251–260 of 311 posts
It's a race to the bottom. DeepSeek beats all others (single-shot), and it is ~50% cheaper than the cost of local electricity only. > DeepSeek V3.2 Reasoning 86.2% ~$0.002 API, single-shot > ATLAS V3 (pass@1-v(k=3)) 74.6% ~$0.004 Local electricity only, best-of-3 + repair pipeline
All those parameters and it still won't answer questions about Tianenman Square in 1989... :(
Earlier quoted context omitted.
Yup, they do quite poorly on random non-coding tasks: https://aibenchy.com/compare/minimax-minimax-m2-7-medium/moo...
It’s worth also comparing Qwen 3.5, it’s a very strong model. Different benchmarks give different results, but in general Qwen 3.5, GLM 5, and Kimi K2.5 are all excellent models, and not too far from current SOTA models in capability/intelligence. In my own non-coding tests, they were better than Gemini 3.1 flash. They’re comparable to the best American models from 6 months ago.
I badly want to shift more of my work to them, and I'm finding ways of shifting more lower-level loads to them regularly, but they're really not there yet for anything complex.
Earlier quoted context omitted.
> The $200 per month subscription comes with a ton of usage. $200 dollars + VAT is half of my rent. I know HN is not a good place to rant on this subject, but I'm often flabbergasted about the number of people here that lives in a bubble with regard to the price of tech. Or just prices in general. I remember someone who said a few years ago (I'm paraphrasing): "You could just use one of the empty room in your house!"…
$200/mo is a lot, sure, but the shocking part of that comparison is your rent. I didn’t know $400/mo apartments still existed. For most people in the US and EU, $200 would be closer to 15%-20% of rent I think? My cell phone bill for my family is almost $200/mo. Last year, at first, $200 seemed crazy. Now that I’m getting addicted to coding agents, not so much. Some companies are paying API rates for AI for employees,…
Even the US has places with cheap rent/housing. The downside is that there's no (well-paying) work nearby.
I'm always skeptical because you can make it pass the benchmarks, then you use it and it is not practically useful unlike an extremely general model. Cool work though, really excited for the potential of slimming down models.
I find it's often very language and sector dependent. I still see a massive difference in systems programming (normally c++ and rust) between any open model I've tried and something like sonnet 4.5 (not really tried 4.6). And honestly, even the big models (like Opus 4.6) struggle in many cases. Perhaps these things aren't well represented in the training data for these open models? Every local model I've tried (minim…
I know from first-hand experience that at least a couple of the SOTA providers use third-party providers for supervised finetuning with instructions that are heavily geared towards a specific set of languages as well. But of course the base dataset from the major providers is likely to be sufficiently better that it matters less, and the big models are good enough at carrying over training that it at least seems like extra training on the core languages they care about at least somewhat carries over (you see this with natural language too - they do really well for many minor languages that make up a miniscule proportion of the training data).
(I won't say much more regarding the SFT/RLHF work due to NDAs - plural; I know who one of the providers is; I don't know who the one or more others are as the intermediary I did some work for obscured it well enough that I couldn't really violate the NDA even if I wanted to)
Earlier quoted context omitted.
[flagged]
I have never read a snide comment on this site that i've been more repulsed by. I think because it's so specifically sharpened to stab at the software developer, my compatriot, one of the foremost primary populations here, rather than just an overall shitty human insult -- and timed to do so when the person opens up in an honest dialogue about what they're doing. But good news: every large software house i've talked…
Earlier quoted context omitted.
[flagged]
We have the quietest on-call rotation of any company I've ever worked at. We have a high standard for code review, static verification, and tests. The fact that the code isn't hand-rolled artisanal code, and is generated by AI now, has so far turned out to have no impact on product quality or bugs reported.
So, which company is it again?
Earlier quoted context omitted.
I use both, read what I need to read and fix small issues myself. Both Agents are pure magic and none of their issues warrant a tantrum on a public forum.
I posted a more detailed report in case you can't see it in your thread view: https://news.ycombinator.com/item?id=47541369 and other comments further back in my history > none of their issues warrant a tantrum on a public forum I don't get frustrated if a problem is genuinely difficult to solve and the product creator is trying their best, I get frustrated when a problem has been solved by other similar products but…
Earlier quoted context omitted.
You still need to give it precise context and instructions when dealing with things that are not web apps or some other software cliche. The reasoning is great in opus, unbeatable at the moment. I understand what you mean, it becomes disappointing on more niche or specific work. It’s honestly a good thing to see these models are not really intelligent yet.
I still don't trust any AI enough to generate or edit code, except for some throwaway experiments, because every time I tried it's been inefficient or too verbose or just plain wrong. I use it for reviewing existing code, specifically for a components-based framework for Godot/GDScript at [0]. You can view the AGENTS.md and see that it's a relatively simple enough project: Just for 2D games and fairly modular so the…
I still get really mad at AI sometimes and I am not sure whether I could use AI for coding full time.
(Codex broke my git a few days ago.)
Earlier quoted context omitted.
Not the answer that you are looking for, but I am a fellow AMD GPU owner, so I want to share my experience. I have a 9070 XT, which has 16GB of VRAM. My understanding from reading around a bunch of forums is that the smallest quant you want to go with is Q4. Below that, the compression starts hurting the results quite a lot, especially for agentic coding. The model might eventually start missing brackets, quotes, etc…
For autocomplete, Qwen 3.5 9B should be enough even at Q4_k_m. The upcoming coding/math Omnicoder-2 finetune might be useful (should be released in a few days). Either that or just load up Qwen3.5-35B-A3B-Q4_K_S I'm serving it at about 40-50t/s on a 4070RTX Super 12GB + 64GB of RAM. The weights are 20.7GB + KV Cache (which should be lowered soon with the upcoming addition of TurboQuant).