch @Teknium They are different sessions, you could connect up a more advanced memory provider which will help share context. I'm testing out Honcho at the moment. I also write a lot of my work to Obsidian vaults and then reference my working files to bring a different session up to speed.

@GeoffWellman @NousResearch @Teknium You like the Tui in Hermes over OpenClaw? I have both OpenClaw and Hermes but the Tui in Hermes loses context going from desktop to remote mobile, from tab to tab. And copy and paste make me batty. Hoping the experience improves in it it soon

@austinbv @luksamuk @Teknium Value per token is definitely higher with GLM.

@luksamuk @Teknium I liked GLM but i noticed its "task" work was a bit worse than opus

How are people using smart model routing on Hermes? It seems to lobotomize itself when it's not using opus. @Teknium ??

Good decision. Hermes feels like the grown-up option next to OpenClaw.

Hermes writes what it learns to markdown — readable, editable, persistent. Pay the learning cost once. Invest the savings in getting smarter. @nousresearch 2/2

The most expensive thing an agent can do is forget. Re-reading, re-learning, re-sending context you already have. OpenClaw's context bloat is a tax on amnesia. 1/2

TL;DR: Opus 4.7 = same price, more tokens. Watch usage, mind session limits, find your new normal. The most expensive model is the one you don't understand. 5/5 #Opus4.7 #ClaudeCode #Anthropic

But xhigh can also save tokens by getting it right first time. "The price of anything is the amount of life you exchange for it." — Thoreau. In AI, you're exchanging tokens. Manage trade-offs. 4/5

Opus 4.7 is out. Same per-token price as Opus 4.6. New xhigh effort level, now the default. Sounds like a win-win, right? 🧵 1/5

@Teknium @bilion1983 @ollama I've had a good experience with Ollama. Generally using cloud models but also have used local Gemma4 models. Would be great to see native Ollama cloud support though. Might work on a PR later.

@bilion1983 See @ollama configuration is impossible here please help out lol Never get these kinds of issues with vllm/sglang/llama-server/lmstudio :l

Hermes 的 chat 命令又超时了（之前也遇到过这个问题）。 结论：Hermes 的配置有问题，无法正常使用 Ollama 模型。 当前状态： • ✅ Ollama 本地有 10 个模型 • ✅ Hermes 配置指向 Ollama（http://localhost:11434） • ❌ Hermes 无法正常调用模型（超时/路由错误） 建议： 1. 暂时放弃 Hermes（配置问题太多，之前也没搞定） 2. 直接用 Ollama CLI：ollama run hermes3:8b "你的问题" 3. 或者用 OpenClaw + Ollama（我可以调用本地模型） 要不要我帮你配置 OpenClaw 使用 Ollama 本地模型作为备用？

Every time!

bro was right. Atlassian down 75%. HubSpot down 69%. Figma down 86%. Almost all of them down 30–70% from their 52-week highs. AI is literally eating software alive and repricing every company in real time. SaaS is cooked fr 😭