I’ve been having decent luck telling it to keep track of itself in a .plan file, not foolproof, of course, but it has some ability to “preserve context” between contexts.
Right now I’m experimenting with using separate .plan files for tracking key instructions across domains like architecture and feature decisions.
> I’ve been having decent luck telling it to keep track of itself in a .plan file, not foolproof, of course, but it has some ability to “preserve context” between contexts.
This is the way. Not only have I had good luck with both a TASKS.md and TASKS-COMPLETE.md (for history), but I have an .llm/arch full of AI-assisted, for-LLM .md files (auth.md, data-access.md, etc.) that document architecture decisions made along the way. They're invaluable for effectively and efficiently crossing context chasms.
Yeah, this. Each project I work on has it's own markdown file named for the ticket or the project. Committed on the branch, and I have claude rewrite it with the "current understanding" periodically. After compacting, I have it re-read the MD file and we get started again. Quite nice.
The entire website was created by Claude Sonnet through Windsurf Cascade, but with the “Fair Witness” prompt embedded in the global rules.
If you regularly guide the LLM to “consult a user experience designer”, “adopt the multiple perspectives of a marketing agenc”, etc., it will make rather decent suggestions.
I’ve been having pretty good success with this approach, granted mostly at the scale of starting the process with “build me a small educational website to convey this concept”.
I'm sharing Fair Witness Bot with HN first because this community understands both the technical and philosophical dimensions of AI. The framework needs people who can critique its assumptions and help evolve the implementation. If you've been thinking about epistemology in AI or are just tired of LLM hallucinations, I'd appreciate your perspectives on whether this approach could become a community standard.
The framework idea and yaml prompt was developed with the assistance of Kagi Assistant and Claude Sonnet 3.7 (Thinking),
The site was vibe coded with Windsurf Cascade and Claude 3.7 Sonnet (Thinking).
I've been interested in the idea of E-Prime (e.g. write a classifier that can tell if a text is in E-Prime, something that rewrites text in E-Prime, etc.) Eventually I lost interest because you can write just as bad E-Prime as you can in English.
For instance, sci-fi writer Charlie Stross wrote "Keir Starmer is a fascist" which is a clear abuse of "to be" but you can stuff adjectives just fine in E-Prime: "Fascist Keir Starmer never stops pushing fascist policies with his fascist attitudes and fascist friends." You could make the case that E-Prime frequently improves on English but some constructions become terribly tortured.
I understand where you are coming from - I’ve gone so far as to try to regularly write at work in E-Prime in the past. I definitely found that it forced me to think hard about what I was trying to convey, which ultimately improved the vocabulary I was using. I also definitely found it to be a lot of trouble the maintain with consistency.
The thing is, though, that LLMs don’t appear to trouble themselves at all when following E-Prime!
After a lot of conceptual refinement for the overall idea I had (minimizing hallucinations by prompt alone), it was almost trivial to make the LLM consistently use E-Prime everywhere.
You raise an interesting thought though: how to tweak this prompt such that it gets the LLM to avoid using E-Prime where it significantly reduces readability or dramatically increases cognitive load.
A classifier for “bullshit” detection has been on my mind.
Truth is the most problematic problem in philosophy, the introduction of the idea of the truth erodes the truth as seen in Godel's theorem or the reaction you get when you hear "9/11 truther." In many cases you can only determine the truth by physical observation, in other cases it is inaccessible. An A.I. that can determine the truth of things is a god.
A emotional tone or hostility detector, on the other hand, is ModernBERT + BiLSTM for the win. I'd argue the problem with fake news is not that it is fake but that it works on peoples emotions and that people prefer it to the real thing.
You can detect common established bullshit patterns and probably new ones that are like the old ones. 30 years from now there will be new bullshit patterns your model doesn't see.
I don't see how Gödel's theorems at all shows that "the introduction of the idea of the truth erodes the truth". Gödel's incompleteness theorems are mostly about provability anyway, which is a distinct concept from truth.
