HN user

trio8453

58 karma
Posts1
Comments28
View on HN

prompting very small tasks after you have made the initial design, something along the lines of "Create a database migration that adds column [x], not null", "add a field to the this form that will accept string value, validate it on the backend against this format, and save it to column [x]". So basically, writing code in plain English.

Are you presenting this as the option that allows you to have better understanding (smaller tasks, closer to the changes), or the option with which you don't have understanding (because you're still getting assistance, not solving every problem on your own and not typing the code out yourself)? I genuinely can't tell from your post, people can and do take both of these positions.

I will lose the ability to think about code and understand code

If you lose it (whatever "it" is), it's because you don't use it. If you don't use it but you're still getting your job done, is that really a loss?

GPT seems to be designed more as a tool. If you want your agent to do what you say without questions and without having its own ideas and agendas you’ll likely prefer it.

Lately ChatGPT expresses a lot of opinions and it pretends to be a human more than it used to - e.g. "this is one the most <> that _I've seen_" or "people tell me that <>". It uses language which sounds like it's referring to its experience outside of the session that we're having - I really don't appreciate it.

Not quite a "successful treatment":

This case documents transient multidomain functional improvement in advanced Alzheimer’s disease following psilocybin administration. The findings do not imply disease reversal but suggest that residual functional capacity may persist in late-stage neurodegeneration and may become transiently accessible under specific neuromodulatory conditions.

Very interesting nonetheless.

One month after the initial session, the patient remained continent and functionally improved compared with baseline. A second supervised psilocybin session using 3 g was subsequently performed and was associated with greater verbal expressivity, improved facial mimicry, spontaneous humor, emotionally valenced autobiographical imagery, and increased agility while walking.

The patient spontaneously stated: “It is pleasant to come here.

This is just wonderful.

So true. One of the smartest animals being treated in the worst possible way. You can't even justify it with some nutritional or health argument - there's nothing essential in pork that humans can't get from other sources. It's cruelty and torture that's happening out of habit, out of people being stubborn and not wanting to go without a taste they're familiar with.

I'm Done Using AI 2 months ago

You should probably adjust how you work and find a workflow that feels ok to you instead of abandoning it completely.

Finished episodes buzzing with ideas and forgot everything within 48 hours.

Write them down?

For me, podcasts are for entertainment and exposure to ideas, not for learning that needs to retained. Otherwise it becomes yet another thing that you ruin the enjoyment of by trying to squeeze out the max value from it.

But if you are getting interesting ideas, writing them down to process later seems like a very obvious thing to do.

Not quite - English might be the interface but knowing English isn't enough to understand what's happening, what to ask for, how to verify and guide the output.

Do you really think your line helps? It seems like very basic stuff that's already built into it.

I don't use Claude/agents files - I can point each session to the readme/docs which summarize the project, it's linters/checkers/scripts, how to run tests etc. It's shared humans/bots documentation. The rest seems too session-specific to codify.

I'm not saying these files are never necessary, they seem to fit well in some projects and some people's workflows (at least for the current models, newer models will likely make them obsolete) but yours honestly seems completely redundant - you're prompting a 2026 coding assistant as if you're talking to a 2023 version of ChatGPT.

No, it isn't.

1. The videos we have make it very obvious that he was murdered without any justification.

2. People who claim that he wasn't don't care about evidence. Even more, they're inclined towards conspiracies and a complex tool that edits video will only add more supicion, more things to quibble about. It wouldn't clarify anything, it would just muddy the waters more.

Who do you think you're going to convince and of what? I don't get how you can look at what happened and think "do you know what we need? - an obscure peace of complex video editing technology, that will sort this out".

Makes sense for the free tier, sucks to include ads in a paid tier though. Not sure who the target audience for the Go subscription is anyway, they might be better off removing it purely from a product point of view.

What matters most:

- Responses in ChatGPT will not be influenced by ads.

- Ads are always separate and clearly labeled.

- Your conversations are private from advertisers.

The part that's left out is that you'll obviously be profiled as an user and get targeted ads based on your chat history.

1. Get assessed by a psychiatrist for ADHD.

2. If you're diagnosed, start medication and see if it works for you - it's by far the intervention with most evidence behind it for alleviating ADHD symptoms. It's not for everyone but for many of the people it helps starting medication is an absolutely life changing decision in the best possible way.

affects shell startup time

You'll never get back those milliseconds. Just like I can't get back the time I wasted reading this article.

This results in the somewhat unintuitive combination of a technology that can be very useful and impressive, while simultaneously being fundamentally unsatisfying and disappointing

Useful = great. We've made incredible progress in the past 3-5 years.

The people who are disappointed have their standards and expectations set at "science fiction".