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

231–240 of 631 posts

Re: The last six months in LLMs in five minutes

#231

Post by jaccola »

hollowturtle wrote: post #228
treme wrote: post #220

Earlier quoted context omitted.

you are experiencing reverse Dunning–Kruger effect. For someone that just dabbled in coding prior, it went from AI building 80%, and struggling through to finish the 20% when trying to build an app/website. now it's like 97% and struggling with last 3%. Yes it'll look rough around the edges when evaulated by a senior dev, but being able to build MVP level things to completion with ease helps you stay engaged and moti…

Please do not cite Dunning–Kruger effect at random. Who needs to generate a dumb demo of a 97% done crud app? We had code generators for those, everytime I read claims like that and I ask to explain further I then discover it's people who were not productive before generating the so called "MVP level things to completion with ease". If you're trying to solve a HARD problem people REALLY have, it's a novelty that agen…

The obvious pushback to all of the slop is: coding was never hard. Learning resources were abundant and free.

If these people had a burning desire to build things prior to LLMs and couldn’t put in the effort to learn to build them (which is also fun!) then why would they ever put the effort into anything to understand it and make it good??

Re: The last six months in LLMs in five minutes

#232

Post by tonyedgecombe »

LtWorf wrote: post #121
satvikpendem wrote: post #102

Earlier quoted context omitted.

Of course you can always program by hand, no one is stopping you.

Plenty of companies are forcing the use of AI to people.

In most cases you could work around that. For instance write the code yourself and make the AI write the tests. Or keep it busy writing superfluous documentation. Very few people are micromanaged to the extent that they can’t subvert the system.

Re: The last six months in LLMs in five minutes

#233

Post by LAC-Tech »

xbmcuser wrote: post #18
Insanity wrote: post #10

I wonder how much the 'inflection point' is a thing vs marketing. I'm sure the models got somewhat better, but even now when I'm trying to 'vibe code' a game with the latest models (combination of Codex w/ gpt5.5 and gpt5.3-codex), they really do struggle. They definitely get something barebones up and running, but it's far from a fully fledged application.

It's real for me as a non coder previously uploading a python script asking it to add this function or that function used to break it now usually it just works at least with Claude and Chat Gpt models. Google Gemini still breaks stuff but rumors are their new flash model that will be announced soon is very good. I am usually working with data in csv files and generating spreadsheet pdf etc and the results for that ha…

"flash" or "fast" AI models are worse than useless at coding for me. they make my codebase much worse. It's a maintenance burden.

Gemini Pro on the other hand can be quite a pleasant experience.

Re: The last six months in LLMs in five minutes

#234

Post by dcminter »

specproc wrote: post #193
wewewedxfgdf wrote: post #150

Does this guy have a "publish to front page of HN" button on his blog editor?

He's one of the main developers behind Django.

Years ago I used to read his blog on Django and found it quite interesting despite being neither a Django nor even a python user - this must have been at least 10 years ago and perhaps more.

When he resurfaced in my feeds as an AI commentator it took me quite a long while to join the dots that he was the same person!

Re: The last six months in LLMs in five minutes

#235

Post by hollowturtle »

kstenerud wrote: post #219
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…

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…

Don't want to be rough, but I'd like to read experiences about novelty ideas that solve people real problems in the real world, your project it's just about selling new shovels.

As I commented on another thread

> If you're trying to solve a HARD problem people REALLY have, it's a novelty that agents can't help with, otherwise if it gets 97% there MAYBE it's just a signal that your idea isn't that novel!

Re: The last six months in LLMs in five minutes

#236

Post by mrcsharp »

dawnerd wrote: post #176
WesolyKubeczek wrote: post #163

Earlier quoted context omitted.

> Key has been to spend a fair amount of time on initial overall design document, which is split into tangible and limited phases. > For each phase an implementation plan is made. At the end, a summary document of what was delivered and what was discovered. > I do check the documents, and what they're doing. I also check the tests, some more thorough. Sounds like programming, but with extra steps.

Also the least fun part of development. Maybe I’m the weird one but I like to just jump right in, planning every last detail before writing code is boring.

> planning every last detail before writing code is boring

Not only that but you can't really plan everything. It is impossible. Without LLMs, with every line of code you are making a decision or discovering something new that must be dealt with or realizing how the current thing might impact something else and so on.

There is no way for a programmer to consider all of these little things ahead of time and if an attempt is made, it will take as long as actually writing that code.

Re: The last six months in LLMs in five minutes

#237

Post by magicalhippo »

WesolyKubeczek wrote: post #163
magicalhippo wrote: post #92

Earlier quoted context omitted.

I've "vibed" some non-trivial stuff lately using a combination of Codex with 5.5 and Claude Code with Opus 4.7. Key has been to spend a fair amount of time on initial overall design document, which is split into tangible and limited phases. I go back and forth between them on this document until we're all happy. For each phase an implementation plan is made. At the end, a summary document of what was delivered and wh…

> Key has been to spend a fair amount of time on initial overall design document, which is split into tangible and limited phases. > For each phase an implementation plan is made. At the end, a summary document of what was delivered and what was discovered. > I do check the documents, and what they're doing. I also check the tests, some more thorough. Sounds like programming, but with extra steps.

It's software development, but with much less actual programming (in my case none).

When I said I check the documents, the initial design document was the only I really took a hard look at. The intermediary I just skimmed, looking for red flags or something I had forgotten to tell them. Those documents served as a basis for their work, and as a record of what was done.

Overall I spent perhaps a few hours on each project, over the course of a few days. I'd check in every half hour or whenever I had time, tell Claude "Great, let's do the next deliverable", or GPT "We're done with phase 4, please do a detailed code review, reference the design document and documentation of previous phases". Then I'd leave them cooking.

Re: The last six months in LLMs in five minutes

#238

Post by paulluuk »

hollowturtle wrote: post #235
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…

Don't want to be rough, but I'd like to read experiences about novelty ideas that solve people real problems in the real world, your project it's just about selling new shovels. As I commented on another thread > If you're trying to solve a HARD problem people REALLY have, it's a novelty that agents can't help with, otherwise if it gets 97% there MAYBE it's just a signal that your idea isn't that novel!

This is a pretty wild take. What percentage of human engineers are creating novel solutions for hard problems, you think? I work in R&D and even my work is 90% doing things that other people already solved. If you are really doing cutting edge SOTA work that has never been done by another human in some form or another, then kudos to you and I want your job.

Re: The last six months in LLMs in five minutes

#239

Post by falcor84 »

ionwake wrote: post #218
jimbobthemighty wrote: post #161

I asked Gemini for a video of 'pelican riding a unicycle in hyde park' - I was blown away by the output: https://gemini.google.com/share/55e250c99693

only SVG counts tho, dont know why

Willison chose this task because (unlike actual images of pelicans) is was clearly not in training data, but could be reasoned about and composed from what's there. But just like those "how many golf balls can you fit in a 747?" interview questions, it should now be retired.

Re: The last six months in LLMs in five minutes

#240

Post by viking123 »

bluegatty wrote: post #17

'Producing Images' or even 'Some Code that is Valid and Compiles' is in some ways one of the most misleading ways we assess quality of the AI. It is getting very good at producing code that compiles - at the algorithmic level. This is definitely noteworthy - and the AI is crossing a critical 'productivity threshold'. But 'Drawing of a Proper Duck' is almost arbitrary because it may have nothing to do with the ' Speci…

Wow! Actually a sensible comment under all the astroturfing that even this place is so full of now.
Post reply on HN