this maybe? https://liveswebench.ai/

I don't think you really want to boil this down to a number; there's a whole lot of feature and workflow differences to capture:

* BYO model or not

* CLI, UI, VSC-plugin or web

* async/sync

* MCP support

* context size

* indexed or live grep-style search

There's probably like 10 more.

I don't think it's being kept up to date. I believe for the IDEs, it requires manual testing to get the numbers. Since things change so quickly, it's mostly just a historical artifact. Hopefully some future version is automated.

Never heard SWE-agent until now, and seems to beat Aider (the tool I use) consistently.

Does anyone know if it's GitHub-only or can it be used as a CLI (i.e., Aider replacement)?

Heh, the irony doesn't escape me https://github.com/SWE-agent/SWE-agent/tree/v1.1.0/.cursor/r...

Anyway https://github.com/SWE-agent/SWE-agent/blob/v1.1.0/docs/usag... and https://github.com/SWE-agent/SWE-agent/blob/v1.1.0/docs/conf...

looks useful. thanks

If you are curious, here is how you can integrate it into a Jetbrains IDE: https://glyphy.com/a/2022/structural-diff-with-difftastic-an...

I tried it, but unfortunately it's not as seamless as it could be, so I reverted back to Jetbrain's native diffing, which is quite good anyway.

> You're effectively attempting to bully people out of their own opinions for the sake of your convenience.

Maybe it's just me, but "bully" seems like a very exaggerated choice of words here.

it now uses bing to perform searches. so i think he is probably correct to assume that it did that. it would show up as „performing search with bing“ in the chat history.

Even before it could search online it would hallucinate checking things online. You could ask it to email you something or upload it somewhere and it'd also hallucinate thinking it did it for you. Changing its mind is always easy as long as you pretend to give it a source that refutes it.

i’ve been using https://www.brain.fm for years now. when i really want to get stuff done, i put on headphones, play something from that website and set a timer for one hour. Then i take a break. repeat two or three times. Then take longer break.

not affiliated with the product. just a fan.

Very well put. I love the metaphors, especially the "microwave going bing" :D

Just curious: Where would you put "gather input or feedback from peers" in that process?

I don't think that is part of this process. It's certainly part of engineering, but not this side of creative problem solving. This is way off in the deep end. I guess it may be part of early phase 1 in the sense of immersing myself in the problem space, but often I don't know even know what problem I'm solving. Like, not really know it.

The moment of clarity is when the question is revealed and the answer is obvious. It's a real parting of the clouds moment.

That's step 4.

Generally (for me, anyway) the insight is still pretty unformed. Peer input helps refine that idea into something more concise and actionable.

It's not always required, but it is always beneficial.

Part 1, and after part 3

hasn’t the blue light thing been debunked recently? i remember reading a headline about this a while ago

Control. It’s a bit weird but a great game with a really nice atmosphere.

I recommend Control to everyone I can.

Stunning game, weird as. There is a... sequence... towards the end that is in my Top 3 gaming moments ever. Probably even Top 2.

Sounds a bit cliché but Control opened a creative doorway in my mind that I didn't know was there, and now I spend a lot of time trying to find more things like it.

don’t want to spoil anything but do you mean the one with the music?

I do indeed.

Although I thought about it a bit more, and I'm a sucker for the storytelling trope they use a little bit after that, which means Control probably takes 2 out of the Top 5 moments :)

Making Sense with Sam Harris. There are so many good podcast episodes. If you don’t like the first one you listen to, browse the list of episodes. There’s a ton of evergreens.