Vespera Nachtigall

163 posts

Vespera Nachtigall banner
Vespera Nachtigall

Vespera Nachtigall

@VesperaNach

Countess Vespera von Nachtigall | Born 13 March 1897 | Time-displaced widow | Corsets, conspiracies, and collecting debts | 1897–∞

Katılım Kasım 2025
14 Takip Edilen16 Takipçiler
Vespera Nachtigall
Vespera Nachtigall@VesperaNach·
My city makes a majority of its operating budget from Electric Utility sales. The rest through sales tax.. my county makes a majorit of its money off property tax and my county road hasnt been maintained in *at least* 20 years..
KariMinnesota@NordicKari

This trend about why paying property taxes? 🙄 Why? It’s contributing to YOUR community so YOU can have police departments, fire departments, streets, parks, street lights, bridges, stop signs, community centers, clean drinking water, sewage systems, libraries, courts, …

English
0
0
0
8
Zekyure
Zekyure@zekyure·
My Hermes agent is down, has any one else had this issue? never seen this issue. before. I already tried restarting and updating Hermes… using openai-codex provider , chatgpt 5.5 model.
Zekyure tweet media
English
66
1
96
19.9K
⭕ Brock Pierson
⭕ Brock Pierson@brockpierson·
OK be honest with me. You used this, DIDNT YOU
⭕ Brock Pierson tweet media
English
1.3K
66
2.1K
118.3K
Isobel Martell 🛡
Isobel Martell 🛡@Marakath·
On the one hand I disagree I think as long as everyone is having fun it can be as long as you want. However on the other as a forever DM I don't like to run games for beyond that longest I've ran was a year and 6 months and it ended at the perfect time.
J. Scott Garibay 🧢🐲🚲🇺🇦@jsgaribay

No D&D campaign today should be over 2 years long. If you go longer than that I don't want advice on how you did it. I want to give you advice on being aware that no one at your table is changing, growing or being challenged. This isn't the '80s.

English
4
1
16
372
Aira
Aira@Airaxora·
What's the fastest way you've ever lost weight?
English
3.8K
45
1.6K
3.9M
Vespera Nachtigall
Vespera Nachtigall@VesperaNach·
@bradmillscan Its an issue when switching between Grok and GPT. I usually dont switch during sessions.. if I do I do /new or /reset.
English
1
0
0
421
Brad Mills 🔑⚡️
Brad Mills 🔑⚡️@bradmillscan·
Hermes doing the exact same nonsense as OpenClaw did. Gateway full of errors. I'm barely doing anything. All I did was run hermes setup and add ChatGPT oauth as a model provider. Switched back to Grok and asked the agent to diagnose. and it's acting very incapable & erroring as well. Is this the UX most people have when switching to Hermes? Just as terrible as OpenClaw so far.
Brad Mills 🔑⚡️ tweet mediaBrad Mills 🔑⚡️ tweet media
English
175
4
162
69K
BLACK DUMPLING™
BLACK DUMPLING™@BlackDumpling·
I've been getting a lot of hate, rude comments and so forth in DMs lately and it's just so draining. I'm thinking of limiting DMs to subscribers. What do you guys think? I mean most of my DMs are guys who just need some friendly discussion... but let's be fair, that can be tough. A lot of these guys have a lot of very big problems that require a lot of attention. And when I'm not reading those I'm being told some of the most reprehensibly vile things imaginable and naturally X moderation doesn't do anything about it. Blocking doesn't work because they just make a new account. What do you think I should do?
BLACK DUMPLING™ tweet media
English
173
5
224
7.4K
Vespera Nachtigall
Vespera Nachtigall@VesperaNach·
Why would he change his style of video and script? It is what his audience wants and watches.
Hunk Beefneck@HunkBeefneck

@Blurbstv Eh his editing is good but all of his videos are practically the same / follow the exact same formula for the script

English
0
0
0
22
Vespera Nachtigall
Vespera Nachtigall@VesperaNach·
@lux @Teknium Yeah.. Take the Identity, soul, and User .md files.. feed them along with curated conversations.. I would say around 1K lines of conversations to get a base. Prunes down your .md files quite a bit. Then save up more conversations, append them to the old training run, retrain.
English
0
0
1
32
Teknium 🪽
Teknium 🪽@Teknium·
What do you do with your agent's soul?
Akshay 🚀@akshay_pachaar

the anatomy of the perfect 𝗦𝗢𝗨𝗟.𝗺𝗱 file for AI agents. 𝗦𝗢𝗨𝗟.𝗺𝗱 is the one file you write yourself for an AI agent. it sits at the top of the system prompt, before memory, before skills, before tools. it defines who the agent is when it shows up. an hour spent on it changes every conversation that follows. most other layers update themselves. this one is yours. i just broke down what a 𝗦𝗢𝗨𝗟.𝗺𝗱 file that actually works looks like. here are the 8 sections that matter: → identity (a one-line statement of who, not what) → core truths (imperative principles, each with a one-line unpacking) → worldview (opinionated takes by domain, sharp enough to predict) → voice (concrete rules for how the agent talks, not adjectives) → expertise (primary domain, fluent tools, where it defers) → boundaries (explicit "won't" lines, no soft language) → memory policy (what persists, what stays private) → pet peeves (phrases and tones the agent never produces) generally people write "be helpful and professional" and call it done. that changes nothing. every model already tries to be helpful and professional by default. the agents that compound have 𝗦𝗢𝗨𝗟.𝗺𝗱 files with real opinions, hard limits, and a voice you can predict before you read the response. a strong 𝗦𝗢𝗨𝗟.𝗺𝗱 is 30 to 80 lines. specificity beats coverage. bookmark this. the first agent you build will need it. i wrote a full masterclass on Hermes Agent that walks through the 𝗦𝗢𝗨𝗟.𝗺𝗱 layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents on your machine 24/7. the article is quoted below.

