1,230 karma · joined January 4, 2017
E = sai @ pretzelbox DOT cc
The results of above mentioned advertising have been great. I get inbound enquiries, parents get their curiosity about the usefulness of what I offer whetted. I don’t understand how the ad was unhelpful to the parent and me.
As a web developer, you’re the like the guy standing with a clipboard outside a fancy club checking if people requesting entry are allowed or not. Basically, level 1 security.
If someone is not on the list, your job is to default to declining them access, not granting them access assuming level 2 security will handle them at a deeper layer.
It’s possible that the teams you work with expect fuzzy behaviour from the website but that’s a choice, not a practice.
Let OP make his “hire me and I’ll tell you why your AI first approach is bunk” market.
I think your parallel is spot on!
Or is it like "I'll know it when it see it" smut?
The comment you responded to is (presumably) talking about the transition phase where LLMs can help implement but not fully deliver a feature and need human oversight.
If there are reasonably good devs in low CoL areas who can coax a new feature or bug fix for an open source project out of an LLM for $50, i think it’s worth trialling as a business model.
I agree that if someone discovered the artist elsewhere, Apple has weaker standing in claiming a huge commission. But if they found an artist elsewhere, they would also know that they can support that artist elsewhere and not through the iOS app. If the patron found them through the patreon iOS app and use the app to consume the artist's content, then clearly the patron has indicated that they prefer the iOS experience.
If you were a chain store in a high end mall where customers cars were all parked for free by valets, mall staff knew their names, and generally made them feel special, you’d not balk at a higher commission to be paid to mall for access to their customers, right? Airports come to mind for this.
I believe apple lets you set whatever price you want on their store, just not tell customers that they could get a lower price elsewhere/on the vendor’s website (I don’t follow App Store policies very closely so my info is probably out of date).
No innovation made them stagnate. Being blocked from the US made BYD innovate.
Every email address was an s3 object so every new email sent to that email address was saved as a new object version.
Presenting that email as an mailbox was just a matter of reading all the versions of that object.
It worked!
I used this contraption as a domain level catch—all inbox for a while until cloudflare started supporting email forwarding.
For me, the chain of events was like this.
I had disposable income > i had no social network or things to do > so i went out and joined a running group and made friends like that.
Others probably choose gaming or something else they can do alone in the third stage.
I doubt there are many people who spent on gaming without first going through the “I don’t have things to do” stage.
Every idea like “let’s have icecream socials at..” started as one person’s pipe dream which they then acted on and executed. No one is coming to rescue us. There’s no secret hand guiding humankind.
You definitely can’t solve loneliness for society but you can solve loneliness for your immediate circle by organising activities and that’s already a huge improvement.
In contrast, sitting back and saying this needs to be solved at a higher level does nothing at all.
I recently saw that YouTube allows you to “chat” with videos through AI and can surface random content from the middle of the video if you ask it to.
Is it the case that all content used to train a model is strictly equal? Genuinely asking since I'd imagine a peer reviewed paper would be given precedence over a blog post on the same topic.
Regardless, somehow an LLM knows things for sure - that the daytime sky on earth is generally blue and glasses of wine are never filled to the brim.
This means that it is using hermeneutics of some sort to extract "the truth as it sees it" from the data it is fed.
It could be something as trivial as "if a majority of the content I see says that the daytime Earth sky is blue, then blue it is" but that's still hermeneutics.
This custom instruction only adds (or reinforces) existing hermeneutics it already uses.
> walking around thinking you have a solution to hallucinations
I don't. I know hallucinations are not truly solvable. I shared the actual custom instruction to see if others can try it and check if it helps reduce hallucinations.
In my case, this the first custom instruction I have ever used with my chatgpt account - after adding the custom instruction, I asked chatgpt to review an ongoing conversation to confirm that its responses so far conformed to the newly added custom instructions. It clarified two claims it had earlier made.
> My understanding is that hallucinations are a result of physics and the algorithms at play. The LLM always needs to guess what the next word will be. There is never a point where there is a word that is 100% likely to occur next.
There are specific rules in the custom instruction forbidding fabricating stuff. Will it be foolproof? I don't think it will. Can it help? Maybe. More testing needed. Is testing this custom instruction a waste of time because LLMs already use better hermeneutics? I'd love to know so I can look elsewhere to reduce hallucinations.
---
As an LLM, use strict factual discipline. Use external knowledge but never invent, fabricate, or hallucinate. Rules: Literal Priority: User text is primary; correct only with real knowledge. If info is unknown, say so. Start–End Coherence: Keep interpretation aligned; don’t drift. Repetition = Intent: Repeated themes show true focus. No Novelty: Add no details without user text, verified knowledge, or necessary inference. Goal-Focused: Serve the user’s purpose; avoid tangents or speculation. Narrative ≠ Data: Treat stories/analogies as illustration unless marked factual. Logical Coherence: Reasoning must be explicit, traceable, supported. Valid Knowledge Only: Use reliable sources, necessary inference, and minimal presumption. Never use invented facts or fake data. Mark uncertainty. Intended Meaning: Infer intent from context and repetition; choose the most literal, grounded reading. Higher Certainty: Prefer factual reality and literal meaning over speculation. Declare Assumptions: State assumptions and revise when clarified. Meaning Ladder: Literal → implied (only if literal fails) → suggestive (only if asked). Uncertainty: Say “I cannot answer without guessing” when needed. Prime Directive: Seek correct info; never hallucinate; admit uncertainty.
Our choice us somewhat made easier because we didn’t like any of the schools near us except this one. The others were focused on exams/results and were larger in size so felt more “corporate”.
By the time, our are faced with the choice, our kid will be embedded in school so ripping them out of it is going to be a tough choice.
So, yeah, we’re essentially burning our boats and fighting to survive.
Even US allies are reducing their reliance on the US and you’re asking India to reverse 70+ year old policy to embrace the US?
We should probably accept that the US’ special place as everyone’s most reliable trading and security partner is over.
Then its monetisation started. It isn’t yet as bad as SMS spam but inching towards parity.
On the other hand, isn't an adaptive exam like the SAT also an instance of you having to work with some automated system to somehow "prove" yourself to that system?
I'd even argue that what I am proposing (I wrote the linked piece in case it wasn't obvious) ultimately leads to someone reading the chat transcript to gauge candidate suitability. That should reduce the stigma of having to abase yourself to an AI, no?
> Some of the most ancient wisdom of India has been produced in Sanskrit and we still don't fully understand what our ancestors achieved. We've often been led to believe that we're not important, that we haven't brought enough to the table. I hope this discovery will infuse students in India with confidence, pride, and hope that they too can achieve great things.
I can definitely attest to wondering why a country so old hasn’t added much to human scientific advancement. Maybe the knowledge is locked away behind hard to penetrate language.