roveo

My experience with greenfield is that when you're just starting out, you have to be really strict and careful about overall architecture, establish a framework, provide structure, separate concerns well.

If the project is not throwaway, this first set of iterations is critical, without guidance LLMs will just bolt on things and produce special-cased spaghetti, even the very-frontier models.

Once the framework is established, it's smooth sailing.

But I haven't gotten to "very large" size yet, I expect it produces another kind of coherence problems.

HN is essentially the only news source that I consume in addition to local news that are likely to have stories that do affect me personally.

When I stopped reading X, I had this thought one morning:

> The political crisis, the bloody war, the looming apocalypse only exist to distract you from the fact that you didn't fold the laundry.

The longer I live news-free, the more I find it true.

I'm using eigenrobot's (X user) prompt for ChatGPT and the style is very recognizable. Everything lowercase, tone, zoomer abbreviations, esotheric style of jokes.

Telegram wasn't fully blocked in Russia even for a single day. They tried to block it and failed miserably. The team actively circumvented the blocking by deploying to new IPs faster than they were blocked, and in addition to that every IT guy in Russia had a tgproxy instance running for family and friends.

After a while they just stopped trying and decided that it's less reputational damage to just let it be.

> GPT4 alone will especially not be that useful for analytical work. However, developers can make it a semi-capable analyst for some use cases by connecting it to data lakes, describing schemas, and giving it tools to do analysis. Usually this is not a generalist solution, and needs to be built for each company's application.

I've been thinking about this a lot lately. I'm a data analyst and all these "give GPT you data warehouse schema, let it generate SQL to answer user's queries" products completely miss the point. An analyst has value as a curator of organizational knowledge, not translator from "business" to SQL. Things like knowing that when a product manager asks us for revenue/gmv, we exclude canceled orders, but include purchases made with bonus currency or promo codes.

Things like this are not documented and are decided during meetings and in Slack chats. So my idea is that in order to make LLMs truly useful, we'll create "hybrid" programming languages that are half-written by humans, and the part that's written by LLMs when translating from "human" language is simple enough for LLMs to do it reliably. I even made some weekend-prototypes with pretty interesting results.

Thank you for your game, kind stranger, I've just wasted my day.

You can edit any of your messages in ChatGPT and the chat will start from there. Not quite branching, because you will lose the old "branch".

Oh, I recently moved to Israel, and at first was shocked with how much worse design in general is. Like, typography, ads and of course UI. There are maybe 3-4 common fonts used everywhere, and I think it's a common problem for "rare" scripts. It seems you need some "critical mass" of visual content to come up with good design practices and figure out what looks good in your cultural landscape.

I imagine this word should be of Indoeuropean origin, Eastern Slav words for a mill also contain m-l-n (e.g. melnitsa).

Modern English lost the "n" part, but it was present in Middle English, milne.

I did the same thing, but also mapped Caps Lock to Cmd+Shift+Ctrl+Option (so-called Super key) when it's pressed together with another key. Useful for application switching and other custom stuff.

Oh, I actually received such a call from a government-funded polling agency while still in Russia. Told them everything I think about it (which was still somewhat difficult despite the fact that the actual risks were low), but some questions were tricky to answer in such a way that actually reflects my opinion, e.g. something like "do you think our army is succeeding in defeating the nationalist batallions in Ukraine and protecting the people of Donbas?" Yes/No/Refuse_answer

A better idea would be to use custom inputs that produce "typos" that the user didn't make. E.g. you have a "zip/postal" code field and your input sneakily swaps 2 neighbouring characters at some point, resulting in error "this zip code doesn't exist". Or change 8 to 9 etc.

Or you could make a "check your input one more time before confirming" step and display typos in e.g. names/emails there.

There's another thing that was different at Euromaidan vs current Russia: Yanukovich and his people had somewhere to run (Russia). Putin doesn't.

Also Estonia isn't a prime destination for Russians in this situation. Countries that don't require a visa are. Yesterday 42 passenger planes landed in Yerevan (Armenia), normal number being 3-4 daily.