[mesmertech]

For coding you always want to go with the best model in the category, not something that would be the best model if we went 1 year back which GLM 5.1 is, and I'm saying that as a big fan of GLM cause I run a translation site where GLM is good enough for the price.

Most of the money right now is in coding. Openai and Anthropic just have to be 6 months ahead of SOTA open source models and they'll capture most of the enterprise and dev market

[binary0010]

Yes I'm an engineer (20 years most in games/graphics industry) and only use it for code. I've been using glm 5.1 this week a lot. I went in expecting another "decent" but not really "up to standard" open source model.

I highly doubt I'll ever use Claude again.

I think you are wrong about Claude being any significant level better

[cassianoleal]

I've been mostly coding with GLM-5.1 as well and I agree with you. DeepSeek V4 Flash is another very good surprise. Incredibly cheap, fast and effective.

[MaKey]

I've been using DeepSeek v4 Flash with OpenCode for the whole week to refactor a Terraform code base I inherited and it worked surprisingly well.

[aspenmartin]

Well I think there are a multitude of harder measurements that would disagree with you, but ultimately there is absolutely a use case for cheaper open models (or even cheaper tiers of proprietary models) and in fact the unsolved optimization everyone is trying to get to is how much spend to use for a given task. But there will always be a market, especially in enterprise, for the best performance there is to offer

[ggttk]

Why are you boosting so hard? Lmao either you’re a paid poster or you own stock in a frontier firm. Which one?

[aspenmartin]

Sadly neither :(

[RevEng]

I strongly disagree. I'm an engineer - I'm all about the fastest, cheapest thing that meets the requirements. I don't need Opus 4.7, even for my complex programming tasks. It costs over 10x other models available that still give good enough answers. Those smaller models are also a lot faster to output tokens, which saves me time.

Once the model gets good enough, the returns on bigger models diminishes quickly. I don't want to spend 10x the money and wait 5x the time to get answers that are equivalent.

[yokoprime]

Same here, i can't say i've seen any difference in 4.6 vs 4.7 other than price

[odie5533]

If I generate code with Claude, ChatGPT, and GLM 5.1, I can't say which model is which reliably. I exclusively use Claude more out of superstition than reason.

[lunar_mycroft]

> For coding you always want to go with the best model in the category

This is transparently false, because the best "model" is still competent human developers. They're just more expensive. If you're willing to use current LLMs at all, it means you're willing to sacrifice quality for a better price, and your disagreement with the comment you were replying to is entirely about what the optimum tradeoff is.

[aspenmartin]

Well it may be false that you always want the best model, but the point is performance of you+<agent> is far more cost effective than you+someone else

[lunar_mycroft]

Maybe, but that's a different claim than the one I was responding to. And also raises the question of "if the lower quality but cheaper output of frontier models is more cost effective than humans, is the even lower quality but even cheaper output of OSS models is more cost effective still?" With an absolute rule like GP suggested ("no, you always want the best code generator") the answer is clear, but it get much murkier if you reject such rules (as you have to to be an LLM coding proponent)

[aspenmartin]

I think that’s a fair and good q and point.

[noname120]

It was true 6 months ago, not anymore. Frontier models now outperform developers on many tasks, be it on quality/readability/maintainability, and let’s not talk about speed…

[lunar_mycroft]

I've seen the code they produce without extensive help from human developers, this is clearly false.

Good to see the classic "yeah the models weren't good enough six months ago, but this time they actually are, promise! Please forget you were hearing the exact same thing six months ago!" is alive and well though.

[aspenmartin]

Are you aware of performance trends though? You’re painting a picture that seems to ignore how things have consistently trended for many years now, even pre ChatGPT. It is absolutely data driven to say “an inflection point has happened within the last 6 months”. And that was also true 6 months ago (where people started using coding agents fairly consistently since sonnet 4). And it was true 6 months before that. It’s not like people are like “we’ve fixed all the bugs!” And then nothing has changed. I don’t necessarily agree with the parent poster that agents are better than humans but they are certainly much better at many tasks.

[lunar_mycroft]

> Are you aware of performance trends though? You’re painting a picture that seems to ignore how things have consistently trended for many years now, even pre ChatGPT.

Models have been getting better, but all that follows from that is that newer models tend to be better than older ones. It doesn't follow that they have (or even will in the future) gotten better than anything else, be that human developers, a given definition of good enough, etc.

> It is absolutely data driven to say “an inflection point has happened within the last 6 months”.

With all due respect to OP (who I think is responsible for popularizing that way of phrasing it), I don't think it is when you consider the actual definition of "inflection point". At best I think you can say that models crossed a lot of developers definition of good enough around then, which is a different thing. The problem I have with that is that as a (mostly) outsider looking in, it doesn't seem like they're right.