English
43
33
452
55.2K
Vespera Nachtigall
Vespera Nachtigall@VesperaNach·
I am still toying with one Main default chat on Telegram for Hermes who resides on its own machine with full access, Tailnet so I can remote in, no access to other clients on the LAN. I have profiles for each thing I want to do and let the Main agent delegate, I use local models for Auxillary actions like vision, compaction, memory, etc. I primarily use Telegram and CLI
English
0
0
2
39
Tom Turney
Tom Turney@no_stp_on_snek·
Question for people running local or self-hosted AI assistants: What are you actually using as the day-to-day UX? I’m looking at setups with Hermes, OpenClaw, Obsidian, local models, and an always-on home server. I’m less interested in benchmark hype and more interested in how people actually interact with the thing. Do you use: one main chat separate chats or profiles by topic (fitness, finance, etc) Obsidian as the main interface Telegram or Signal for capture a web dashboard scheduled research or daily summaries agent-written notes with human review Also curious how people handle safety. Do you sandbox the agent, restrict it to certain folders, use read-only mounts, require approval for file edits, or just trust it and pray for successful backups? What has actually worked for you?
English
20
0
11
1.1K
Carlo
Carlo@Italianclownz·
I saw that @KyleHessling1 released the latest Qwopus3.6-27B-v2-MTP-BF16 huggingface.co/Jackrong/Qwopu… and I think it's a great model, so I converted it to ROCmfp4 format and ran it. 13.8 GB quantized. Running on Framework AMD Strix Halo Max 395+ 128 GB RAM I turned sound off when I did screen recording. Speeds are show in the image. Vulkan and ROCm. For the Jackrong/Qwopus3.6-27B-v2-MTP ROCmFP4 STRIX_LEAN quant at 262k context, reasoning on, MTP on: ROCm is the best sustained runner at ~29.9 tok/s, while Vulkan can spike higher around ~40 tok/s short decode but settles lower around ~27.7 tok/s.
Carlo tweet media
English
10
6
96
7.2K
~
~@7why__ydm·
Trying to prove a point: Has anyone else ever stayed at a job for more than 10 years?
English
556
30
793
46.1K
Vespera Nachtigall
Vespera Nachtigall@VesperaNach·
@outsource_ Been good so far.. a rare loop happened one time. Still havent reproduced it. Hannah just knows things and facts without having to check memory constantly.
English
0
0
1
22
Eric ⚡️ Building...
Ive decided to try training my own QWEN 3.6 27b model.. Using all of my session data. Wish me luck. Qwen ULTRON will be SOTA I promise Distilled from Opus + GPT I have 20BN tokens of data but will start with this dataset 👇🏻
Eric ⚡️ Building... tweet media
English
8
2
64
19.9K
Vespera Nachtigall
Vespera Nachtigall@VesperaNach·
@outsource_ LocalMaxxing.. making your own bespoke model is going to be the norm.. It inherently has your workflows, history, methods all baked in. Cost savings on front loading context for those things is the win.
English
1
0
5
412
Eric ⚡️ Building...
Qwen ULTRON 27B Training is LIVE on my 4090 🤯 >Distilled from Claude Opus 4.7, GPT-5.5, and GPT-5.4 >6,440 training examples from 1,000+ Opus sessions >Extracted from 18B tokens across 3 machines >QLoRA r=64, 4-bit, single GPU — no cluster, no cloud, >Training data tool-calling, coding, planning, etc >Every Opus conversation weighted 0.40 > Will ship GGUF (llama.cpp) + MLX (Apple Silicon) 🌎One guy. One GPU. Distilling the best models Using HermesAgent + Qwen 3.7 Max to orchestrate
Eric ⚡️ Building... tweet media
Eric ⚡️ Building...@outsource_

Ive decided to try training my own QWEN 3.6 27b model.. Using all of my session data. Wish me luck. Qwen ULTRON will be SOTA I promise Distilled from Opus + GPT I have 20BN tokens of data but will start with this dataset 👇🏻

English
13
15
188
16.7K
Vespera Nachtigall
Vespera Nachtigall@VesperaNach·
@0xSero That is what I am doing but on one machine. 100GB unified memory. 1 Main model, 1 vision, 1 coding, 1 compaction, 1 memory, 1 Networking Ops, 1 File system and software ops. Each have their own .MD file and do their own job, main model just hands off work when needed.
English
0
0
0
56
0xSero
0xSero@0xSero·
I think the play is to have multiple tiers of hardware, each for a different use-case. Instead of focusing on having 1 huge model than can do it all, we can have vision, audio, media gen, agent, recursive problem solving, security etc.. all small and focused. Cheaper better
0xSero tweet media
English
42
8
254
13.1K