Though, Gödel's completeness theorem I suppose does relate provability to truth in that it shows that (for systems with the right kind of rules of inference) provability is equivalent to something being true in all models...
Still, are you sure Tarski's undefinability theorem isn't more relevant to your point?
> I don't think there is a shift to the right, but rather a shift towards authoritarianism.
In my opinion, that may be a fairly contrary-to-fact opinion to hold.
Take the contentious issue of transgender human rights, for example: the HN discussions that I’ve seen quite heavily tended towards right-wing principles of distrust of intellectuals [0] (vis-a-vis completely discounting readily available scientific information). I presume that much of the indignation towards trans topics also stems from a the right-wing principle of religious traditionalism [0].
Granted, that’s just based on my experiences in the comments. I’ve not done any sort of in-depth analysis to arrive at the above opinion.
Alternatively, perhaps the latest stage of right-wing politics could be defined as the replacement of democratic law-and-order with righteous authoritarianism, rendering the quote somewhat nonsensical, in my hypothetical opinion.
> Take the contentious issue of transgender human rights [...] tended towards right-wing principles of distrust of intellectuals
There's a weird form of "intellectual"ism going on these days.
I've gotten insanely mad pushback on my contention that we simply cannot know if Covid leaked from Wuhan. (Or, back in 2020 we couldn't - who knows where we're getting now.) It could be easy to show there was a leak, but would be almost impossible to show there wasn't. Note that I wasn't saying "we shouldn't take the vax" or anything, just the leak issue. Total rabid culture war.
Similarly, there's a huge push that "trans women are women" and that there's science for this, gender spectrum and so on, but there's no ability to look behind the curtain. The studies don't show what they purport to, and don't match the claims they're being used to defend. Nobody has attempted to show a midpoint on the sex spectrum, and even if they did - the argument has moved on and now trans is an issue of self-id that doesn't require any physical issue. Bring this up and you're "literally saying trans people shouldn't exist", etc.
In both cases there's no depth to the argument, despite that it apparently comes from the best scientific minds in the world - it claims to be a factual claim but when you ask to see the facts it becomes a purity issue where you're then shamed for not simply believing. I was told I was a Covid denier because of not simply accepting the no-lab-leak story.
> perhaps the latest stage of right-wing politics could be defined as the replacement of democratic law-and-order with righteous authoritarianism
One side makes "facts" a matter of righteousness and the other side simply eschews facts for their religion.
That’s the scary part - the facts are readily available, but so few take the time to understanthe current state of it. Instead, they argue from their armchair based on this-or-that principle of the day.
The science is still new, but has solid foundations. It might only be a matter of years before a genetic test for tendency towards “transgender” will be created.
> The science is still new, but has solid foundations. It might only be a matter of years before a genetic test for tendency towards “transgender” will be created.
Unlikely, considering that when researchers control for homosexuality in their test subjects, the correlations with gender incongruence that were supposedly found in earlier research are no longer present.
> It might only be a matter of years before a genetic test for tendency towards “transgender” will be created.
Do you recognize that you're about five years behind in "the message"? Trans is purely self-id, to declare yourself trans in the "progressive" countries like NZ and Canada you don't need to even suggest that there's anything physical involved. Specifically you're even allowed to keep changing your identity, something that couldn't happen if trans had a physical nature. Also, you're allowed to claim non-binary but use the women's washroom without even explaining why this would be appropriate.
In Canada you'd be called a trans-medicalist, which theoretically is advocating conversion therapy - to talk people out of their felt experience of gender or gender identity. It's borderline 'hate speech'.
> The science is still new, but has solid foundations.
What is the contention? Not the evidence, just the premise?
Do you suggest that males, like William (Lia) Thomas and Boyd (Fallon Fox) Burton are no stronger than women the moment they transition or that they rapidly become female-like by taking estrogen and losing testosterone as a consequence of their genital surgeries?
In these studies, is Caster Semenya treated as female despite fathering a baby?
