I'm impressed by how many people who are working with Claude Code seem to have never heard of its open source inspiration, aider: https://aider.chat/
It's exactly what Yegge describes. It runs in the terminal, offering a retro vision of the most futuristic thing you can possibly be doing today. But that's been true since the command line was born.
But it's more than Claude Code, in that it's backend LLM agnostic. Although sonnet 3.7 with thinking _is_ killing the competition, you're not limited to it, and switching to another model or API provider is trivial, and something you might do many times a day even in your pursuit of code that vibes.
I've been a vim and emacs person. But now I'm neither. I never open an editor except in total desperation. I'm an aider person now. Just as overwhelmingly addicted to it as Yegge is to Claude Code. May the future tooling we use be open source and ever more powerful.
edit: Another major benefit of aider is its deep integration with git. It's not "LLM plus coding" it's really like an interface between any LLM (or LLMs), git, and your computer. When things go wrong, I git branch, reset to a working commit, and continue exploring.
maybe my settings were off but i tried aider when it first came out and kept coming back to it and it ended up being super slow and generating subpar stuff compared to just chat. actually turned me off to CLI based style code assistants.
claude code blew my mind, however. really great for refactoring existing stuff with a proper CLAUDE.md file or one-shotting small features. i mainly use it for scaffolding, sounding board and refactoring but it's been a game changer (albeit more expensive).
still like to use boring chat-based and pasting back and forth as it helps me approach and understand issues better for later on. i find generating huge blocks of code/files to feel like magic but then u dig into a bug later and find the LLM wrote or structured a bunch of semi-garbage that you have to undo.
> i tried aider when it first came out and kept coming back to it and it ended up being super slow and generating subpar stuff
I had very similar results. I discovered Aider & Claude-code at the same time. I even tried Aider with Claude 3.7 (with thinking), and it just wasn't as good. I think it's a lot more annoying to use and set up, a bit more conservative in how it tries to understand your project, where claude-code has no problems scanning your entire codebase.
> still like to use boring chat-based and pasting back and forth as it helps me approach and understand issues better for later on. i find generating huge blocks of code/files to feel like magic but then u dig into a bug later and find the LLM wrote or structured a bunch of semi-garbage that you have to undo
Same. When an LLM generates code in a simple chat, it's always a bit more abstract, which is a good thing. Some of the things claude-code generated turned out to be garbage.
Aider does scan your entire codebase. What did you try to do that didn't work?
A typical workflow for me involves developing a plan document using copy/paste from the command line into a (cheap/fixed cost) webui and discussing it with the AI. Then, the result gets pasted back into aider to implement the changes in code. Aider, for me, mostly replaces the text editor, and the mindless process of squashing compilation and test bugs.
Do you happen to know how they compare in actual usage? Steve Yegge is gushing proudly, so it makes me wonder if, while of course aider and CC are of the same rough variety of tool, Claude Code is way better at something, or a little better at a few things, or something that's causing him to be so excited, and makes me wonder if aider is quite "up there" with Claude Code at doing those things.
I guess what I'm saying is, if Steve Yegge tried aider would he gush about it the same way?
I've spent more on Claude Code than I'm willing to admit, and I'd estimate about 50% of the spend is "written off". With CC it can be tough to judge when to stop on a particular path.
Prior to CC I was using Goose, which is similar - and it's hard to tell how much better CC it than Goose as Sonnet 3.7 was released at the same time I switched. One of the nice features of Goose that CC doesn't have is loadable history/resumable sessions.
The workflow I've actually found most effective (and cheaper) now is to use the GitHub integration in the Claude.ai to get started, then use Claude Code to fill in the bits. The GH integration is much better than I expected, and worth a try if you have a Claude plan.
Claude code is surprisingly good. It's easily another 2x speed up over my previous AI enabled software development (copilot + chatgpt).
It's not a replacement for a SWE today, but it allows a SWE to get a lot more done.
