richkuo

Composer 2.5 is really effective at some tasks, but doesn't do as well on higher complexity tasks from my own experience.

With that being said, Cursor Bench is nonetheless a fantastic gauge of LLM quality and performance. The most interesting outcome of Cursor Bench is Fable 5 to GPT 5.5, its almost a perfect continuous line. As of the report, Fable to GPT might be the new standard of agentic programming/building

I did my own rounds of tests for a lot of models.

I made multiple rounds of comparisons for issues in my open source project using Fable 5, GPT 5.5, Opus 4.8, and Composer 2.5

Made them work on various complexity issues

Here are the reports, i recommend using a Sonnet 5 or better model to summarize them because its quite a bit of information to consume across all the various tests: https://www.richkuo.com/#llm-battles

My takeaway from Composer 2.5 is that its better to use Opus or GPT for planning, and then Composer to build, use Opus/GPT to pr review, and have Composer fix findings, and loop that process. Incredibly token efficient, fast, and gets the same quality as if you worked the whole thing with Fable/Opus/GPT.

You can create your own, you get image credits on sign up, enough for two short stories or one long story.

this was meant for https://news.ycombinator.com/item?id=9905363

Google 'You dun goofed.'

Personally the 'if' conditional statement acts as a visual trigger.

It allows me to quickly recognize that something may or may not show up on the view.

I would prefer something along these lines:

  class ProfilePresenter < ::Presenter
    def with_experience?
      profile.has_experience? && profile.experience_public?
    end
  end

  <% if user_profile.with_experience? %>
    <p><strong>Experience:</strong> <%= user_profile.experience %></p>
  <% end %>

as someone learning iOS development - thank you

one of the funniest websites i've ever visited, not to mention an awesome topic!

I believe most internet users would like to be anonymous in real life as well.

This post sounds like an attempt to settle an argument - some of the issues you mentioned should be settled as a team. A poorly settled "You're wrong and I'm right" argument might lead to bigger and more serious disagreements down the road.

If it were me... stop what you're doing and sign some papers. Friendships tend to break when dealing with the potential for making a lot of money. Is your relationship worth a million dollars? Maybe. What about a $100 million dollars? You're friendship isn't going to hold up if what you are forecasting is true. (I'm sure Zuck has 'lost' a lot of friends)

Without much other information on your company, here are some considerations:

If you don't get your % split, would you still be as motivated? work as hard? be as involved? What about your partner? How will it affect your business?

Your partner has crazy connections - how has that helped your business? How will it help your business in the future? How come you haven't raised money yet? If you don't raise money, how else does a VC play in your business?

He's put in $80k, why don't you just give him $80k for 100% of the company?

What if you just up and left, would the company be able to continue without you? (aka are you reasonably replaceable?) What if you just took the code and left?

How will all of this play out with the rest of the team?

Just some food for thought. Good luck!

PS. Unless your designer is doing front-end dev, I feel like you are overpaying your designer.

This tutorial literally changed my life.

Props for making the best RoR tutorial available.

Thank you mhartl

Attention all vampires: They are on to us!

The irony is that Leaseweb's slogan is "reliable hosting"

Good reasoning here.

Might I add that LinkedIn has implemented the same stalker features that make it just as creepy as online dating websites...

Can you imagine if Facebook had a "who's been viewing your profile" page? It'd be gg.

Not to mention the NSA would be overloaded with 'suspicious activity'.

'scale, skew and rotate the sh out of any element'

win

Shirts.io logo uses the same image as the Stripe 'cloud' but inverted on the y-axis

They also have suspiciously similar UI/UX with similar color schemes. The random green sign up button mouse over is an obvious attempt at 'throwing you off' from the idea that the design was copied.

Every non-technical entrepreneur or co-founder needs to read this. Twice.

You would not believe how many non-technical people think that programming is a critical component to the problems they are trying to solve.

great post btw

In a general sense, this is natural design evolution - where Darwin's mutation and natural selection concepts can be applied (generally) to the evolution and advancement of good/effective design.

The windows phone likely took some of its design concepts from previous iOS and Android designs, and now iOS7 is 'evolving' the same way.

This (evolution) can be described as a recursive process: keep the things that work (natural selection), try something new (mutate) with the things that didn't work.

I would also like to note that I find iOS7's weather app design closely resembles Yahoo's weather app, more so than the Windows' phone.

"lets your biceps do the talking"

my biceps already do the talking

"22. Don’t die."

aka "Don't YOLO"

I suspect this is a possible case incomplete journalism.

"Rohit ... has been programming professionally for a decade" doesn't sound much like a "noob" to me

zyzz brah