₳lien.Ant

Student📚| CYB👨🏾‍💻| ADA💙 #Cardano $ADA $CHAD

[Nous Research @NousResearch]

Your team and your Hermes can now share a computer.

The new @trycua Spaces plugin gives Hermes its own Linux, macOS, or Windows Space on hardware you already own. Anyone on your team can open it, watch live, step in, and hand it back while Hermes keeps working.

https://t.co/nVs7sCmspk

[Cua @trycua]

1/ Introducing the Cua Spaces SDK.

Every big lab now ships a bot with its own computer: Grok Bot, Muse, dots. None let you bring your own. With Cua Spaces, now you can.

Put Claude Code, Codex or any agent on compute you choose, and run jobs across all your computers at once.

[Midnight @MidnightNtwrk]

we've been trying to reach you about your blockchain's privacy

[₳lien.Ant @LilAnt3000]

@IOHK_Charles Reminds me of state taxes. Pay up blindly then wondering why shit isn’t getting better. 🫪

[₳lien.Ant @LilAnt3000]

@RahulRa66547685 @IOHK_Charles

[WallStreetBets @wallstreetbets]

never really thought ab this but a private transaction can still leak info

wallet, rpc, identity, even the way you read the chain can give you away

privacy has to cover the whole stack

makes the whole thesis way bigger than i thought

[₳lien.Ant @LilAnt3000]

@elonmusk @TalulahRiley wen AGI?

[₳lien.Ant @LilAnt3000]

@IOHK_Charles plus the MidnightxMLH hackathon ✨🙌🏾

[₳lien.Ant @LilAnt3000]

@IOHK_Charles I’m playing around with ODS
https://t.co/Co98Ogiq0H

[Andrew Ng @AndrewYNg]

The most important skills in Building and Deploying AI Applications. https://t.co/IyWIKLIzeM

[el.cine @EHuanglu]

holy sht.. you can now control computers with your thoughts

someone at WAIC 2026 is playing Black Myth: Wukong using only a brain-computer interface

the system flashes visual targets at different frequencies, your brain generates unique EEG signals in response, which are detected by a headset and translated into in-game controls

staff say it only takes around 5 minutes to calibrate

we’re watching the next generation of human-computer interaction in real time

[Charles Hoskinson @IOHK_Charles]

Well fuck, I've got to find 4 TB of RAM and 8 GPUs so I can run this and Kimi K3, and GLM 5.2 in parallel for a "thing"

[rabbit inc. @rabbit_hmi]

THE COUNTDOWN BEGINS
🥕 + 🪽

[YanXbt @IBuzovskyi]

HERMES AGENT SUB-AGENTS DO THE GRUNT WORK
ON A CHEAP MODEL WHILE YOUR MAIN AGENT
ONLY SEES THE SUMMARIES.
SAME QUALITY. 5X CHEAPER.

@tonbistudio just dropped module 8 of his masterclass
covering delegation, parallelism, and cost control.
here is the full architecture.

WHY DELEGATE:

two problems with a single agent loop:

1. CONTEXT POISONING
every tool call, retry, dead end from a long task
stays in the context window.
the window fills. the model gets worse.

2. SERIAL SLOWNESS
10 research tasks one at a time = 10x the wait.

sub-agents fix both.
each child gets a clean isolated context.
runs in parallel.
only the final summary returns to the parent.

the parent never sees the mess.

HOW DELEGATE_TASK WORKS:

the agent calls delegate_task with:

→ goal: what the child must achieve
→ context: every detail it needs
(file paths, error messages, project root,
stack traces. if it's not in context, it doesn't exist.)
→ tool_sets: scoped per task

the child is a fresh agent.
own conversation. own terminal session.
own iteration budget. works alone in a clean room.
returns a structured summary: what it did, found, changed.

THE ONE RULE:

sub-agents know nothing.

BAD: goal = "fix the error"
(which error? what file? what project?)

GOOD: goal = "fix the type error in api_handlers.py
line 47. stack trace: [full trace].
project root: /home/user/app. python 3.12."

same discipline as cron prompts.
fresh session. no memory. write everything down.