I feel the current system is constrained in 2 dimensions: overall integration ( writing a feature and then using/testing it to make sure all the relevant cases are covered) and still limited context ( in a bigger code base there are utility functions and conventions that it doesn't always follow and so it introduces subtle bugs).
However, it's not like a new software engineer would get all of these things right as well.
The future of coding seems really to be a lot more review and test based vs. hand crafting all the details. That being said, you should keep your eye on what makes your app unique. Chances are high that it doesn't get these things right without enough guidance.
I have been throwing it on to our codebase last couple of days.
I found it to be good in reviewing code. I ask it to check if we missed anything. If the diff is sound etc. Works really good. Caught a couple of issues and provided decent feedback.
I asked it to implement new things and.. I’m not sure. Depends on what you are working on I guess but it did “fine” overall. I’d need to provide feedback, ask it to consider some other stuff etc. Overall it was like steering an extremely intelligent junior developer. Not that revolutionary.
I don’t know how people actually utilise these though. Maybe I’m doing it wrong.
See, by intellectual accountability, I mean when someone provides a total lack of support for their position. World leaders are now actively acting and speaking as if this is a possibility: https://www.youtube.com/watch?v=egGm4Od5rp0
This talking head guy is just saying stuff to make you angry and click his videos. He doesn't actually know anything. Editing together a montage of clickbait/ragebait headlines from left-liberal media outlets and talking over it isn't an argument.
Let's go through:
>former ally Canada
Still allies. Not a former ally. First lie of the video.
>Trudeau said X, Y, Z
Saying things isn't the same as believing them. Trudeau doesn't believe any of what he is saying here, he is trying to rally support from his support base because the Liberals are likely to lose the next election. He is trying to stoke a "rally around the flag" effect.
Guy talks over a story entitled "The inside story of a high-stakes call between Justin Trudeau and Donald Trump as the tariff deadline loomed". Subtitle is that Justin Trudeau "revealed" some details "behind closed doors". Why should I trust this guy's interpretation of a paywalled article about some journalist's impressions of some Trudeau advisor's impressions of Trudeau's claimed experience on a call with Trump? That's four levels of people with an incentive to spin the story.
Then it is a NY Times article about Trump challenging some border arrangements with Canada about water access. How is this an indication he wants to annex Canada? It is absurd.
Trump allegedly said he didn't think "the treaty that demarcates the border between the United States and Canada" is valid? More likely he wants to do exactly what he said: renegotiate the arrangements between the US and Canada about how the border and shared water resources are managed.
The guy goes on to say Trudeau got caught on a hot mic. Lol. No politician gets caught on a hot mic in 2025 just by chance right in the middle of a political issue like this. It was very obviously staged like all these other so-called hot mic incidents. He wants to dispel the obvious notion that he is just playing this up to try to win the election.
This guy has no idea what he is talking about. He seems to think NATO isn't fully functional? Why would Trump be so resistant to giving security guarantees and NATO membership to Ukraine if he didn't think holding to security guarantees like NATO was important?
This guy wants this all to be a big deal. It isn't.
It isn't, which is why non-US NATO leaders have been scrambling recently to build new security arrangements.
> Why would Trump be so resistant to giving security guarantees and NATO membership to Ukraine if he didn't think holding to security guarantees like NATO was important?
Donald Trump unilaterally abandoning the NATO-wide commitment (announced in a joint communiqué of NATO Heads of State on February 25 immediately following North Atlantic Council consultations held under Article 4 of the Washington Treaty) on Ukraine [0] is major reason why NATO has become non-functional, with NATO allies, most especially those on NATO’s eastern flank who have been most adamant about Russia’s unchecked aggression against its neighbors posing an existential threat, distrusting American commitment and seeing the US as a threat rather than a reliable ally.
[0] “...We will continue to provide political and practical support to Ukraine as it continues to defend itself and call on others to do the same. We reaffirm our unwavering support for the independence, sovereignty and territorial integrity of Ukraine within its internationally recognised borders, including its territorial waters. This principled position will never change.”
