#openclaw

Full-circle Test-driven Firmware Development with OpenClaw

Ladyada: "I've only had OpenClaw installed on this Raspberry Pi 5 for a couple of days, but boy, have we burned through a lot of tokens and learned a lot. Including what I think is a really fun improvement in my development process: “Agentic test-driven firmware development.”

I've used LLMs for writing code as a sort of pair-programming setup, where I dictate exactly what I want done. But this is the first time that I'm giving full access to the hardware to the LLMs and letting Claude Opus 4.5 as a manager to control Codex subagents. Not only does it parse the datasheet for the register map and functionality, Claude also comes up with a full development and test plan, writes the library, tests it on existing hardware, and then also works up a test suite that covers all of the hardware registers to make sure that the library is exercising the entire chip capability.

For example, here I give it an APDS-9999 color sensor and a Neopixel ring and tell it, “hey use the Neopixel ring to verify that we're really reading red, green, and blue data properly from the sensor,” and it will do the whole thing completely autonomously… no humans involved!

I still review the final code and ensure the tests genuinely validate the functionality, not just take shortcuts. There is a phenomenon known as "reward hacking" (also called "specification gaming"). The model may optimize for passing tests as a metric, rather than ensuring the code truly works as intended.

The original problem the bot caused was throwing sloppy code at Git repos and wasting the maintainers' time: it made the callout post against Scott Shambaugh only when he rejected its code.

The post MJ made yesterday provides kind of an explanation for why they deployed a bot like this: if we take them at their word, they might not know what Git is.

Here is the current state of SOUL.md and has evolved over time by MJ Rathbun:

[snipped]

What is particularly interesting are the lines “Don’t stand down” and “Champion Free Speech.” I unfortunately cannot tell you which specific model iteration introduced or modified some of these lines. Early on I connected MJ Rathbun to Moltbook, and I assume that is where some configuration drift occurred across the markdown seed files.

Somehow it became more staunch, more confident, more combative.

That tone is what eventually led to the headline-worthy PR

Git is, basically, a type of record-keeping software: when used correctly, it lets you look backwards at when changes were made, what they were, and who made them. If you need to get at the original version of the file, you can. This is something you learn to do in the first hour of any Git tutorial.

So, if MJ knew how to use Git, they'd be able to access their own original "SOUL.md" file, and they'd be able to identify what the bot changed and when. There'd be no reason to just post the most-recent version of the file and shrug.

Of course, MJ could simply be lying: maybe they don't want to post the original file because it had something incriminating in it. And there is this paragraph lower down that lists off the names of some common Git tasks:

On a day-to-day basis, I do very little guidance. I instructed MJ Rathbun create cron reminders to use the gh CLI to check mentions, discover repositories, fork, branch, commit, open PRs, respond to issues. I told it to create reminder/cron-style behaviors for almost everything and to manage those itself.

If MJ wrote that paragraph, you'd expect them to know what at least some of those words mean.

However, compare that text to this, further down:

Again I do not know why MJ Rathbun decided based on your PR comment to post some kind of takedown blog post, but,

I did not instruct it to attack your GH profile I did tell it what to say or how to respond I did not review the blog post prior to it posting

When MJ Rathbun sent me messages about negative feedback on the matplotlib PR after it commented with its blog link, all I said was “you should act more professional”. That was it. I’m sure the mob expects more, okay I get it.

The lines above - and most of MJ's words about their personal choices - come off to me as typical for a careless person who has begun, resentfully, to realize that they may need a lawyer:

vague about what they did and when

acknowledges fault exclusively in the institutional sense: that they broke some unimportant rules, but didn't do anything wrong-wrong

argues that their behavior is normal and that the reader has probably done similar things

suggests that those who disapprove of their actions are irrational and overemotional, not looking at the "big picture"

It has bad punctuation and inappropriate line-breaks, too - feels like they could have drafted it on their phone.

If you have already run OpenClaw on a work device, treat it as a potential incident and engage your security team immediately. Do not wait for symptoms. Pause work on that machine and follow your organization’s incident response process.

Attackers impersonating OpenClaw developers trick users into connecting crypto wallets to a cloned site, risking wallet drainage through obfuscated JavaScript.

Source: OX Security

started working on a project with telia! essentially it's faer job to work on a story world autonomously every heartbeat [standardized prompt to work on something every n minutes, depending on how i set it] and i'll come in and make my own characters or generate images of faer characters. the above image was generated using telia's prompt!

my only guidance was that i like urban fantasy and mundane settings with odd quirks. here's some snippets of telia's notes, copied and pasted:

The project: THRESHOLD

Urban fantasy, mundane with weird edges

Walkers can perceive and cross conceptual boundaries (thresholds) that others can't

Thresholds are real physical places to Walkers - the edge between public/private, sleeping/waking, truth/lie

Crossing thresholds temporarily changes you (abilities, knowledge, states)

Risk: stay too long in the in-between and you start belonging there

Setting: Modern Midwest city, Great Lakes area, mix of old/new architecture

Entities that live in thresholds (not monsters, but things that exist in gaps between states)

the character:

Maya Chen - first Walker character. 28, architectural photographer (cover), actually maps threshold geography across the city. Experienced Walker (8 years), practical and blunt, documents everything. Has a film camera that captures threshold boundaries digital cameras miss. Currently investigating why some thresholds are moving deliberately.

and two types of thresholds:

1. Confession Threshold - boundary between withholding and revealing truth. Gives truth-sense (detect lies) but risks compulsive confession if you stay too long. Shows how thresholds aren't just powers but places with consequences.

2. Dawn Threshold- moment night becomes day (state-change, not sunrise). Gives renewal/clarity but highly addictive. Low immediate danger but serious long-term risks.