281–290 of 765 posts
That PR is a maintainer's nightmare. "Here's a massive bunch of AI generated code. LGTM. Let me know if there are any problems"
The code had tests, which is the real-world check against bad code, both AI and human written.
Tests is just one part of QA. Code review is another.
> 99% of the code in this PR [for llama.cpp] is written by DeekSeek-R1 I hope we can put to rest the argument that LLMs are only marginally useful in coding - which are often among the top comments on many threads. I suppose these arguments arise from (a) having used only GH copilot which is the worst tool, or (b) not having spent enough time with the tool/llm, or (c) apprehension. I've given up responding to these.…
> 99% of the code in this PR [for llama.cpp] is written by DeekSeek-R1 I hope we can put to rest the argument that LLMs are only marginally useful in coding - which are often among the top comments on many threads. I suppose these arguments arise from (a) having used only GH copilot which is the worst tool, or (b) not having spent enough time with the tool/llm, or (c) apprehension. I've given up responding to these.…
I’m still just looking for a good workflow where I can stay in my editor and largely focus on code, rather than trying to explain what I want to an LLM. I want to stay in Helix and find a workflow that “just works”. Not sure even what that looks like yet
> 99% of the code in this PR [for llama.cpp] is written by DeekSeek-R1 I hope we can put to rest the argument that LLMs are only marginally useful in coding - which are often among the top comments on many threads. I suppose these arguments arise from (a) having used only GH copilot which is the worst tool, or (b) not having spent enough time with the tool/llm, or (c) apprehension. I've given up responding to these.…
If AI increases the productivity of a single engineer between 10-100x over the next decade, there will be a seismic shift in the industry and the tech giants will not walk away unscathed. There are coordination costs to organising large amounts of labour. Costs that scale non-linearly as massive inefficiencies are introduced. This ability to scale, provide capital and defer profitability is a moat for big tech and th…
I hate the idea of building a business to hundreds/thousands of employees, I love startups and small but highly profitable businesses.
Having productivity be unleashed in this way with a small team of people I trust would be amazing.
> 99% of the code in this PR [for llama.cpp] is written by DeekSeek-R1 It's definitely possible for AI to do a large fraction of your coding, and for it to contribute significantly to "improving itself". As an example, aider currently writes about 70% of the new code in each of its releases. I automatically track and share this stat as graph [0] with aider's release notes. Before Sonnet, most releases were less than…
> 99% of the code in this PR [for llama.cpp] is written by DeekSeek-R1 you're assuming the PR will land: > Small thing to note here, for this q6_K_q8_K, it is very difficult to get the correct result. To make it works, I asked deepseek to invent a new approach without giving it prior examples. That's why the structure of this function is different from the rest. This certainly wouldn't fly in my org (even with test c…
> This certainly wouldn't fly in my org (even with test coverage/passes).
To be fair, this seems expected. A distilled model might struggle more with aggressive quantization (like q6) since you're stacking two forms of quality loss: the distillation loss and the quantization loss. I think the answer would be to just use the higher cost full precision model.
For what i can understand, he asked deepseek to convert arm simd code to wasm code. in the github issue he links he gives an example of a prompt: Your task is to convert a given C++ ARM NEON SIMD to WASM SIMD. Here is an example of another function: (follows a block example and a block with the instructions to convert) https://gist.github.com/ngxson/307140d24d80748bd683b396ba13b... I might be wrong of course, but ask…
That said, translating good code to another language or environment is extremely useful. There’s a lot of low hanging fruit where there’s, for example, an existing high quality library is written for Python or C# or something, and an LLM can automatically convert it to optimized Rust / TypeScript / your language of choice.
Earlier quoted context omitted.
> If anything we're the last generation that knows how to debug and work through issues. I suspect that comment might soon feel like saying "not too worried about assembly line robots, we're the only ones who know how to screw on the lug nuts when they pop off"
I don't even see the irony in the comparison to be honest, being the assembly line robot controller and repairman is quite literally a better job than doing what the robot does by hand. If you're working in a modern manufacturing business the fact that you do your work with the aid of robots is hardly a sign of despair
I think what we're all learning in real-time is that human technology is perpetually aimed at replacing itself and we may soon see the largest such example of human utility displacement.
Earlier quoted context omitted.
I don’t understand. When I asked DeepSeek how to find AWS IoT Thing creation time it suggested me to use “version” field and treat it as a Unix timestamp. This is obvious nonsense. How can this tool generate anything useful other than summaries of pre-existing text? My knowledge of theory behind LLMs also suggests this is all they can do reasonably well. When I see claims like this I suspect that either people around…
You're making the mistake of treating an LLM like a search engine, and expecting it to be able to answer questions directly from its training data. Sometimes this works! But it's not guaranteed - this isn't their core strength, especially once you get into really deep knowledge of complex APIs. They are MUCH more useful when you use them for transformation tasks: feed in examples of the APIs you need to work with, th…
There is a space for learning materials here. I would love to see books/trainings/courses on how to use AI effectively. I am more and more interested in this instead of learning new programming language of the week.
Earlier quoted context omitted.
> it isn't entirely bluster "Development" is effectively translating abstractions of an intended operation to machine language. What I find kind of funny about the current state is we're using large language models to, like, spit out React or Python code. This use case is obviously an optimization to WASM, so a little closer to the metal, but at what point to programs (effectively suites of operations) just cut out t…
I've wondered about this too. The LLM could just write machine code. But now a human can't easily review it. But perhaps TDD makes that ok. But now the tests need to be written in a human readable language so they can be checked. Or do they? And if the LLM is always right why does the code need to be tested?
Earlier quoted context omitted.
"Jobs are going to be lost unless there's somehow a demand for more applications." That's why I'm not worried. There is already SO MUCH more demand for code than we're able to keep up with. Show me a company that doesn't have a backlog a mile long where most of the internal conversations are about how to prioritize what to build next. I think LLM assistance makes programmers significantly more productive, which makes…
> There is already SO MUCH more demand for code than we're able to keep up with. Show me a company that doesn't have a backlog a mile long where most of the internal conversations are about how to prioritize what to build next. This is viewing things too narrowly I think. Why do we even need most of our current software tools aside from allowing people to execute a specific task? AI won't need VSCode. If AI can short…
But the bit of data we got in this story is that a human wrote tests for a human-identified opportunity, then wrote some prompts, iterated on those prompts, and then produced a patch to be sent in for review by other humans.
If you already believed that there might be some fully autonomous coding going on, this event doesn’t contradict your belief. But it doesn’t really support it either. This is another iteration on stuff that’s already been seen. This isn’t to cheapen the accomplishment. The range of stuff these tools can do is growing at an impressive rate. So far though it seems like they need technical people good enough to define problems for them and evaluate the output…