Alright, you want to talk line by line, we'll talk line by line. Before we begin, let's just put a blanket statement over how poorly you support your argument: All you are doing is showing how head-in-the-sand you are.
> This talking head guy is just saying stuff to make you angry and click his videos.
This is obviously false, and I could easily say the same thing about you and your sources, except you haven't provided any.
> Editing together a montage of clickbait/ragebait headlines from left-liberal media outlets and talking over it isn't an argument.
Blanket denial sprinkled with lies isn't an argument either. He at least explains why he thinks something, provides support for his position and is willing to admit he's wrong.
> Still allies. Not a former ally. First lie of the video.
If you continue deny that our relationship is becoming strained, given Ontario just put 25% tax increase on electricity exported to the US, and we've countered by upping the tariffs to 50% as of an hour ago, I'm just going to tell you to go back to 8kun.
Furthermore, you seem to be working a very specific (and given your previous behavior), weasel-y definition of 'ally' that I'm not interested in arguing. When you set aside the word games, it becomes obvious that the USA is making policy moves that will hurt Canada and Canadians, and that is notably less ally-like behavior than anytime in my life, or yours.
> Saying things isn't the same as believing them.
Yeah it seems pretty clear you don't believe the nonsense you're saying. you'd argue in better faith if it weren't the case.
> Trudeau doesn't believe any of what he is saying here,
Unprovable.
> he is trying to rally support from his support base because the Liberals are likely to lose the next election.
I think this community should take anyone making claims like "Liberals are likely to lose the next election" with a grain of salt the size of an iceberg. Politics is more complex than what you make it to be.
> He is trying to stoke a "rally around the flag" effect.
Both things can be true.
> Guy talks over a story entitled "The inside story of a high-stakes call between Justin Trudeau and Donald Trump as the tariff deadline loomed". Subtitle is that Justin Trudeau "revealed" some details "behind closed doors". Why should I trust this guy's interpretation of a paywalled article about some journalist's impressions of some Trudeau advisor's impressions of Trudeau's claimed experience on a call with Trump?
Because we don't have a better alternative? Because it's supported by other reporting as well? Perhaps if you would step up and support your opinions we could do better.
> That's four levels of people with an incentive to spin the story.
You need to work on your counting.
> Then it is a NY Times article about Trump challenging some border arrangements with Canada about water access. How is this an indication he wants to annex Canada? It is absurd.
>
> Trump allegedly said he didn't think "the treaty that demarcates the border between the United States and Canada" is valid? More likely he wants to do exactly what he said: renegotiate the arrangements between the US and Canada about how the border and shared water resources are managed.
"But Trump is also pushing mineral-rich countries to join his cause — even by threatening their sovereignty."
> The guy goes on to say Trudeau got caught on a hot mic. Lol. No politician gets caught on a hot mic in 2025 just by chance right in the middle of a political issue like this. It was very obviously staged like all these other so-called hot mic incidents. He wants to dispel the obvious notion that he is just playing this up to try to win the election.
Whether or not it's staged has nothing to do with whether or not it has truth. A staged hot mic is is just one of many ways to communicate in the political arena. You can't pretend that Trudeau is just playing things up when provincial governments are also starting to act on the growing hostilities: https://www.cbc.ca/news/canada/british-columbia/us-truck-tol...
> Why would Trump be so resistant to giving security guarantees and NATO membership to Ukraine if he didn't think holding to security guarantees like NATO was important?
Because he is using his capitulation in Ukraine as a 'card' in the game where he, Putin, and Xi drag us back deeper into the multi-polar-world-mode where shipping is much less safe, there's much less trading, and power is much more concentrated in the hands of the few. It's like picking teams in schoolyard football. Russia picked Ukraine to bully and invade, and now we're picking the Panama Canal, Canada, and Greenland to bully then invade. There's certainly rumblings of things popping of in Taiwan in the next 3 years. I wouldn't be surprised if the suwalki gap gets attacked in the next 10 years with Russia trying to peel off the baltics. It seems plausible for there to be a concrete test of Article 5 over some sort of border strike along the finnish border areas. I predict global conflict will expand over the next 4 years, due to this divvying up process that you seem to be ignorant of.
