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

The last six months in LLMs in five minutes

simonwillison.net

Post reply on HN
Print view View original

481–490 of 631 posts

Re: The last six months in LLMs in five minutes

#481

Post by manmal »

rafaelmn wrote: post #205
manmal wrote: post #172

Earlier quoted context omitted.

Can you share how you use it to edit code? I‘ve seen a couple approaches, curious what you are doing: 1. Spec -> plan -> code (all agent driven, maybe with grill-me or ultraplan) 2. Handwritten spec -> agent driven plan -> agent driven code 3. Agent driven spec -> vibed code -> Fix by handholding until ok-ish 4. Vibed throwaway prototypes -> extract useful patterns -> rewrite with handholding 5. Generate file structu…

Usually I describe the problem, explore a bit with LLM iteratively. Then I switch to creating a plan when I have enough insight (and the LLM has it in context/same session as exploration), specifying all the things I'm trying to accomplish. Then I just iterate with LLM - I let it start writing stuff in YOLO mode and check on what it's doing in the code steering it in the direction I want. Usually the code LLM generat…

Thank you for elaborating. Really interesting.

Re: The last six months in LLMs in five minutes

#483

Post by wanderlust123 »

Philip-J-Fry wrote: post #248
kstenerud wrote: post #219

Earlier quoted context omitted.

The polarization comes from the very disparate coding experiences and output quality that different people find when using these tools. For example, I've had the opposite experience of yours, generating very high quality work using Claude (such as https://github.com/kstenerud/yoloai ). Just in dealing with all the bugs and idiosyncrasies in the technologies I'm using, the agent has been a godsend in discovering and c…

I don't want to offend (it's AI coded anyway :)) but that does not scream "high quality" to me. The headline gif on that repo just paints a terrible picture. It can't draw a box correctly, there's random underscores all over the screen. The UI itself is just incredibly incoherent. I don't even know what I'm looking at. Like, no it doesn't seem like very high quality work... It just seems like a vibe coded tool. Edit:…

I think at this point there is no convincing people. Clearly there is value in these tools and it generates code when steered properly. Perhaps your struggles are down to a skill issue.

Re: The last six months in LLMs in five minutes

#484

Post by datadrivenangel »

hollowturtle wrote: post #465
DennisP wrote: post #458

Earlier quoted context omitted.

Steve Yegge wrote about this in his book Vibe Coding . He says it takes about a year of experience before you're consistently getting good results. He writes about lots of different techniques for doing that, but also says a lot of it comes down to just getting a feel for when the LLM is going to go haywire.

It's been 4 years of using them for me, before writing a book I'd wait to have a decade of experience to share with others, otherwise it would have the same value as a book on a react tutorial

From what I've heard this is a good assessment of steve's book.

Re: The last six months in LLMs in five minutes

#485

Post by prettyblocks »

hollowturtle wrote: post #209

> The coding agents got really good It's since november 2025, the so called "inflection point", that I'm still wondering for who coding agents become "really good". All I observe they got better at tool call and answering questions about big codebases, especially if the question has a vague pattern to search, and they're superuseful for that! For generating production code even with a lot of steering and baby sitting…

I'm curious. What have you actually tried? Are you just prompting the LLM with one off tasks? For good results, you need to take the time to read the documentation for the harness you are using and configure your environment. This tuning can take dozens hours to nail down. Then there's the actual approach for working on your projects. Many people that have good results with agentic coding actually spend the bulk of their time in plan mode where they go back and forth with the LLM designing a granular playbook for the task at hand before they ever have it write any code.

Re: The last six months in LLMs in five minutes

#486

Post by newaccount670 »

hollowturtle wrote: post #209

> The coding agents got really good It's since november 2025, the so called "inflection point", that I'm still wondering for who coding agents become "really good". All I observe they got better at tool call and answering questions about big codebases, especially if the question has a vague pattern to search, and they're superuseful for that! For generating production code even with a lot of steering and baby sitting…

Good is relative. If somebody struggles with getting their hand-written code to compile, the LLM coding agents will look like geniuses to them.

An idiosyncrasy of humanity is that the dumbest individuals tend to also be the loudest.

Re: The last six months in LLMs in five minutes

#487

Post by captn3m0 »

Antibabelic wrote: post #157
minimaxir wrote: post #6

Earlier quoted context omitted.

Every modern image-generation model can generate a pelican on a bicycle trivially. The point of the test is to generate SVG text that represents an image, which is more complicated. Yes, there are ways to convert raster images to SVG for use in training data but it's not a good use of anyone's time.

I don't understand this response. Human artists can and do make SVGs.

They typically use a visual editor like Inkscape with visual feedback. Nobody is hand-coding a complex SVG.

Re: The last six months in LLMs in five minutes

#488

Post by empath75 »

vishal_new wrote: post #49

what are your thoughts on Software engineer replacement. My team has already seen big reductions. Q/A team is gone. Software Engineer reduced by a third. Scared for the future

There is an entire category of software engineers who exist entirely to knock out features on microservices or do easily automatible QA work whose jobs will disappear.

Re: The last six months in LLMs in five minutes

#490

Post by timacles »

windexh8er wrote: post #437
kstenerud wrote: post #219

Earlier quoted context omitted.

The polarization comes from the very disparate coding experiences and output quality that different people find when using these tools. For example, I've had the opposite experience of yours, generating very high quality work using Claude (such as https://github.com/kstenerud/yoloai ). Just in dealing with all the bugs and idiosyncrasies in the technologies I'm using, the agent has been a godsend in discovering and c…

A standard Docker container, with the container UID/GID mirrored to the host user, holding the host user's API keys, with the host user's project directory bind-mounted. The tooling doesn't even use gVisor / Kata by default which could implement the claim made, but in reality this entire project appears to be security theater.

I’d like people to notice that those who claim this amazing AI productivity boost are always: pushing out software they don’t know how to judge the quality of and pushing projects that are 70% done. Every. Single. Time.

I use Claude all the time, it is immensely helpful. It is also very nuanced and requires a high level of expertise in a specific domain to produce quality work. Even then, that take time and effort. Anyone saying otherwise, quite frankly, doesn’t know what they’re doing.

Post reply on HN