BLOCKED TOOLS FOR CHILDREN (by default):

→ delegation (no recursive spawning)
→ clarify (no asking the user)
→ memory (no writing to shared memory)
→ send_message (no firing off Telegram messages)
→ code_execution (no sandbox escape)

if the subtask needs any of these, do it in the parent.

CHEAP CHILDREN, STRONG PARENT:

route every sub-agent through a cheaper model.

set in Desktop app, Dashboard, or config.yaml:

delegation:
model: "nvidia/nemotron-3"
provider: "openrouter"

one model for the whole child fleet.
children do token-heavy grunt work cheap.
parent keeps the strong model for orchestration.

THE COST PROOF:

same research task. same output quality.

without sub-agents (main model does everything):
→ 9 minutes. 66 cents. one model.

with sub-agents (cheap model for workers):
→ 9 minutes. 13 cents. 5x cheaper.

80% of token volume ran on the cheap model.
the strong model only touched the summaries.

BATCH MODE:

pass multiple tasks as an array.
they run in parallel through a thread pool.

default concurrency: 3 children at once.
results come back sorted by input index.
interrupt the parent = all children canceled.

batch bigger than the limit = error.
raise max_concurrent_children or batch smaller.

THREE-LEVEL RESEARCH TREE:

parent delegates to 3 sport orchestrators.
each orchestrator delegates to 3 research workers.
9 workers research in parallel.
3 orchestrators synthesize per sport.
parent synthesizes all three into one report.

to enable nested delegation:

delegation:
max_spawn_depth: 2
orchestrator_enabled: true

spawn sport children with role: orchestrator.
each orchestrator can delegate its own workers.

at depth 3 with concurrency 3:
3 × 3 × 3 = 27 concurrent workers.
each level multiplies the spend.
raise depth intentionally.

set child_timeout_seconds higher for nested trees.
default 600 seconds. nested trees need 1200+.

SYNC VS ASYNC:

default: synchronous.
delegate_task blocks until child finishes.
interrupt parent = children canceled.

v0.17.0 added background mode:
delegate_task(background=true)
returns a handle immediately.
child runs in the background.
result re-enters as a new turn when finished.
your session stays live.

background sub-agents are single-session.
they die when the session ends.
for work that must survive restarts: use cron.

WHEN NOT TO DELEGATE:

→ sequential dependent steps that need memory
and user interaction: single loop
→ independent subtasks needing reasoning
and parallel fanout: delegate_task
→ work that must outlast the session
or run on a schedule: cron job
→ deterministic multi-step pipelines
with no reasoning needed: execute_code
→ cross-profile durable work with human gates:
Kanban board (module 9)

more agents is not always better.
the skill is knowing when a fresh child
beats one more turn in the parent.

full Hermes architecture deep-dive in the article 👇

[CHAD @charles_thechad]

Chadano Citizens mint is now LIVE 🚀

1,500 unique CHAD NFTs
15 ADA per Citizen
25 ADA for Citizen + Booster Pack

Citizens are your identity and entry ticket into the upcoming gamified fee-distribution platform.

Booster Packs may include new traits, utility cosmetics, consumables, boosts, and evolution 👀

We are doubling down on Cardano and building real infra, tooling, and dApps for native assets, NFTs, and DeFi.

[Nous Research @NousResearch]

Hermes Agent now has a production-grade WhatsApp Business Cloud integration: use it as a private WhatsApp bot for yourself or your team, or configure it for customer-facing support.

Connect an existing WhatsApp Business Cloud number or create one through Meta Business Manager, then run 'hermes whatsapp-cloud' to wire it into Hermes with guided setup, secure webhooks, media/voice support, read receipts, typing indicators, and interactive approval buttons.

[Nous Research @NousResearch]

Hermes Agent now has Automation Blueprints, turning cron jobs into clickable, fillable, conversational workflows.

[ElevenLabs Developers @ElevenLabsDevs]

Call your Hermes Agent

[Nous Research @NousResearch]

We have been working closely with @nvidia to ensure Hermes Agent works smoothly on their new @NVIDIARTXSpark superchip and integrates with the new OpenShell runtime, which connects Hermes to @Microsoft's security primitives.

Watch our feature in the big announcement at Computex:

[Teknium 🪽 @Teknium]

Just pushed an update to help remote connecting with the Hermes Agent GUI over tailscale to function!

Please update if you had any issues!