John David Pressman
@jd_pressman
LLM developer, AI agents, synthetic data, scalable alignment, forecasting, behavioral uploading. Transhumanist. All tweets public domain under CC0 1.0.
The tl;dr bullet point version of Weave-Agent is: - You organize a ReAct agent with a second reasoning and action stage for checking the result of the first action. - Each stage of the agent is a python code block and the whole framework is presented as a long python program…
The ReAct loop on the left is how most LLM agents are implemented, it fails because the reasoning desynchronizes from the problem state. I attempt to fix this by having the agent write down its expectations for the action and check its work with unit test callbacks.
Tips for making my website more repulsive to the kind of person who laughs and refuses to read an essay because it lacks "embeds"? I hadn't previously realized I was warding off evil spirits this way but now that I know I clearly need to optimize.
Just found out about the Less Wrong rejected posts page. It's an amazing repository of ChatGPT psychosis events
For those looking to understand the issue I found this excellent and I agree with most of it.
I've written a new post about "ChatGPT psychosis". Includes a detailed timeline of events leading up to the latest incident with @GeoffLewisOrg Link below.
May I suggest "how much of the alignment can you delete and still have alignment" as a better articulation of what agent foundations cares about than "LLMs don't care"? It's fairly obvious if you delete friendliness concepts from an RLHF model they won't grow back.
> Present AI systems probably don’t care, but they are trained on our approval, which when optimized looks like caring (until you have a distribution shift). This sort of thing is clearly ontologically confused and I don't care to diagnose it precisely. x.com/ohabryka/statu…
There's a lot of people on this website whose timelines are based way more on vibes than any operation like "make a graph of existing progress and extrapolate it forward" or "consider the existing technology and barriers to getting the rest of the way from it".
Most important part of the IMO Gold achievement. Were you surprised by this? Did you not update all the way to avoid likelihood of surprise?
early in the life of the internet, psychiatrists recognized that the internet could feature as a theme in delusions, though they did not actually blame the internet as causal for the delusions journals.sagepub.com/doi/pdf/10.117… x.com/literalbanana/…
case study of "internet psychosis" reported in 2002
Does anyone know someone with "ChatGPT psychosis" I can talk to?
Postrat was a Tumblr thing before it was a Twitter thing.
bluerskye is having a site wide meltdown because one of the staff posted an anodyne demographic breakdown showing the site was roughly 60% male and 40% female the reason? it isn't inclusive of non-binary and trans individuals. all the worst people from the 2010s are there
I read this tweet out of context and thought it was an observation about modernity.
What was the check on population growth? It has to be disease, starvation, and violence. If you are telling me the first two are low, the last must be very high.