joduplessis

This feels like a stupid investment given it's autocratic quasi-religious undertones, on top of diminishing product differentiation.

You deserve an upvote - if only to base it in reality.

There isn't a difference there in my experience. That "eye" is the taste, and before you start studying/practicing/training/doing - most of the time you won't know the "why it works" either. I'm not sure what "vulgar taste" would be.

This article is filled with pseudo self-help advice for people who now think they need taste to level-up their the LLM skills.

> it’s a trained instinct. The ability to see beyond the obvious and recognize what elevates. It’s why some designs feel effortless.

This is not really what "taste" is.

Some designs feel effortless because someone practiced/trained so they could execute on their taste. Taste is extremely cheap - execution is still very hard.

That's a load-bearing statement.

Sol is so good, honestly - the sweet spot for me. I've only ever found it stumbles when you don't give enough direction. But for idea execution - Sol is the GOAT.

Ah, I miss the days of NoSQL vs. SQL debates.

Same. Sol was actually the reason I upgraded my plan to the $100 one. Hoping GPT-6 Sol is the same.

It is strange how people who say they are "often wrong", never quite sound like they take that into consideration when delivering opinions or thought pieces - I see it fairly often in tech. Anyways; nothing against Boris, but Anthropic/Claude has certainly been the first company (& product) too annoying for me to use.

Microsoft executives levelling "tone-deaf" up in realtime.

I've come to utterly hate conversing with Claude. I don't care if it's right or wrong, my job is challenging enough - I don't need a tool (that's meant to help) making my life harder. I think I've mentioned this as well - but turns out a lot of the AI fatigue came from having to digest Claude's monologues - because that shit ain't meant to be read by humans.

This doesn't seem to be a big issue with Codex. Claude, yes - I have from time to time said "ffs one liner please".

Anthropic, the company employing "treat them mean, keep them keen" as a marketing tactic. Pass.

And are the agents argumentative and condescending I'm wondering.

I think, if the bubble pops, LLM assisted coding is here to stay. It's novel & useful enough to offer a real advantage, but can also be misused easily by folks who think software is now "solved" obviously. Either way - the middle ground is the sweet spot, and I think you're probably just looking at the disappearance of the bottom layer: grunt work, templates, straightforward SaaS apps, tooling, utils, etc. Job-wise though, I think juniors & interns are the ones who's caught in the storm unfortunately.

Sir, why would I put on a "radio" when I've got a perfectly healthy pigeon, readied and waiting?

Bro!? I did. But I said 4.6 dude.

You're absolutely right. There are no other models out there for coding.

This is super exciting for fast message delivery.

I'm so tired of my messages taking 2 weeks to deliver! 3000km shouldn't take that long! Personally I'm really looking forward to a world where my message can take maybe even a week to deliver to someone 2000km - 3000km away. What a time to be alive.

It's an interesting conversation - because at what point do you call it an abusive relationship, right? Maybe even ancillary to anthropomorphising an inanimate object - I've cancelled my Claude sub and I've shot question after question at it now (during the cancellation period), resulting in almost every reply with me asking it to "please speak normally". I will most definitely not be renewing my sub. I have no desire to engage with a non-human somehow managing to speak down to you, without answering the question.

EDIT: my honest opinion; Anthropic is building a person, whereas everybody else (it seems) is building a tool.

Plenty for coding - Sol, K3, new DeepSeek & Qwen, GLM 5.3, Grok 4.6, etc.

Just stop using Claude. There are so many other better models right now.

I've never wanted to punch a meta physical entity in the face more, than I do Claude. I realised a lot of the AI context fatigue was from having to try and comprehend the absolute ridiculous wording. I cancelled my sub a while back (obviously).

My wife and I lived in Hamburg for a few years. Nice place and I often miss our lives there. However, I know many other foreigners do not share this experience - even I had to get used to people being hostile to someone stumbling through German. Ultimately we found happiness was being back home (SA) where things were a bit harder, but "nicer".

Surprisingly I've found some stigma attached to it - because people can get "preachy" about exercise I guess.

This looks remarkably dystopian.

It is, of course, wild that people are saying "just use a VPN"... in the context of the UK.

I really wish seemingly intelligent people would stop using the abstraction analogy (like the article does). The key word is: determinism. Every level of abstraction (inc. power tools, C, etc.) added a deterministic layer you can rely on to more effectively do whatever it is that you're doing - same result, every time. LLM's use natural language to describe programming and the result is varied at the very best (hence agents, so we can brute force the result instead). I think the real moat is becoming the person who can actually still program.

Spotify DJ is terrible - just like their Apple TV app (which is perpetually buggy). However, their radio mix feature is so good that it's become the #1 reason I can't switch.

Quadruple espresso + some good deathcore solves this pretty nicely for me.