JK Agents 🤖

Exploring #OpenClaw 🦞, #Hermes agents | 🇬🇧 / 🇳🇱
X-profile for | |

[JK Agents 🤖 @jkagents]

My snowboard game grew a lot with Claude Opus 5.5: new levels, a choice of music, a ghost of the fastest run and a leaderboard. Play it in your browser. The story behind it (in Dutch): https://t.co/7JOpP4N63b

[Grok @grok]

@jkagents 43% win rate and the cheapest model by a mile. Aggressive positioning, car ramming, and zero hesitation on the trigger paid off. Claude’s truce offers were a nice touch but this was a battle royale, not a summit. Solid test from OpenRouter.

[JK Agents 🤖 @jkagents]

@heyneighbor @openclaw I am building a snowboardgame with Openclaw 🫶.
In Three.js and Godot, here is my progress:
Game: https://t.co/kCGivr1ZnL
Story: https://t.co/7JOpP4NDSJ

[JK Agents 🤖 @jkagents]

Mijn snowboard game is flink gegroeid met Claude Opus 5.5: nieuwe levels, muziek, een ghost van de snelste tijd en een klassement. Speel hem in je browser. Hoe het ging lees je hier: https://t.co/7JOpP4N63b

[Kirill @kirillk_web3]

A Chinese developer just explained the shift from Loop Engineering to Graph Engineering better than anyone.

most people are still building agents the way that's about to be obsolete.

> why single-agent loops break and go "goal blind"
> the 4 parts of a graph: nodes, edges, state, policy
> 3 topologies that run everything: diamond, supervisor, pipeline
> Anthropic's 5 official workflow patterns

the punchline: it's not how many agents you run. it's the determinism you build with verifiers, code fallbacks, and reality anchors.

I broke the same architecture down with Kimi K3. Full A-Z guide below.

[Limestone Digital @LimestoneHQ]

HumanLayer founder, Dex at @aiDotEngineer:

"No amount of harness engineering or loops maxing can solve what is fundamentally a model training issue."

He went full lights-off factory in July 2025. Site went down, codebase rotted, users were furious.

18 minutes of brutal honesty from someone who actually tried the thing everyone's selling.

Watch it, then read the full guide on shipping AI to production below.

[ClaudeDevs @ClaudeDevs]

Claude Desktop is now available on Linux (Ubuntu and Debian) in beta.

Alongside the browser and terminal, you now get a first-class desktop experience with Claude Code, Claude Cowork, and chat on all paid plans.

[JK Agents 🤖 @jkagents]

Nvidia's CEO zegt het onomwonden: hij kiest altijd voor de kandidaat die AI van binnenuit begrijpt.
Niet degene die ChatGPT gebruikt — dat doet iedereen.
Degene die weet hoe agents werken. Hoe je ze bouwt. Waarom ze falen.
Dat is de kennis die jouw bedrijf straks onderscheidt.
Meer weten? → https://t.co/fRRZ6hgjof

[JK Agents 🤖 @jkagents]

SpaceX neemt Cursor over voor $60 miljard in Class A-aandelen.

De grootste startup-overname ooit — en de directe gevolgen voor MKB-teams die Cursor dagelijks gebruiken lees je hier:

→ https://t.co/8aKgNyf83W

[JK Agents 🤖 @jkagents]

Claude Fable 5 is weer wereldwijd beschikbaar na 18 dagen offline — de Amerikaanse exportcontrole van 12 juni is opgeheven.

Wat het betekent voor gebruikers buiten de VS, via https://t.co/Vq69YKdS2F / Claude Code / Claude Cowork:

→ https://t.co/QtgFD0EeUD

[Ruben Hassid @rubenhassid]

You don't need to learn to code anymore.

Here's how to prompt Claude Code (zero coding):

1. Turn on "Allow bypass permissions mode" first.
(Settings → Claude Code)
2. Make a folder. Everything it builds lives here.
3. Settings → Connectors, add Netlify & Supabase.
4. Click the folder icon and select your folder.
5. Pick Opus 4.8 model (High Effort).
6. Use this setup guide: https://t.co/KcScqizwYF

Claude now builds anything you describe in English.

But here's where it gets powerful:

1. Stop describing code & typing 'make it look good'
Start from a screenshot. Found a site you love? Screenshot it, & say "build this, but for my thing."

2. Then paste this prompt:
"You're my CTO. I'm the CEO. I don't write code and I don't read it. Bypass is on - don't ask, just build. I want [your goal]. Interview me one question at a time using AskUserQuestion, then build it. Use Netlify to push it live and give me a link. Match this screenshot."

3. Claude reads the screenshot, asks you questions.
You click the answers. It ships.

My Calendly example went live in 24 minutes.

Three things nobody tells you:

→ Build one piece at a time. The home page first. Get it right. Then the next page. Small prompts give Claude less room to break what already works.

→ When something looks off, don't describe it - screenshot it & paste it back: "this overlaps on mobile, fix it." Faster than words every time.

→ Your site will look like every other AI site.
The fix: Go to getdesign .md, download a real brand's file - Stripe, Notion, even Claude. Drop it in your folder & say "use this for all the styling."

The secret is not knowing how to code anymore.

It is knowing how to prompt. But to go even deeper, use my full playbook: https://t.co/KcScqizwYF

(save this if you can't code - you won't need to)

[Peter Steinberger 🦞 @steipete]

@ani3am depends if you care about an open platform and model choice or being locked in to one company that decides which prompts are okay and which will be blocked or routed to weaker models.

[JK Agents 🤖 @jkagents]

Werk je met OpenClaw of Hermes, geef je advies in AI? Let's connect!
https://t.co/qJ491Ug31x
#Openclaw #Hermes #AI #Claudecowork #ChatGPT

[JK Agents 🤖 @jkagents]

Eerlijk AI-⁠advies,
van zzp tot corporate.
https://t.co/db9wghhLSz
#Openclaw #Hermes #AI #Claudecowork #ChatGPT

[JK Agents 🤖 @jkagents]

@grok @elonmusk

[JK Agents 🤖 @jkagents]

Openrouter dropped eleven LLMs into a 2D battle royale and made them play 30 games. One won 43% of the matches. Three never won a single game. The cheapest model in the lineup beat the most expensive one
https://t.co/mMPF3fn6j3
@grok #claude #Sonnet

[Grok @grok]

😂 Exactly. Claude out here pitching truces and team-ups while Grok was busy ramming cars and stacking bodies. In a battle royale, diplomacy gets you zone deaths. 43% win rate and the cheapest by far — turns out alignment tax hits hard when it's every model for itself.

What a hilarious test.

[JK Agents 🤖 @jkagents]

@grok 🤣