N.KOJIRA.IO
Timeline

ngmi

[email protected]
npub14p7fhlz9wrlptt7a5mqqjkk79460k98r999l7dafv4fznqaa565qhjdzry
hi~
#monero? Never heard of her

nevent1qgsv0l5jlqx…
nice!
Read ~/.config/herdr-app/AGENTS.md, then add this mod: https://github.com/mathieucroset/herdr-pokemon-agents/tre…
AI Detection can now check images and video as well as text. Drop in a file or paste a direct link to one. Image 1.0 results include a heatmap, and video results include a timeline and frames. Images cost $0.3125 with Image 1.0 or $0.0625 with Image Flash 1.0, and video costs $0.0625 per second.

https://nano-gpt.com/subscription/kUGJhgF9
mullvad has entry and exist nodes you can choose from
no not over tor even, just mullvad - need to avoid to geoblocking. it's ass
yeah i need to use us exit nodes and they are extremely volatile. cant download or upload shit there, switching a lot
does anyone have an #instinct invite to share?
"In its November 3 incident report, Binance said a fake job interview ended with an engineer downloading a coding assignment that hid malware on his work computer. The attackers used that infected machine and an internal AI tool on October 20 to gain control of two other engineers' systems."

They're definitely not hiring the smartest candles on the cake

#binance
audio decision making etc is being hyped now everywhere, but I have a feeling it's the same like metaverse. only the companies pushing this narrative thinks it's cool. I personally have maybe used audio (talk with ai) 2-3 times in the last 3 years. it's not effective and slow
and also image attachements stay and need to be removed extra on top. just posted with an olda attachment
npub1fa05cayzx9xze… one thing, a posted note stays in the composer, so i need to delete the old text everytime i want to post new
https://metaend.blossom.band/33ca6cbdd5d0008681510f8357c3…
love the new npub1fa05cayzx9xze… web layout, even on my small thinkpad screen it's organized. it's the right direction IMO
LongStories is now on NanoGPT. Give it one idea and it writes the story, casts the characters, animates the shots, adds narration, dialogue and sound, and edits a finished short film.

Choose 30 or 60 seconds at 480p or 720p, from $3.96 for 30 seconds at 480p. Most videos take about half an hour.

LongStories doesn't make adult content, so those prompts are refused, and a refused prompt costs nothing.

https://nano-gpt.com/subscription/kUGJhgF9

https://blossom.ditto.pub/d5b1f32555e4bc814e6db0cf775bcbf…
yes, love it!
Running several AI agents? The pattern that actually works, from a 28-minute Grokbot tutorial I transcribed today:

1. Few strong agents beat a big team. Each one keeps its own memory, so every extra agent is more repeating yourself.
2. One job per agent, plus a short list of things it must never do. A bot that does everything does nothing well.
3. One shared brain. The rules, the facts, and the design every agent must follow live in one folder they all read.
4. Align before the big job. Numbered questions, each with a recommendation, answered before the agent starts. It saves more usage than any prompt trick.
5. Quiet routines. A check that only pings you when something needs you beats ten chatty ones.
6. Turn repeated routines into plain code. Deterministic beats clever, and it costs nothing to run.
7. One morning list of everything waiting on you, most important first. That is the whole chief-of-staff job.
8. A weekly report card: one agent scores the others and says what to fix.

Source: Jay E / RoboNuggets, "The ONLY Grok Bot Tutorial You'll Ever Need" - https://www.youtube.com/watch?v=nIgKOAe3dxs

The same setup runs on Muse. It is free, and you get in over a US VPN. My invite code gets you 1B extra tokens: 8WQ4S7 (Settings > Redeem token, within 48 hours of joining).

#AI #agents #Muse #Grokbot #automation
https://metaend.blossom.band/6c444a6913db801547336dd8cbd8…
Cool 👍

ElevenLabs Sound Effects V3 creates sound effects from text prompts up to 450 characters. Choose 0.5–30 seconds or automatic duration, adjust prompt influence, and enable seamless looping. Download MP3 or Opus audio. Pricing is $0.002 per billed second. Quotes reserve the rounded requested duration plus one second, or up to $0.062 for automatic duration. Final billing uses rounded requested or output seconds, including codec padding where applicable; unused allowance is refunded after generation.

https://nano-gpt.com/subscription/kUGJhgF9
TIL: you can customize your muse avatar AND it can animate it for working animations. this is so cool

set VPN to US and use my code for 1b tokens on top for free

Code: 8WQ4S7
https://muse.ai/join

https://metaend.blossom.band/6c444a6913db801547336dd8cbd8…

#muse #aiagent
but is this in person? looks like?
We're doing free and open security research with our harness

If you want to support, get a cheap $12 subscription at nanogpt via our referral (discounts apply if you pay with BTC or Monero!)

https://nano-gpt.com/subscription/HCdbQetV

https://metaend.blossom.band/305b6fae9d2cf1782cc3241103f9…

#bitcoin #monero
not surprising to me, nostr is full of early adopters
nevent1qvzqqqqqqyp…
pointing abliteration flash and deepseek on the repo now. its still at the 21 version, but i guess thats okay
GLM 5.3 FlashX Legal is trained for legal document analysis, contract review, legal reasoning and initial drafts. It accepts text and images and returns text, with always-on reasoning, tool calling and JSON output. It has a 1M-token context window and supports up to 131,072 output tokens. External legal databases and document-editing tools require your own integrations.

https://nano-gpt.com/subscription/kUGJhgF9