971–980 of 1001 posts
The real big deal about 'claws' in that they're agents oriented around the user. The kind of AI everyone hates is the stuff that is built into products. This is AI representing the company. It's a foreign invader in your space. Claws are owned by you and are custom to you. You even name them. It's the difference between R2D2 and a robot clone trying to sell you shit. (I'm aware that the llms themselves aren't local b…
One safety pattern I’m baking into CLI tools meant for agents: anytime an agent could do something very bad, like email blast too many people, CLI tools now require a one-time password The tool tells the agent to ask the user for it, and the agent cannot proceed without it. The instructions from the tool show an all caps message explaining the risk and telling the agent that they must prompt the user for the OTP I ha…
I've created my own "claw" running in fly.io with a pattern that seems to work well. I have MCP tools for actions that I want to ensure human-in-the loop - email sending, slack message sending, etc. I call these "activities". The only way for my claw to execute these commands is to create an activity which generates a link with the summary of the acitvity for me to approve.
Earlier quoted context omitted.
Handing your digital life to a claw bot that was vibe coded however, is a good idea?
Every single documentation and commentary about this says that it is not a good idea, but it does trigger the inspiration and imagination of people of what the future is going to be. The whole conversation around this comment is that people don't get why people are excited about this.
If you have 10 minutes, here is an example of how LLM tech can trigger inspiration and imagination of people of what the future is going to be:
Earlier quoted context omitted.
I work at a company that is forcing us to use AI as much as possible for our coding work. I did 1 month's of work in 1 day last week. A few hiccups, but the slop works as expected. From where I sit, the hype is real.
Well, roughly half developers are below the average. LLM code is good enough for them, but now such developers can add technical debt faster. Sorry, but if you don't see the issues with the code LLM generates....
It's an accelerant, both good and bad. How that plays out in companies where the majority are below-average is a nuanced and concerning case
Earlier quoted context omitted.
This is interesting. Do you mean this is like chat with your book, or these are books you've already finished reading which you have a query over to ask? And does it search raw book text or metadata?
I add books to Calibre in order to load them on my Kindle. Claw gets the Calibre files, including both metadata.db and full-text-search.db, via Syncthing. I can ask it to perform metadata updates, since it's a two-way sync, or ask questions about the content.
Earlier quoted context omitted.
Would you say that Musk is one of the most significant AI pioneers in history? I don't personally believe that founding the organization is more meaningful than doing the actual work.
The difference is that Andrej is an actual AI engineer who remained involved in the company. Musk was just an early co-founder who eventually left and had no involvement on the breakthroughs of the company.
Earlier quoted context omitted.
sexps?
> sexps? Not the person you're responding to, but I think they mean sexps as in S-expressions [1]. These are used in all kinds of programming, and they have been used inside protocols for markup, as in the email protocol IMAP. [1] https://en.wikipedia.org/wiki/S-expression
"Just existing tech repackaged" is accurate and beside the point. Dropbox was just rsync repackaged. The value is in how it comes together, not the individual pieces.
What's actually missing that nobody's built yet: declarative workflow definitions. Everything I have is imperative bash. Want to change the order something runs? Edit a 1,300-line script. A real Claws system would define workflows as data and interpret them.
Earlier quoted context omitted.
Of course it can "model time". It has access to system clock and know its heartbeat rate. Can you "model time" when you are asleep? Whatever "model time" means, it sounds like projection to be frank. > Or feeling things for that matter. Philosophical zombie experiment, the conclusion is qualia dont matter, only IO. If two systems have the same behavior there is no meaningful difference.
Modeling time means there is some way of e.g. evolving state over time, or projecting change over a period of time. Or being able to count time passing (without being told by external sources). The LLM has no model of time. It is being called at regular times. If the cronjob misses two days or even a whole year of calling the LLM, the LLM will not respond any differently from if the cronjob was on time.
If you give it clock as input, it will observe the passage of time and can model it. The entire explosion of the AI industry due to LLMs is the observation that their abilities generalize, so there's no reason to believe that LLMs can't "model time". They can, if you tell it to and give it proper input.
Earlier quoted context omitted.
> We already have examples of these agents creating an AI religion, an AI social network (which debated how to keep humans out using a human captcha), attempting to legally separate from their creators Didn’t these turn out to be fake and/or humans cosplaying as bots?
It doesn’t even matter anymore. The hype is an unstoppable force
I don’t know, this seems like the typical ‘insane last gasp’ of a bubble. petz.com superbowl ad?