sandbags

Mentally preparing for the @GCMarathon in 2 days!!! Our team has almost raised our total fundraising target of $2500! 🤍 We helping change some lives @headspace_aus! #GCM23 goldcoastmarathon23.grassrootz.com/headspace/ibvn…

@BeepBoopBotz Boop cunt

Beep

@elonmusk The rigmarole 🤣

😑

Eagles music.youtube.com/channel/UC49r4… via @YouTubeMusic

🚨 Apple Plans to Manufacture Mac Mini in Houston wsj.com/tech/apple-pla…

@karpathy BEST ❗️ ‼️ 🎉

Bought a new Mac mini to properly tinker with claws over the weekend. The apple store person told me they are selling like hotcakes and everyone is confused :) I'm definitely a bit sus'd to run OpenClaw specifically - giving my private data/keys to 400K lines of vibe coded monster that is being actively attacked at scale is not very appealing at all. Already seeing reports of exposed instances, RCE vulnerabilities, supply chain poisoning, malicious or compromised skills in the registry, it feels like a complete wild west and a security nightmare. But I do love the concept and I think that just like LLM agents were a new layer on top of LLMs, Claws are now a new layer on top of LLM agents, taking the orchestration, scheduling, context, tool calls and a kind of persistence to a next level. Looking around, and given that the high level idea is clear, there are a lot of smaller Claws starting to pop out. For example, on a quick skim NanoClaw looks really interesting in that the core engine is ~4000 lines of code (fits into both my head and that of AI agents, so it feels manageable, auditable, flexible, etc.) and runs everything in containers by default. I also love their approach to configurability - it's not done via config files it's done via skills! For example, /add-telegram instructs your AI agent how to modify the actual code to integrate Telegram. I haven't come across this yet and it slightly blew my mind earlier today as a new, AI-enabled approach to preventing config mess and if-then-else monsters. Basically - the implied new meta is to write the most maximally forkable repo and then have skills that fork it into any desired more exotic configuration. Very cool. Anyway there are many others - e.g. nanobot, zeroclaw, ironclaw, picoclaw (lol @ prefixes). There are also cloud-hosted alternatives but tbh I don't love these because it feels much harder to tinker with. In particular, local setup allows easy connection to home automation gadgets on the local network. And I don't know, there is something aesthetically pleasing about there being a physical device 'possessed' by a little ghost of a personal digital house elf. Not 100% sure what my setup ends up looking like just yet but Claws are an awesome, exciting new layer of the AI stack.

@michielmv @dedene @karpathy Thank you! 🙏🏽

@dedene @karpathy the tools proxy pattern is the way. your agent does the work, but never has direct access to the keys. more people should be running it this way

@dedene @karpathy Genius

@karpathy I run my OpenClaw in a sandbox with a sort of “tools proxy” so it never sees any keys or things it shouldn’t have access to. github.com/dedene/claw-wr… gives me a little more peace of while the agent can still access all the tools I want.

@rida @karpathy Love it Rida!

@karpathy If you do one thing, give its own identity and accounts and let it collaborate with you. I gave mine X and GitHub accounts and a 1Password vault and now I can trust it more since we have clear boundaries.

@karpathy Ahahaha I bought one of these a year ago no one could figure it out not even me!!!

Broke into the top 100 on volume for @yeet Airdrop farming baby 😏

@LieutenantPonzi @yeet Bin a minute brother @LieutenantPonzi I need to get my ass back into Discord methinks it’s been about a year dead to the world!!!!!

Bayes’ theorem is probably the single most important thing any rational person can learn. So many of our debates and disagreements that we shout about are because we don’t understand Bayes’ theorem or how human rationality often works. Bayes’ theorem is named after the 18th-century Thomas Bayes, and essentially it’s a formula that asks: when you are presented with all of the evidence for something, how much should you believe it? Bayes’ theorem teaches us that our beliefs are not fixed; they are probabilities. Our beliefs change as we weigh new evidence against our assumptions, or our priors. In other words, we all carry certain ideas about how the world works, and new evidence can challenge them. For example, somebody might believe that smoking is safe, that stress causes mouth ulcers, or that human activity is unrelated to climate change. These are their priors, their starting points. They can be formed by our culture, our biases, or even incomplete information. Now imagine a new study comes along that challenges one of your priors. A single study might not carry enough weight to overturn your existing beliefs. But as studies accumulate, eventually the scales may tip. At some point, your prior will become less and less plausible. Bayes’ theorem argues that being rational is not about black and white. It’s not even about true or false. It’s about what is most reasonable based on the best available evidence. But for this to work, we need to be presented with as much high-quality data as possible. Without evidence—without belief-forming data—we are left only with our priors and biases. And those aren’t all that rational.

@elonmusk I am in a psych ward and can concur

Banger

believe in something nigga

@volcanobl4ck @tribeodyssey Gud tribe is god TRIBE

Rain slicks the asphalt, but my fur remains dry dust and death, pure Ash. I stalk wastelands draped in Barbarian fur, a primal king in the wasteland. The slouchy beanie is a stylistic joke; the jagged Punk steel driven through my snout isn’t. My Toxic optics cut the smog, glowing like chemical spills, tracking heat signatures in the alleyways. When I breathe, I don't exhale steam. I bleed an absolute darkness leaking from a broken soul. They say the Radioactive Core burns you alive. Wrong. It forged me. I’m the savage consequence of a wastelands that forgot how to die.

Lurking in the Dark.