[aspenmartin]

> Models have been getting better, but all that follows from that is that newer models tend to be better than older ones. It doesn't follow that they have (or even will in the future) gotten better than anything else, be that human developers, a given definition of good enough, etc.

But this is not true, you’re saying we only have relative performance numbers and not absolute measures of capabilities and reliability but that’s simply not true. OSS benchmarks as well as the internal flywheels of these companies are good complementary measurements.

> At best I think you can say that models crossed a lot of developers definition of good enough around then, which is a different thing

That’s the inflection point. Implication is a massive jump in adoption. We’re not like pulling this out of a hat, there are a number of compelling datapoints. The onus is on people to bring actual evidence that contradicts all of the data and observations we have.

[suddenlybananas]

Why is anthropic hiring software developers then?

[aspenmartin]

Because they still need them?

[suddenlybananas]

Why would they still need them if "[f]rontier models now outperform developers on many tasks, be it on quality/readability/maintainability, and let’s not talk about speed"

[aspenmartin]

Because to replace a SWE you need them to reliably outperform developers on ALL tasks

[eikenberry]

> For coding you always want to go with the best model in the category [..]

And this is why many companies go out of business. You always want the best bang for your buck, sometimes this is the "best model" and sometimes it is not.

[kgwgk]

For coding like for everything else in life cost is a factor.

[mesmertech]

Cost for the value delivered. Like if you offered the current SOTA open source models at $0.1/M, I still think I'd be using Opus or 5.5 at $30/M. Or say GPT 5 which was released Aug 25, I don't think I'd use it for coding for even $0.1. I'd def find other uses for it(translations, agentic workflows, prompt guards etc), but for coding I don't think I'd ever completely switch to a SOTA open model

Unless ofc there was an actual speed difference, only reason I'd be willing to go with a worse model couple of percent worse than current best model is if the speed was at least 5x higher. Looking forward to kimi k2.6 offered publicly by Cerebras

[kgwgk]

> I still think I'd be using

That's fine. Other people may not want to pay 300x more and will rather make do with last year's SOTA.

> For coding you always want to go with the best model

Maybe you meant "For coding I always want to go with the best model"?

[mesmertech]

Based on current market for LLMs I'd say my use of "you" in the general is fine. Even openrouter which doesn't capture all of the SOTA closed models but nearly all of opensource model usage has Opus as 1st(on last week) on "Programming" category and 3rd in overall rankings

https://openrouter.ai/rankings

[simonw]

I'd trust the OpenRouter rankings a lot more if they exposed the number of unique users for each model, as opposed to just a token count.

Currently I have no way of telling if big changes in their rankings are caused by a single "whale" switching providers, or if it's a more meaningful trend.

[mesmertech]

My point was that even openrouter, the one place people who are looking for open source SOTA models go to, doesn't definitively have opensource models at the top. Esp considering quite a lot of the closed models usage is through AWS, GCP , Azure etc, probably dwarfing the usage on openrouter by a huge factor

[danny_codes]

Why? If it's good enough, it's good enough. Though I read the code that gets vibed so maybe my use-case is different.

[yokoprime]

It's driven a lot by the harness too. If you're using claude code, you're actively being pushed towards newer models, even though older ones work perfectly fine for your use cases

[danny_codes]

Yeah wouldn't touch ClaudeCode when there are so many better harnesses that are free and portable. Seems like a waste of time to learn a proprietary tool when the FOSS ones are better.

[solomatov]

>For coding you always want to go with the best model in the category, not something that would be the best model if we went 1 year back which GLM 5.1 is, and I'm saying that as a big fan of GLM cause I run a translation site where GLM is good enough for the price.

Currently, the difference is substantial, but what happens if capabilities saturate?

[aspenmartin]

Then the house of cards comes crumbling down, but there is so much evidence to point to this not happening that it requires a bit of a theory for how that may happen

[solomatov]

> but there is so much evidence to point to this not happening

Could you explain this?

[aspenmartin]

Well I think there are several fairly stable trends that paint a pretty compelling picture:

- performance scales with compute very very reliably. We have “scaling laws” (and have for years) and they are almost miraculously stable and show no sign of being invalidated at all even at the very largest scales. There are some theoretical bases for this though I’m not as familiar with the details

- these scaling laws are on an unintuitive quantity (validation loss on pretraining datasets), so we can look at downstream performance. Benchmarks are a minefield of junk but there are many decent ones and enough variety of techniques and data sources and scoring methods etc that in aggregate they are useful. The single number that I think is the best summary statistic across the crazy (O(100k)) number of benchmarks is the “epoch capability index” (just some branding over a reasonably standard statistical model that was really well thought out and a great idea). The trends in this are extremely stable. Eyeballing the trend over time on their graph we’re getting basically a GPT-4 to GPT-5 level capability improvement every ~18 months

- coding agents are not limited by the quality of the human training data they’re trained on, this is such a massive misconception: human data is only a bootstrap to a reinforcement learning phase. This combined with the fact that we have verifiable rewards means it’s just a matter of when not if for any given level of reliability.

