Eight more months of agents • Hacker News Board

Re: Eight more months of agents

#191

Post by dagss » Tue, Feb 10, 2026, 2:14 PM UTC

written-beyond wrote: post #29

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…

Just use Codex 5.3 in codex cli, the $20/mo plan is basically limitless at least for me and I keep reasoning efforts high. You can enjoy it while it lasts, OpenAI is being very liberal with their limits because of CC eating their lunch rn.

Thanks a lot, after today I have fully switched to Codex I think.

This vscode extension makes it almost as easy to point codex to something as when doing it in cursor:

https://github.com/suzukenz/vscode-copy-selection-with-line-...

Re: Eight more months of agents

#192

Post by vedhant » Tue, Feb 10, 2026, 2:15 PM UTC

The sandboxing pain is real. Sadly, a new VM seems like the most simple and viable solution. I don't think the masses are doing any sandboxing at all. We really need a sandbox solution that is sort of dynamic and doesn't pester the user with allow/deny requests. It has to be intelligent and keep up with the llm agents.

Re: Eight more months of agents

#193

Post by amarble » Tue, Feb 10, 2026, 2:21 PM UTC

entropyneur wrote: post #124

> I deeply appreciate hand-tool carpentry and mastery of the art, but people need houses and framing teams should obviously have skillsaws. Where are all the new houses? I admit I am not a bleeding edge seeker when it comes to software consumption, but surely a 10x increase in the industry output would be noticeable to anyone?

This weekend I tried what I'd call a medium scale agentic coding project[0], following what Anthropic demonstrated last week autonomously building a C-compiler [1]. Bottom line is, it's possible to make demos that look good, but it really doesn't work well enough to build software you would actually use. This naturally lends itself to the "everybody is taking about how great it is but nobody is building anything real with it" construct we're in right now. It is great, but also not really useful.

[0] https://www.marble.onl/posts/this_cost_170.html

[1] https://www.anthropic.com/engineering/building-c-compiler

Re: Eight more months of agents

#194

Post by nathias » Tue, Feb 10, 2026, 2:21 PM UTC

entropyneur wrote: post #124

> I deeply appreciate hand-tool carpentry and mastery of the art, but people need houses and framing teams should obviously have skillsaws. Where are all the new houses? I admit I am not a bleeding edge seeker when it comes to software consumption, but surely a 10x increase in the industry output would be noticeable to anyone?

yes, there is a very large increase in TUI tools

Re: Eight more months of agents

#195

Post by habinero » Tue, Feb 10, 2026, 2:22 PM UTC

jfreds wrote: post #174

mono442 wrote: post #154

Earlier quoted context omitted.

Using these tools comes down to basically just writing what you want in a natural language. I don't think it will be a problem to catch up if they need to.

Context management, plan mode versus agent mode, skills vs system prompt, all make a huge difference and all take some time to build intuition around. Not all that hard to learn, but waiting for things to settle down assumes things are going to settle down. Are they? When?

You wait for everyone to go broke chasing whatever, and then take their work for your own. It's not that hard to copy and paste.

Re: Eight more months of agents

#196

Post by RobMurray » Tue, Feb 10, 2026, 2:26 PM UTC

properbrew wrote: post #27

jonas21 wrote: post #17

Earlier quoted context omitted.

So that you can be using the current frontier model for the next 8 months instead of twiddling your thumbs waiting for the next one to come out? I think you (and others) might be misunderstanding his statement a bit. He's not saying that using an old model is harmful in the sense that it outputs bad code -- he's saying it's harmful because some of the lessons you learn will be out of date and not apply to the latest…

You also don't have to throw away everything you've learnt in those 8 months, there's some things that you'll subtly pickup that you can carry over into the next generation as well.

Also a lot of what you learn is how to work around limitations of today's models and agent frameworks. That will all change, and I imagine things like skills and subagents will just be an internal detail that you don't need to know about.

Re: Eight more months of agents

#197

Post by asa400 » Tue, Feb 10, 2026, 2:29 PM UTC

jfreds wrote: post #174

mono442 wrote: post #154

Earlier quoted context omitted.

Using these tools comes down to basically just writing what you want in a natural language. I don't think it will be a problem to catch up if they need to.

Context management, plan mode versus agent mode, skills vs system prompt, all make a huge difference and all take some time to build intuition around. Not all that hard to learn, but waiting for things to settle down assumes things are going to settle down. Are they? When?

That these facets of use exist at all are indicative of immature product design.

These are leaked implementation details that the labs are forcing us to know because these are weak, early products and they’re still exploring the design space. The median user doesn’t want to and shouldn’t have to care about details like this.

Future products in this space won’t have them and future users won’t be left in the dust by not learning them today.

Python programmers aren’t left behind by not knowing malloc and free.

Re: Eight more months of agents

#198

Post by conartist6 » Tue, Feb 10, 2026, 2:51 PM UTC

entropyneur wrote: post #124

> I deeply appreciate hand-tool carpentry and mastery of the art, but people need houses and framing teams should obviously have skillsaws. Where are all the new houses? I admit I am not a bleeding edge seeker when it comes to software consumption, but surely a 10x increase in the industry output would be noticeable to anyone?

It's AI features and 10x more bugs. Microsoft is leading the way.

Re: Eight more months of agents

#199

Post by conartist6 » Tue, Feb 10, 2026, 2:59 PM UTC

IDEs are going to come roaring back.

As the author says, there's nothing wrong with the idea of the IDE. Of course you want to be using the best, most powerful tools!

AI showed us that our current-gen text-editor-first IDEs are massively underserving the needs of the public, yes, but it didn't really solve that problem. We still need better IDEs! What has changed is that we now understand how badly we need them. (source: I am an IDE author)

Re: Eight more months of agents

#200

Post by meowface » Tue, Feb 10, 2026, 2:59 PM UTC

arrrg wrote: post #151

entropyneur wrote: post #124

> I deeply appreciate hand-tool carpentry and mastery of the art, but people need houses and framing teams should obviously have skillsaws. Where are all the new houses? I admit I am not a bleeding edge seeker when it comes to software consumption, but surely a 10x increase in the industry output would be noticeable to anyone?

To me the hard problem isn’t building things, it’s knowing what to build (finding the things that provide value) and how to build it (e.g. finding novel approaches to doing something that makes something possible that wasn’t possible before). I don’t see AI helping with knowing what to build at all and I also don’t see AI finding novel approaches to anything. Sure, I do think there is some unrealized potential somewh…

In a few decades, AIs will probably be better at those than most humans. Possibly even sooner.