> That’s the scary part - the facts are readily available, but so few take the time to understan the current state of it.
What facts? Be specific. Because many studies in the subject area would have failed a second-year student recently in any other specialty. Specifically the small sample size and self-selected nature of the trans athletes who have a motive to sandbag and return worse times in order to "prove" that they belong in women's sports, etc.
If that isn't what you meant, then please list these good studies because the space is crowded with academically blessed nonsense.
Tell you what, I'll examine any of those studies with you if you wish. If you're serious, tell me which claims resonate with you and we can examine them.
My post (parent to yours) outlined enough problems with "studies" in general that I can't think you're seriously suggesting any of them except by inertia at this point. Trying to pick an accurate journal, by reputation, in a time of extreme cancelling doesn't work. Even if SciAm had any standards they couldn't have published a negative article about transition because they would literally receive death threats.
If you've got sources that say sex is a spectrum, they're simply wrong. Developmental sex disorders don't make a new sex. Males produce sperm, and females produce eggs. There's no third sex that produces spegg, or what have you.
All of these articles contradict basic, and observable, biology. If they were true we'd have discovered it long ago when people and animals couldn't breed in expected ways. It's one of those things that only academics, who've never set foot on a farm, could believe.
Further, most of those articles are literally attempted child murder to justify the fetishes of their adult authors. They say things like "puberty blockers are reversible" despite all evidence (and basic logic) showing that they are not. It's impossible to have performed a study on giving children puberty blockers (at regular puberty age, not earlier like in the cases of precocious puberty) because we weren't performing a standard procedure until recently which could be studied. Those authors are saying "things we've never tested, which have huge and systemic impacts on your body, have zero long-term consequences".
John Stewart tells us that children are not being given puberty blockers, but doctors are telling us they are - and in sufficient quantity to have studied their impact. Obviously one, or both, of these is a lie. The more you look into trans "science" the more you'll see none of it is even intellectually plausible, let alone the pinnacle of science as you implied.
> I'll examine any of those studies with you if you wish. If you're serious, tell me which claims resonate with you and we can examine them.
What, did you leave your brain at home?
It sounds like you want me to walk you through the science?
How about you read the research and tell me what your questions are and then I will respond.
> If you've got sources that say sex is a spectrum, they're simply wrong.
Apparently you've never heard of people with intersex conditions.
> despite all evidence (and basic logic) showing that they are not
Sources?
Also, basic logic built upon faulty assumptions leads to faulty conclusions, no matter how correct your logic is or is not.
> children are not being given puberty blockers
Medical conditions that require puberty blockers are very rare and, at any given time, not every state has an individual with such a medical condition or such a treatment plan.
> The more you look into trans "science" the more you'll see none of it is even intellectually plausible
The more you write like that, the more you sound like a foolish human.
P.S.,
"Is it possible to control man’s mental evolution so as to make him proof against the psychoses of hate and destructiveness? Here I am thinking by no means only of the so-called uncultured masses. Experience proves that it is rather the so-called ‘Intelligentzia’ that is most apt to yield to these disastrous collective suggestions, since the intellectual has no direct contact with life in the raw, but encounters it in its easiest synthetic form—upon the printed page."
My pleasure, hopefully this answers your questions, but if not, I’ll check back to see if you ask a follow up question.
From the “Applications and Results” section towards the end of the paper:
“Figure 9 documents the energy consumption of the three images of Figure 8. Energy consumption is measured according to our energy model from Equation 1, using various grid sizes. The most prominent observation is the substantial energy savings achieved by colors chosen according to our continuous optimization approach. Across the different grid resolutions, we save on average 41 percentage of energy compared to using ColorBrewer colors.”
This is probably the right post to refer everyone to the Mastodon Server Covenant, which does bind the service provider to some level of consistency: https://joinmastodon.org/covenant
Right now I’m experimenting with using separate .plan files for tracking key instructions across domains like architecture and feature decisions.