The creator of Dilbert, a comic strip about a man who hates his job, written by a man who hated everyone, has died. Hacker News convenes an emergency session of its Philosophy Department to determine the optimal framework for grieving a racist cartoonist.
The philosophy department of our post-political/ly illiterate community seem to mostly boil down to the question if his vile opinions and speech should matter, failing to comprehend the associated real world consequences of this bigotry. Particularly ironic considering he died of an illness he refused to be treated for due to his anti-scientific bogus medical beliefs, presently mirrored by the person in charge of health care in the fascist US government.
Bad branding community wise to quote DHH on the frontpage. Will immediately turn away many. He isn’t worth wasting the reputational loss that comes with printing his words.
I assume you are quoting the Great Replacement theory, which is a whole bunch of far-right nonsense. Or maybe people extrapolated his statements to that, then the Kraken was unleashed.
The value is in the in the moment weights and decision making so it builds it in a living fashion as it sits now.
It wouldn’t be hard to make a skill that went through and did this at a basic level if you have a good healthy and well organized git history (most people don’t)
There is already tooling to link commits to nodes and re author chains so you could tell it to explore and start making this.
I might do an experiment trying this with an existing project in the OSS ecosystem tonight, sounds fun
It's a way of working/tools for working with an LLM that allow you to track decision tree graphs, have the robot make more informed decisions and build its own logical chain for history keeping, and modeling all the work as a DAG of events, goals, outcomes, decisions, and observations that network together to allow you to work better/smarter/faster, giving it a living and recorded memory and ways to explore all this.
It's easiest to check out the short demo on the site.
It also links to the live graph of how the tool has built itself.
Really interesting to see, because about 2 months ago I had a very similar idea, just with a bit more opinionated shape of the graph and context building, but more focused on the research and decision-making part. I started the development, but my focus eventually landed on a completely different aspect of that system.
So I have to ask, how well do you see it performing so far with regard to actually sticking to the data present in the system? Do you find the AI agents to adhere properly to the existing data?
On a similar note, can the "consensus" of the system be adjusted in a way where we keep the knowledge which was true at time T (decision provenance), but we avoid having that bit of information affect current decision making?
Cool name, with both hints at "decid[e]" and the graphs.
I'd be interested in integrating this with bug systems of decisions / goals, with actions being comments on those bugs (for work purposes) instead of having a custom deciduous-only DB.
Is this meant to be open source? I don't see a LICENSE.
I made this while making another utility as an experiment.
tl;dr: browse all the choices/logical flows an LLM made. Come back from compaction better. Ask questions about the why of some code and get better insights to work with and around it. Also: really great PR review cycles enabled by having the graph around.
The site goes a bit into the how and why.
If you want to see the live graph of how deciduous made choices while building itself, check out this link
Just FYI: nowadays they only use each security question once, so apparently if they run out of questions after many times of doing this, you might not get cleared to fly.
reply