I also predict Sal Mercogliano is going to have a busy 4 years reporting on all the crap that will happen on the oceans as the world order changes.
Why do you think Trump is capable of thinking anything besides his own enrichment or engrandizement is important? Given his long and storied track record of prioritizing himself over everyone else, including his own children, how do you justify your confidence in being able to say Trump is trustworthy with making any kind of security guarantee?
> Because Claude Code keeps doing stuff. It keeps solving massive problems, one after another. I throw larger and larger things at it, and it is unfazed. Chomp. Chomp. Chomp.
There's very little substance to this post. What "massive problems"? What "larger and larger things"? Am I supposed to guess? Sorry, I'm not impressed by vagaries.
I'm also personally not very impressed by AI, as it won't solve any problems I have because I have very specific coding problems that are based on undocumented APIs, doing things that literally nobody has done before. I've tried AI, but it's practically always wrong, and when it's correct it's something so trivial that I could have easily written the code. Maybe the problems I'm trying to solve are too "massive" for AI to guess at, or too obscure.
I have some 20-year-old codebases, so I do know what massive problems are. In such codebases AI assistants have finally made it possible to solve problems nobody had time to solve for decades and Claude Code seems to be best fit for that work so far.
Couldn't have put it better myself. It's great for the problems nobody has ever had time to solve. It's the problems that fall just below the ROI threshold, that tend to pile up until you have hundreds to thousands of them, each with icky weird dependencies that are _exactly_ the reason nobody has time to work on them.
Now you can chip through a dozen of these complex issues a day, and hope has finally arisen for getting through the backlog. That's a life-changing difference for anyone with a legacy code base.
Again, grand claims with zero substance. What are these supposed "massive problems"? I think your definition of "massive" and mine could be entirely different things.
Hey, I am not trying to convert you. You might not be the target audience of the post, but I recognized our situation. We have some old, intertwined, outdated, messy distributed complex systems to take care of. Big Balls of Mud. Big Massive Balls of Mud. Big Expensive Balls of Mud. Big Unique Balls of Mud. Big Balls of Critical Mud. So in very general terms, there is the massive problem of entropy we have to reduce. Undocumented APIs actually are an example of such entropy, so beware. AI has helped us with those, just saying. And yes, we've seen generative AI itself being a source of entropy, less so recently.
When the undocumented APIs change, is the AI going to know? Is it going to test hundreds of APIs continuously and then do what? If the API changes aren't something I need to worry about, maybe the AI still will, and so then I have to babysit the AI when it cries about something I don't have to worry about. I have tests for the undocumented APIs. That's really all I need. AI has been more of a miss than a hit for me, it generates far more noise than signal in my experience.
If it works for you, that's great, but I wouldn't trust it with anything important. It would still require a lot of my time to vet the fixes it produces, and from what I've seen (mostly from Copilot) it almost never produces an acceptable result - but then I'm probably outside the typical use case for coding AI.
My company pays for AI but from what I've seen of it, I'd never pay for it for my personal projects.
It's exactly what Yegge describes. It runs in the terminal, offering a retro vision of the most futuristic thing you can possibly be doing today. But that's been true since the command line was born.
But it's more than Claude Code, in that it's backend LLM agnostic. Although sonnet 3.7 with thinking _is_ killing the competition, you're not limited to it, and switching to another model or API provider is trivial, and something you might do many times a day even in your pursuit of code that vibes.
I've been a vim and emacs person. But now I'm neither. I never open an editor except in total desperation. I'm an aider person now. Just as overwhelmingly addicted to it as Yegge is to Claude Code. May the future tooling we use be open source and ever more powerful.
edit: Another major benefit of aider is its deep integration with git. It's not "LLM plus coding" it's really like an interface between any LLM (or LLMs), git, and your computer. When things go wrong, I git branch, reset to a working commit, and continue exploring.