Earlier quoted context omitted.
Reread the blog post, and I suspect Cursor will remain much more competitive on pricing! No specifics, but likely far exceeding typical Cursor costs for a typical developer. Maybe it's worth it, though? Look forward to trying. >Claude Code consumes tokens for each interaction. Typical usage costs range from $5-10 per developer per day, but can exceed $100 per hour during intensive use.
> Reread the blog post, and I suspect Cursor will remain much more competitive on pricing! Until Cursor burns through their funding and gives up or increases their price.
Claude 3.7 Sonnet and Claude Code
741–750 of 1001 posts
Re: Claude 3.7 Sonnet and Claude Code
#742Earlier quoted context omitted.
Hey there! I’m a fellow Qt developer and I really like your takes. Would you like to connect? My socials are on my profile.
We’ve already connected! Last year I think, because I was interested in your experience building a block editor (this was before your blog post on the topic). I’ve been meaning to reconnect for a few weeks now but family life keeps getting in the way - just like it keeps getting in the way of my implementing that block editor :) I especially want to publish and send you the code for that inspector class and selector…
From time to time I'm fooling with the idea of open sourcing the core block editor but I don't really get into it since 1. I'm a little embarrassed by the current unmodularization of the code and want to refactor it all. 2. I want to still find a way to monetize my open source projects (so maybe AGPL with commercial license?)
Dude, that inspector looks so cool. Can't wait to try it. Do you think it can also show how much memory each QML component is taking?
I'm hyped as well about Claude 3.7, haven't had the time to play with it on my Qt C++ projects yet but will do it soon.
Re: Claude 3.7 Sonnet and Claude Code
#743You can get your HN profile analyzed by it and it's pretty funny :) https://hn-wrapped.kadoa.com/ I'm using this to test the humor of new models.
> A cryptography enthusiast who created Coze and spends their days defending proper base encoding practices while reminding everyone about the forgotten 33rd ASCII control character. The nerd humor was hilariously unexpected. > Your deep dives into quantum mechanics will lead you to publish a paper reconciling quantum eraser experiments with your cryptographic work, confusing physicists and cryptographers alike. That…
Re: Claude 3.7 Sonnet and Claude Code
#744Is it just me who get the feeling that Claude 3.7 is worse than 3.5? I really like 3.5 and can be productive with it, but with Claude 3.7 it can't fix even simple things. Last night I sat for 30 minutes just to try to get the new model to remove a instructions section from a Next.js page. It was an isolated component on the page named InstructionsComponent. Failed non-stop, didn't matter what I did, it could not do i…
Re: Claude 3.7 Sonnet and Claude Code
#745Earlier quoted context omitted.
This test has always been so stupid since models work at the token level. Claude 3.5 already 5xs your frontend dev speed but people still say "hurr durr it can't count strawberry" as if that's a useful problem
“Already 5xs” Even AI marketing doesn’t claim this. Totally baseless claim given how many people report negative experiences trying to use AI.
Re: Claude 3.7 Sonnet and Claude Code
#746Earlier quoted context omitted.
It seems to be slowing down actually. Last year was wild until around llama 3. The latest improvements are relatively small. Even the reasoning models are a small improvement over explicit planning with agents that we could already do before - it's just nicely wrapped and slightly tuned for that purpose. Deepseek did some serious efficiency improvements, but not so much user-visible things. So I'd say that the AI rac…
While I agree, you have to remember the dimensionality of the labor-skill space is. The was I see it is that you can imagine the capability of AI as a radius, and the amount of tasks it can cover is a sphere. Linear imporovements in performance causes cubic (or whatever the labor-skill dimensionality is) imporvement in task coverage.
Re: Claude 3.7 Sonnet and Claude Code
#747Earlier quoted context omitted.
Be glad that you are empowered to pivot - I'm making the assumption you are still young being a student. In a disrupted industry you either want to be young (time to change out of it) or old (50+) - can retire with enough savings. The middle age people (say 15-25 years in the industry; your 35-50 yr olds) are most in trouble depending on the domain they are in. For all the "friendly" marketing IMO they are targeting…
Not enough resources to get another bachelors, and a masters is probably practically worthless for a pivot. I would have to throw away the past 10 years of my life, start from scratch, with zero ideas for any real skill-developing projects since I'm not interested at all. Probably a completely non-viable candidate in anything I would choose. Maybe only Robotics would work, and that's probably going to be solved quick…
You can definitely succumb to the fear. It sounds like you have. But courage isn't the absence of fear, it's what you do in the face of it. Are you going to let that fear paralyze you into inaction? Just not do anything other than post about being scared to the Internet? Or, having identified that fear, are you gonna wrestle it down to the ground and either choose to retrain into anything else and start from near zero, but it'll be something not programming that you believe isn't right about to be automated away, or dive in deeper, and get a masters in AI and learn all of the math behind LLMs and be an ML expert that trains the AI. That jobs not going away, there's still a ton of techniques to be discovered/invented and all of the niches to be discovered. Fine-tuning an existing LLM to be better at some niche is gonna be hot for a while.
You're lucky, you're in a position to be able to go for a masters, even if you don't choose that route. Others with a similar doomer mindset have it worse, being too old and not in a position to them consider doing a masters.
Face the fear and look into the future with eyes wide open. Decide to go into chicken farming or nursing or firefighter or aircraft mechanic or mortician or locksmith or beekeeping or actuary.
Re: Claude 3.7 Sonnet and Claude Code
#748Re: Claude 3.7 Sonnet and Claude Code
#749My experience is that these models could write a simple function and get it right if it does not require any out of the box thinking (so essentially offloading the boilerplate part of coding). When it comes to think creatively and have a much better solution to a specific task that would require the think 2-3 steps ahead than they are not suitable.
Re: Claude 3.7 Sonnet and Claude Code
#750Earlier quoted context omitted.
But also for $36.83 compared to DeepSeek R1 + claude-3-5 it's $13.29 and for latter "Percent using correct edit format" is 100% vs 97.8% for 3.7. edit: would be interesting to see how combo DeepSeek R1 + claude-3-7 performs.
is there any public info on why such DeepSeek R1 + claude-3-5 combo worked better than using a single model?