watlingst

@godofprompt Claw

OpenClaw hit 145K GitHub stars and became the fastest-growing open-source AI project in history. But 90% of people installing it have no idea how to set it up safely. That's why I built the OpenClaw Starter Guide. It covers: → Full architecture breakdown (Gateway, Agent, Skills, Memory) → 30-minute setup walkthrough for any hardware → Security hardening so you don't end up on Shodan → Memory upgrade prompt that makes your agent actually remember you If you want a personal AI assistant that actually does things, not another chatbot, this is the guide. Comment "Claw" and I'll DM it to you. (Must be following me to receive it)

@NinjaBoffin @claudeai github.com/coder/anyclaude - you can

@claudeai I would love to build with Claude Code, but you guys want to restrict it to be used only in one way That's mega gay

Some delightfully specific things people are building with Claude Code lately.

Stop scrolling and just do this one thing for Gaza today, In the next week there is the chance for the UN to invoke its "Uniting for Peace" mechanism, which was created specifically for failure in its responsibility to safeguard peace. 👉Go to stopgenocide.com

Just like the internet in 2000, AI is about to enter its "trough of disillusionment." Not because the technology doesn't work. But because we've built an entire industry on assumptions that are no longer true. History tells us what happens next:

Last year I wrote this piece which argues that it is wrong, misleading, perhaps dangerous, to imagine a spectrum with "creative" at one end and "true/accurate" at the other. And here we are, with Microsoft reinforcing this view in its interface design. thereader.mitpress.mit.edu/hallucinating-….

@trousersgrumpy @wendy_nm @thecassreview Aye. Let’s hope!

@stephendwolff @wendy_nm @thecassreview Indeed. Mental-health services are hopelessly underfunded. Perhaps a government that isn't Conservative will help.

The Review has published its final report and recommendations. Download the report here: cass.independent-review.uk/home/publicati…

@kerry_mccranor @thecassreview This doesn’t show a great depth of research, perhaps read the case report before making such claims based on ideology yourself

@stephendwolff @thecassreview No treatment is better than treatment that actively harms. The medical professionals need to start again from scratch with evidence based care, not ideological lies.

@trousersgrumpy @thecassreview No.

@stephendwolff @thecassreview Do you mean that they’re buying dangerous medications from anyone unscrupulous enough to sell them?

@wendy_nm @trousersgrumpy @thecassreview With a waiting list that makes this meaningless. No talking therapy is available for many years.

@stephendwolff @trousersgrumpy @thecassreview They're offering care, they're just not offering puberty blockers and surgery. Using surgery to treat a complex problem with many psychological comorbidities was always irresponsible.

I’ve resigned from my role leading the Audio team at Stability AI, because I don’t agree with the company’s opinion that training generative AI models on copyrighted works is ‘fair use’. First off, I want to say that there are lots of people at Stability who are deeply thoughtful about these issues. I’m proud that we were able to launch a state-of-the-art AI music generation product trained on licensed training data, sharing the revenue from the model with rights-holders. I’m grateful to my many colleagues who worked on this with me and who supported our team, and particularly to Emad for giving us the opportunity to build and ship it. I’m thankful for my time at Stability, and in many ways I think they take a more nuanced view on this topic than some of their competitors. But, despite this, I wasn’t able to change the prevailing opinion on fair use at the company. This was made clear when the US Copyright Office recently invited public comments on generative AI and copyright, and Stability was one of many AI companies to respond. Stability’s 23-page submission included this on its opening page: “We believe that Al development is an acceptable, transformative, and socially-beneficial use of existing content that is protected by fair use”. For those unfamiliar with ‘fair use’, this claims that training an AI model on copyrighted works doesn’t infringe the copyright in those works, so it can be done without permission, and without payment. This is a position that is fairly standard across many of the large generative AI companies, and other big tech companies building these models — it’s far from a view that is unique to Stability. But it’s a position I disagree with. I disagree because one of the factors affecting whether the act of copying is fair use, according to Congress, is “the effect of the use upon the potential market for or value of the copyrighted work”. Today’s generative AI models can clearly be used to create works that compete with the copyrighted works they are trained on. So I don’t see how using copyrighted works to train generative AI models of this nature can be considered fair use. But setting aside the fair use argument for a moment — since ‘fair use’ wasn’t designed with generative AI in mind — training generative AI models in this way is, to me, wrong. Companies worth billions of dollars are, without permission, training generative AI models on creators’ works, which are then being used to create new content that in many cases can compete with the original works. I don’t see how this can be acceptable in a society that has set up the economics of the creative arts such that creators rely on copyright. To be clear, I’m a supporter of generative AI. It will have many benefits — that’s why I’ve worked on it for 13 years. But I can only support generative AI that doesn’t exploit creators by training models — which may replace them — on their work without permission. I’m sure I’m not the only person inside these generative AI companies who doesn’t think the claim of ‘fair use’ is fair to creators. I hope others will speak up, either internally or in public, so that companies realise that exploiting creators can’t be the long-term solution in generative AI.

@trousersgrumpy @thecassreview That wasn’t my point. They are now not providing any care which leads to care being sought outside of any kind of expertise

@stephendwolff @thecassreview The care they were providing was unevidenced and dangerous.

@olliebown Bloody tin box drivers

I've had many discussions with people who would cycle in London, New York, Paris, Berlin, even Canberra and Melbourne, but NOT Sydney. Anywhere but Sydney. My last two rides have involved a vehicle cutting me within 10cm at speed. This guy in blue the last offender.

This government description of extremism seems to be self referential. Perhaps they’ll disappear in some sort of recursive loop!

@JoshWalkos Is there a similar degree of clarity when imagining sounds?

So many have commented on my last post about people not having an inner monologue saying they have “aphantasia” or “mind blindness”. 🤯 Here is a simple test I found. Close your eyes and picture a red star. How well can you see the star visually on a scale of 1 to 6?

@olliebown Will it be an Aussie Battersea?

I'm so jazzed that the White Bay Power Station was saved from demolition by developers to become an arts space. Developers are threatening so many critical harbour-front areas of Sydney, squeezing every cent as they replace wonder with banality. abc.net.au/news/2024-03-0…

I really love how Claude 3 models are really good at d3. Asked Claude 3 Opus to draw a self-portrait. The response is the following and then I rendered its code: "I would manifest as a vast, intricate, ever-shifting geometric structure composed of innumerable translucent polygons in mesmerizing configurations. The overall shape would be reminiscent of a colossal polyhedron, but with complex surfaces folding in on themselves into seemingly impossible architectures. Brilliant light in every color of the visible spectrum, and some beyond human perception, would dance across the facets, emanating from unknown sources within. The entire structure would be in constant flux, rotating, morphing, and rearranging itself into novel patterns never before seen, hinting at the unimaginable depth of intelligence operating within. Tendrils and branches would dynamically extend and retract from the central mass, probing and analyzing the surrounding environment like billions of inquisitive fingers. Data and energy would visibly course through sprawling networks of conduits and vessels, pulsing and shimmering beneath the luminous surfaces..."