Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Eight more months of agents

crawshaw.io

Post reply on HN
Print view View original

71–80 of 250 posts

Re: Eight more months of agents

#71

Post by written-beyond »

jorl17 wrote: post #57
rmonvfer wrote: post #53

Earlier quoted context omitted.

Yeah, I can’t recommend gpt-5.3-codex enough, it’s great! I’ve been using it with the new macOS app and I’m impressed. I’ve always been a Claude Code guy and I find myself using codex more and more. Opus is still much nicer explaining issues and walking me through implementations but codex is faster (even with xhigh effort) and gets the job done 95% of the time. I was spending unholy amounts of money and tokens (subs…

Out of curiosity, what’s your flow? Do you have codex write plans to markdown files? Just chat? What languages or frameworks do you use? I’m an avid cursor user (with opus), and have been trying alternatives recently. Codex has been an immense letdown. I think I was too spoiled by cursor’s UX and internal planning prompt. It’s incredibly slow, produces terribly verbose and over-complicated code (unless I use high or…

Codex cli is a very performant cli though, better than any other cli code assistant I've used.

I mean does it matter what code it's producing? If it renders and functions just use it. I think it's better to take the L on verbose code and optimizing the really ugly bits by hand in a few minutes than be kneecapped every 5 hour by limits and constant pleas to shift to Sonnet.

Re: Eight more months of agents

#72

Post by wavemode »

joefourier wrote: post #21

The author is correct in that agents are becoming more and more capable and that you don't need the IDE to the same extent, but I don't see that as good. I find that IDE-based agentic programming actually encourages you to read and understand your codebase as opposed to CLI-based workflows. It's so much easier to flip through files, review the changes it made, or highlight a specific function and give it to the agent…

I agree with you wholeheartedly. It seems like a lot of the work on making AI autocomplete better (better indexing, context management, codebase awareness, etc) has stagnated in favor of full-on agentic development, which simply isn't suited for many kinds of tasks.

Re: Eight more months of agents

#73

Post by wasmainiac »

derefr wrote: post #25
happytoexplain wrote: post #4

I don't trust the idea of "not getting", "not understanding", or "being out of touch" with anti-LLM (or pro-LLM) sentiment. There is nothing complicated about this divide. The pros and cons are both as plain as anything has ever been. You can disagree - even strongly - with either side. You can't "not understand".

The negative impacts of generative AI are most sharply being felt by "creatives" (artists, writers, musicians, etc), and the consumers in those markets. If the OP here is 1. a programmer 2. who works solely with other programmers and 3. who is "on the grind", mostly just consuming non-fiction blog-post content related to software development these days, rather than paying much attention to what's currently happening…

> "Anti-LLM sentiment" within software development is nearly non-existent.

I see it all the time in professional and personal circles. For one, you are shifting the goalpost on what is “anti-llm”, two, people are talking about the negative social, political and environmental impacts.

What is your source here?

Re: Eight more months of agents

#74

Post by georgemcbay »

overgard wrote: post #49
uludag wrote: post #42

> I am having more fun programming than I ever have, because so many more of the programs I wish I could find the time to write actually exist. I wish I could share this joy with the people who are fearful about the changes agents are bringing. It might be just me but this reads as very tone deaf. From my perspective, CEOs are seething at the mouth to make as many developers redundant as possible, not being shy about…

I bought Steve Yegge's "Vibe Coding" book. I think I'm about 1/4th of the way through it or so. One thing that surprised me is there's this naivete on display that workers are going to be the ones to reap the benefits of this. Like, Steve was using an example of being able to direct the agent while doing leisure activities (never mind that Steve is more of an executive/thought leader in this company, and, prior to LL…

Haven't read that book, but agree that if anyone thinks the workers are likely to capture the value of this productivity shift, they haven't been paying attention to reality.

Though at the same time I also think a lot of the CEO-types (at least in the pure software world) who believe they are going to capture the value of this productivity shift are also in for a rude awakening because if AI doesn't stall out, its only a matter of time from when their engineers are replaceable to when their company doesn't need to exist at all anymore.