- the massive compute investment implies that the compute that we’re building over the next 2-3 years will 10x the effective compute for training models. That combined with various R&D contributions (historically which have been very significant and there is no shortage of wins here), better data curation and flywheels, richer data (wait until conversation capability gets good) means we have several orders of magnitude of runway that we know of, today.

In short I don’t see any compelling evidence to suggest all of the trends we observe in many different ways will end any time soon.

[EGreg]

Most work is not coding.

And also, people have it wrong… their models are not the main problem anymore. It’s the RAG

[tomrod]

Would love to hear more about your thought about the RAG.

[simonw]

I think RAG is a mostly outdated concept now, it's been subsumed by the idea of a "agent harness" which is exactly what Claude Code and Claude Cowork and OpenAI Codex and Claude.ai and ChatGPT themselves have now become.

An agent harness with access to a good search tool is a much more interesting thing than 2024-era RAG systems.

[tomrod]

I appreciate where you are coming from, as you have surfed the front of the wave of GenAI for years. From my point of view, there is interesting because something is SOTA, and there is interesting because there is still more to build. I definitely understand state of RAG tech. I also view it as barely utilized versus what we can do with it, hence my question.

Agent harnesses integrated into good search tools are definitely interesting. Knowledgebasing with partitions and similar structure also remains fruitful for applications, above and beyond standard ElasticSearch on a cache.

[Traveler42]

I generally agree with this, but would note that it assumes that the data is accessible from a web search. Some data sources will be private.

[simonw]

You can configure extra search tools that search private data.

[EGreg]

And how exactly does the agent harness surface ALL the right places that need to be updated, and reason about functions and APIs?

[obsidianbases1]

Depending on RAG is a workflow problem, not an AI problem

[Andrex]

> For coding you always want to go with the best model in the category

Will this always be true? There will never be an event horizon/point of diminishing returns where something not-bleeding-edge is "good enough" for 51%+ of users?

[mesmertech]

As long as closed source is 6 months ahead in terms of current difference. Although this is hard to figure out using simple percent based coding benchmarks, you def. notice it when you're actually trying to do a long task. Even simple things like UI "taste" is enough for me to use opus instead of 5.5 though even though 5.5 is strictly better for anything that doesn't have a UI, ie backend, scripts, making agent workflows etc

[blackjack_]

This is a silly take. There is a line of "good enough" for most coding (most CRUD apps and APIs are nothing special), and once we are past that, nobody will care about having the "newest, best" model except extreme outliers. And this base "good enough" model will become an ultra cheap commodity as we already see with GLM, deepseek, etc.

[mesmertech]

As long as closed models are 6 months ahead I won't be switching from them to prev. 6 month SOTA open source models. Maybe its just a different calculation if you're in a job, but as an indiehacker I'll take any edge I can get

Ofc again, can be convinced to switch if there's however a clear speed difference, like 5x+ for a open source sota even if it was SOTA for 6 months ago

[vidarh]

I have stats from a harness that tells me glm5.1 is far more cost effective for us than Opus with the rate of defects and rework taken into account. In fact, with a decent harness I'm now increasingly favouring eHaiku over Opus for execution too. Opus is still worth it for planning, though, and far better at one-shotting things.

[Perz1val]

And you propose the same companies that have been cost cutting and avoiding buying you a chair for ever won't start objecting to a $200/dev/month subscription? The finance department won't have a say?

[r0b05]

Why do need to go with the best model for coding?

[dogleash]

> For XXX you always want to go with XXX, not XXX

Oh, hey, I recognize you. Thank you for the very forward and thorough orbital sander recommendation at Home Depot. That's exactly what I wanted to deal with on my holiday weekend. You just know so much about this and the rest of us are simple passersbys.

[mesmertech]

Yep sorry was just pulling it out my rear, not like a market trend that nearly every enterprise uses Anthropic or Openai models for coding or that Anthropic has had such ridiculous growth that they're 10x-ing year over year

[dogleash]

I'm ribbing you for writing like a condescending guru that invalidates the evaluatory capability of your peers. Not the meat of your evaluation (not to say that it's any good either, just that it's irrelevant).