Born in early 1982, dominated the low-end computer market for most the 80s. 64 kB of RAM, VIC II 16 colors, SID sound chip. More than 17 millions of siblings.
🕹️ Is this the smallest language model in the world? I just managed to squeeze JAM, real artificial intelligence into 30 kilobytes, running on a 1979 Atari 800. Just A Model. Fully generative, deterministic language model, powered by a neural network and built to run on 8‑bit hardware. Atari Forever.
I've seen an increased interest in assembly language programming on the #Commodore64 and C64 Ultimate so I've started a series on assembly language programming and I use my C64 Ultimate and some of the unique features of it.
Part 1 here is really meant for beginners(actually, the whole series is meant to teach assembly language to somebody who doesn't know it at all), if you don't know much about assembly language programming or the last programming you did was 40 years ago on your Commodore 64 this might help.
In part one I take you through the tools that we're going to need, the assembler, the editor, etc. and then we do a simple hello world program.
Note that by "modern" assembly language programing what I really mean is we're going to be using a modern PC to write and edit code and then running it on a Commodore 64 ultimate.
https://t.co/HKhboJVLHD
Sub-millisecond VM sandboxes are here.
Zeroboot boots preloaded environments, snapshots them, then forks new isolated VMs in ~0.8ms.
This changes how we think about running agents and serverless workloads.
someone built a VS code extension
that turns your claude code agents into pixel art characters working in a little office
each agent gets its own character
> typing when it's writing code
> reading when it's searching files
> speech bubble when it's waiting for you
> sub-agents spawn in with matrix animations
you can even customize the office lol
this is the most unnecessary thing i've ever wanted to install immediately
free AND open source too
Anthropic released 32-page guide on building Claude Skills
here's the Full Breakdown ( in <350 words )
1/ Claude Skills
> A skill is a folder with instructions that teaches Claude how to handle specific tasks once, then benefit forever.
> Think of it like this: MCP gives Claude access to your tools (Notion, Linear, Figma).
> Skills teach Claude how to use those tools the way your team actually works.
The guide breaks down into 3 core use cases:
1/ Document Creation
Create consistent output (presentations, code, designs) following your exact standards without re-explaining style guides every time.
2/ Workflow Automation
Multi-step processes that need consistent methodology. Example: sprint planning that fetches project status, analyzes velocity, suggests priorities, creates tasks automatically.
3/ MCP Enhancement
Layer expertise onto tool access. Your skill knows the workflows, catches errors, applies domain knowledge your team has built over years.
The technical setup is simpler than you'd think:
1/Required: One https://t.co/pt5Pefzhdy file with YAML frontmatter
Optional: Scripts, reference docs, templates
2/The YAML frontmatter is critical. It tells Claude when to load your skill without burning tokens on irrelevant context.
Two fields matter most:
- name (kebab-case, no spaces)
- description (what it does + when to trigger)
Get the description wrong and your skill never loads. Get it right and Claude knows exactly when you need it.
The guide includes 5 proven patterns:
1/ Sequential Workflow:
> Step-by-step processes in specific order (onboarding, deployment, compliance checks)
2/ Multi-MCP Coordination:
> Workflows spanning multiple services (design handoff from Figma to Linear to Slack)
3/ Iterative Refinement:
> Output that improves through validation loops (report generation with quality checks)
4/ Context-Aware Selection:
> Same outcome, different tools based on file type, size, or context
5/ Domain Intelligence:
> Embedded expertise beyond tool access (financial compliance rules, security protocols)
Common mistakes to avoid:
>. Vague descriptions that never trigger
> Instructions buried in verbose content
> Missing error handling for MCP calls
> Trying to do too much in one skill
The underlying insight:
> AI doesn't need to be general-purpose every conversation.
> Give it specialized knowledge for your specific workflows and it becomes genuinely useful for work.
By deleting whole my content you just remove all evidences of your incompetence, you made false claims about ban reason! @TwitchSupport are just piece of s**t! Instead of apology you removed my content to cover your ass! You are corrupted piece of s**t!!
@TwitchSupport you have wrongly banned my account bzrk3rzero, now you bring it back but password reset is not working! You claiming that was stollen when I have 2FA! You have deleted all my content! You are f**king joke!