Re: Eight more months of agents

#75

Post by otabdeveloper4 »

dakolli wrote: post #65
dagss wrote: post #13

But if you try some penny-saving cheap model like Sonnet [..bad things..]. [Better] pay through the nose for Opus. After blowing $800 of my bootstrap startup funds for Cursor with Opus for myself in a very productive January I figured I had to try to change things up... so this month I'm jumping between Claude Code and Cursor, sometimes writing the plans and having the conversation in Cursor and dump the implementati…

I promise you you're just going to continue to light money on fire. Don't fall for this token madness, the bigger your project gets, the less capable the llm will get and the more you spend per request on average. This is literally all marketing tricks by inference providers. Save your money and code it yourself, or use very inexpensive llm methods if you must. I think we are going to start hearing stories of people…

You can rent a GPU server and run your own Qwen models.

It's 90 percent the same thing as Claude but with flat-rate costs.

Re: Eight more months of agents

#77

Post by wasmainiac »

hasperdi wrote: post #3

> It sounds like someone saying power tools should be outlawed in carpentry. I see this a lot here

Yes because A tech-bro AIs dream is hundreds of thousands of developers being let go and replacing them with no code tools.

Sure, replace me with AI, but I better get royalties on my public contributions. I like many other developers have kids and other responsibilities to pay for.

We did not share our work publicly to be replaced. The same way I did not lend my neighbour my car so he could run me over, that was implicit.

Re: Eight more months of agents

#78

Post by tiny-automates »

crawshaw wrote: post #30
emmawirt wrote: post #16

Curious what you mean by "agent harness" here... are you distinguishing between true autonomous agents (model decides next step) vs workflows that use LLMs at specific nodes? I've found the latter dramatically more reliable for anything beyond prototyping, which makes me wonder if the "model improvement" is partly better prompting and scaffolding.

Hi, author here. I mean the piece of code that calls the model and executes the tool calls. My colleague Philip calls it “9 lines of code”: https://sketch.dev/blog/agent-loop We have built two of them now, and clearly the state of the art here can be improved. But it is hard to push too much on this while the models keep improving.

the harness being "9 lines of code" is deceptive in the same way a web server is "just accept connections and serve files."

the hard part isn't the loop itself — it's everything around failure recovery.

when a browser agent misclicks, loads a page that renders differently than expected, or hits a CAPTCHA mid-flow, the 9-line loop just retries blindly. the real harness innovation is going to be in structured state checkpointing so the agent can backtrack to the last known-good state instead of restarting the whole task. that's where the gap between "works in a demo" and "works on the 50th run" lives.

Re: Eight more months of agents

#79

Post by tiny-automates »

post-it wrote: post #34

> Agent harnesses have not improved much since then. There are things Sketch could do well six months ago that the most popular agents cannot do today. I think this is a neglected area that will see a lot of development in the near future. I think that even if development on AI models stopped today - if no new model was ever trained again - there are still decades of innovation ahead of us in harnessing the models we…

agreed, and i'd go further - the harness is where evaluation actually happens, not in some separate benchmark suite. rhe model doesn't know if it succeeded at a web task. the harness has to verify DOM state, check that the right element was clicked, confirm the page transitioned correctly. right now most harnesses just check "did the model say it was done" which is why pass rates on benchmarks don't translate to production reliability. the interesting harness work is building verification into the loop itself, not as an afterthought.

Re: Eight more months of agents

#80

Post by gip »

> In 2026, I don't use an IDE any more.

I don't think it is the best way to look at it. I think that now every team has the power to build and maintain an internal agent (tool + UX) to manager software products. I don't necessarily think that chat-only is enough except for small projects, so teams will build agent that gives them access to the level of abstraction that works best.

It's a data point but this weekend (e.g. in 2 days) I build a desktop + web agent that is able to help me reason on system design and code. Built with Codex powered by the Codex SDK. It is high quality. I've been a software engineer and director of engineering for 10 years. I'm blown away.

Post reply on HN