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

171–180 of 631 posts

Re: The last six months in LLMs in five minutes

#171

Post by 0xCMP »

ramon156 wrote: post #156

> Google released the Gemma 4 series of models, which are the most capable open weight models I’ve seen from a US company. Implying another country has a better model? I'm being pokey here because I'm very curious! I know Gemma is efficient, but I also remember Qwen and Kiwi being referred to as optimized. The difference being that Gemma is using less tokens, but maybe Qwen/Kiwi's quality is higher? I dont know.

In my experience the qwen models are best locally, but gemma ones have always been good. gemma4 is a notable improvement.

Re: The last six months in LLMs in five minutes

#172

Post by manmal »

rafaelmn wrote: post #56
viccis wrote: post #44

Earlier quoted context omitted.

How do you justify your salary given that you're just using a tool that any of us could use for $20 an hour in your role?

How do you justify your salary given that you're just using OSS compiler/editor any of us could use for free in your role ? AI just changed how I edit code - I still see coworkers (senior developers) failing with Claude/Codex and get stuck when there are trivial solutions if you understand the full problem space. Right now AI is just a productivity tool.

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 structure with handholding -> manual TODO comments -> Fill in blanks with handholding

Re: The last six months in LLMs in five minutes

#173

Post by grey-area »

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

That’s really impressive, and slightly worrying for creatives involved in film, animation or modelling.

Re: The last six months in LLMs in five minutes

#174

Post by IshKebab »

apsurd wrote: post #152
IshKebab wrote: post #136

Earlier quoted context omitted.

Supply and demand. Not many people are good at programming and it's highly in demand. The question is how many people will be good at vibe coding? If the answer is "lots" then we can definitely expect programming salaries to return to "normal" levels. His question is very relevant; you can't dismiss it as easily as that.

it can be easily dismissed because "anyone can use the tool that costs $20" makes no meaningful sense. this was always true in fact $20 is more than the free it costs for notepad++ it's a flippant statement. Go down the line of any tool; it's cost has basically nothing to do with skill difference to operate it. See basically everything. There's levels.

I have no idea what you're trying to say. If anyone really can vibe code then programming salaries are pretty much guaranteed to come down. The critical question is whether it really is true that anyone can do it, or if it still requires rare skill.

Re: The last six months in LLMs in five minutes

#175

Post by grey-area »

conception wrote: post #66
LZ_Khan wrote: post #57

I'm curious how the 6 months have looked from a non-programmer's perspective. What kind of co-working tools and similar optimizations have people from other fields experienced?

Claude in Office was a tipping point for nontechnical folks around me. Everyone’s slides decks are immaculate now. Finance isn’t needing nearly as much BI help. It’s pretty impressive.

I find it really troubling finance are relying on LLMs (word generators!) for financial analysis - I mean I guess it means there will never be any annoying gaps in the data.

Re: The last six months in LLMs in five minutes

#176

Post by dawnerd »

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.

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.

Re: The last six months in LLMs in five minutes

#177

Post by notachatbot123 »

grey-area wrote: post #173
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

That’s really impressive, and slightly worrying for creatives involved in film, animation or modelling.

Even more worrying are the implications for fakenews, propaganda, fraud, deception and mental health.

Re: The last six months in LLMs in five minutes

#178

Post by bloppe »

krzyk wrote: post #88
kvakkefly wrote: post #30

Earlier quoted context omitted.

I remember this very clearly myself. Before opus 4.5, I was doing a lot of hand holding and was coding a lot myself, but I have not written code since that day more or less. I did write some stuff myself just to learn how the enigma encryption machine worked, so wrote myself to learn. But professionally, I stopped coding in November.

It is sad. I like programming, if I couldn't do it and had to write text (which I do hate, I'm not a writer) it would be make quite a sad world.

A pattern I've settled into is to write code but leave a TODO for every narrow thing I want the LLM to do for me. Then just tell the agent to fix the todos. It's often faster and easier to give "instructions" this way

Re: The last six months in LLMs in five minutes

#179

Post by ryanjshaw »

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.

I find it gets you past the starting line but when you dig into the code it’s a mess of duplicated code, muddled responsibilities, poor architecture, 10k line files that eat your tokens, etc.

I’m building something using LLMs to scrape websites/socials for unstructured event data from combined text/images and the only way I’ve managed to get 100% consistent results for a reasonable cost is to break the task down into very small pieces that reduce the scope of mistakes significantly.

At present, for reasonable complex tasks, Codex/Claude will happily code you into an expensive corner.

Post reply on HN