Also, I do want to note that these little "Here is how I see the world of SWE given current model capabilities and tooling" posts are MUCH appreciated, given how much you follow the landscape. When a major hype wave is happening and I feel like I am getting drowned on twitter, I tend to wonder "What would Simon say about this?"

But it's not just the commentariat. I have seen very serious people in software engineering and tech talk about the ways in which their coding habits have change drastically.

Benchmarks [1] alone don't seem to capture everything, although there have been jumps in the agentic sections, so maybe they actually do.

My question is; what explains these big jumps in capabilities that many serious people seem to be noticing all at once? Is it simply that we have thrown enough data and compute at the models, or instead, are labs perhaps fine-tuning models to get really good at tool calls, which leads to this new, surprising behavior?

When I explain agents to people, I usually walk them through a manual task one might go through when debugging code. You copy some code into ChatGPT, it asks you for more context, you copy some more code in, it suggests and edit, you edit and run, there is an error, so you paste that in, and so on. An agent is just an LLM in that loop which can use tools to do those things automatically. It would not be shocking to me if we took weaker models like Claude Opus 4.0 and made it 10x better at tool calls, it would be a much stronger and more impressive model. But is that all that is happening, or am I missing something big?

[0] https://substack.com/@noahpinion/p-187818379

[1] https://www.anthropic.com/news/claude-opus-4-6

Comments URL: https://news.ycombinator.com/item?id=47019798

Points: 12

# Comments: 9

It is enormously useful for the author to know that the code works, but my intuition is if you asked an agent to port files slowly, forming its own plan, making commits every feature, it would still get reasonably close, if not there.

Basically, I am guessing that this impressive output could have been achieved based on how good models are these days with large amounts of input tokens, without running the code against tests.

1. When I work on side projects and use AI, sometimes I wonder "what's the point if I am just copy / pasting code? I am not learning anything" but what I have come to realize is building apps with AI assistance is the skill that I am learning, rather than writing code per se as it was a few years ago.

2. I work in high scale distributed computing, so I am still presented with ample opportunities to get very low level, which I love. I am not sure how much I care about writing code per se anymore. Working with AI still is tinkering, it has not changed that much for me. It is quite different, but the underlying fun parts are still present.

I want to mention my current frustration with cursor recently and why I would love an OSS alternative that gives me control; I feel cursor has dumped agentic capabilities everywhere, regardless of whether the user wants it or not. When I use the Ask function as opposed to Agent, it seems to still be functioning in an agentic loop. It takes longer to have basic conversations about high level ideas and really kills my experience.

I hope void doesn’t become an agent dumping ground where this behavior is thrust upon the user as much as possible

Not to say I dislike agent mode, but I like to choose when I use it.

Nothing fancy or special. It was built with streamlit in about 150 lines and a single file. But I was impressed that Claude code 1 shot it

But, I am also having more fun building things than perhaps the earliest days of my first code written, which is just over 7 years now. Insofar as 1) goes, yes, I never want to go back. I can learn faster and more deeply than I ever could. It's really exciting!

I think a fair conclusion here is reasoning models are still really good at solving very difficult math and competitive programming problems, but just better at ones they have seen before.

I am curious, is your Java client one of the many open source bot clients that actually calls into client code? Or is it some type of click script which does some repetitive inputs?

I have had bad luck with the former in terms of getting banned.

I am also a junior dev and completely empathize with being given a lot of responsibility and potentially messing up. I think for someone with < 1 year of experience, to solve the problems you created as fast as you did is really impressive. Thankfully your story ends well :)

If interesting in feedback; 1. It seems to only run the block/reroute to to-do list logic when a page is loaded. If the user is already on their site and then adds that site to the blocked list and has to-do list items, it won't be blocked immediately. I don't think this feature is vital but might align better with expectation. 2. Maybe show the to-do list and blocked sites button on the main extension popup, rather than having to go -> to-do list -> blocked sites 3. Maybe on/off button in case user has some sort of issue and needs to quickly access a site that is blocked.

But, that gets the competitive aspect of this challenge out of the way immediately so I can simply have fun with these problems :)

I am excited for them to become a bit more challenging because my friend and I are going to work on them together.