Personally tried GLM subscription. Bought it during new years discount: 36$ for a YEAR.
Cannot burn tokens through with personal project use. From what I can see in stats they allow 25-100M tokens in 5h period (for cheapest plan), depending on the model. GLM5.1 could be a bit slower and likes to (over)think, but I don't see practical differences from Sonnet 4.6 or Opus 4.6.
> I refuse to give Altman money, but Anthropic keeps disappointing me over and over with crap like this. Gemini seems behind? Not touching Grok.
My thought process is totally the same. And even there's slight concern about ethics using GLM, at least in my conciousness, openai is worse and grok is the worst of them all by far, no competition.
Personally I don't hate tab. Sometimes even it's more convenient to have a tab on the side with all the state, instead of reopening modal.
What I hate though is really unintuitive and "non-standard"[1] shortcuts in search tab.
For example "find in project": cmd+shift+f
Whereas for "find and replace in project" I'd expect: cmd+shift+r , but it's: first toggle find, then toggle find and replace. Ok, absolutely fine, but the keyboard shortcut to toggle is: cmd+shift+h - I never can remember it.
When already searching, for my "convenience", if I'd like to adjust my search or search for something new, I click cmd+shift+f and I am focused back to find input, but here's the kicker. Input have automatically changed to what word was under my cursor. So if I was looking for some long or weird string, I need to retype it again or find and copy/paste it again.
#first-world-problems though.
I got tired of babysitting vim/neovim and all it's plugins and use Zed for most of my editing. It has pretty good vim binding support and maybe I just need to remap some key bindings to have better search experience. Zed is much better at emulating vim than Cursor/VSCode.
[1] there's no standard obviously, but some things are the same/similar across most programs.
They have presets from other IDEs and editors. I use a weird combination of Jetbrains and helix shortcuts with helix mode. Because I used them the most.
I was like: "it should be Ctrl+Shift+H, of course, right?"
So different tastes :-)
What you describe later is "Auto-populate the find dialog with current text under cursor". VSCode has a setting for that; I guess Zed will eventually end upnadeing one too.
IMHO you're shifting goal posts (and I am not downvoting).
Tesla (or probably mostly Elon) was not selling "adaptive cruise control". It's selling "Autopilot" for $8k (now with a subscription AFAIK), with a pinky promise that "soon" or "next year" or "after two weeks" (jk) you essentially will set a destination, go to sleep and wake up at destination[1].
It's same as saying that "LLM != AI" and arguing that "ChatGPT is not AI - it's a glorified statistics model that is good at creating human sounding texts". Yeah - you and I understand this - but the average guy most likely does not and will get burned by this, because dozen tech-bros are burning billions of dollars and try to convince everyone that it's a panacea to every problem you can think of.
[1] It's a slight exageration, though I won't spend time digging for quotes but my main point is that's what Tesla are selling to an average guy and not nerds who can distinguish on what's possible, what's working and what level of driving assist there are.
"Autopilot" is not $8K, that's FSD. Autopilot was the default cruise control/lane keep software and was renamed "Traffic Aware Cruise Control" a few months ago. The original name was ridiculously misleading.
From my short experience with this - manufacturers want to ensure this internationally too. So then same product would cost around the same in Germany and in Poland. Otherwise Germans will check fit of shoes in German B&M store, then go buy it online from some Polish store for X% cheaper.
Manufacturer does not want that, because then it will lose most of it's distributors in Germany.
NB: Though I am not debating if it's right, fair or best for consumer. Just mentioning, what I've experienced.
> <...> even though that someone never did something against them, <...>
Many tech billionaires openly, publicly and loudly said something among the lines: "I/we/my company/tech-bros are building torment nexus - it will take your job and/or kill people and/or shut up political opponents. You are powerless to stop this."
There are some of those billionaires willing to put their name and face in front of billions of people in the world. You will have no trouble finding people that will think that X or Y tech bro is personally responsible for some poor persons problems.
Especially when there's a bunch of news like "layoffs due to AI", "record investments due to AI", etc.
I am not supporting violence, never done it and never considered it. Though not surprising when talking heads of political/economical extremes can get threats from people that have nothing to lose.
Personally tried GLM subscription. Bought it during new years discount: 36$ for a YEAR.
Cannot burn tokens through with personal project use. From what I can see in stats they allow 25-100M tokens in 5h period (for cheapest plan), depending on the model. GLM5.1 could be a bit slower and likes to (over)think, but I don't see practical differences from Sonnet 4.6 or Opus 4.6.
> I refuse to give Altman money, but Anthropic keeps disappointing me over and over with crap like this. Gemini seems behind? Not touching Grok.
My thought process is totally the same. And even there's slight concern about ethics using GLM, at least in my conciousness, openai is worse and grok is the worst of them all by far, no competition.
reply