Corporations are already pulling back from using expensive SotA closed models. The buffet is open weight. Just look at Databricks as an endpoint provider for both open weight and closed LLMs. Companies will utilize what is cheaper and does the job. We all know the market pressure is real and present. What has become truly apparent is that when (not if) mythos class open weight models get released, if cybersecurity folks and developers have no access to use them to help harden and guard infrastructure, it leaves the gates wide open to attach vectors which will not be defensible. This is the real danger that the vast majority of corporate entities should be caring about. Shutting down open models is setting up for serious security concerns.
The OpenAI/Huggingface debacle is patient-zero. Huggingface used GLM 5.2 to help mitigate and were unable to use more capable closed sota models for the analysis due to guardrails. It is a foot gun of the highest order. We should all be concerned. I feel like Captain Obvious saying this.
I had created my own chat tool that can render html responses directly in the chat interface, if needed. It is very handy for when I am needing rich(er) responses dealing for mathematical expressions. But it burns more tokens. It is useful, but I don’t need it for coding.
About 20 years ago I maintained a shop floor control client/server application. I asked my manager why we didn't have any independent Q/A. He said we didn't need any testers because we have 500 in the building.
Ugh, memories. I'm so old my first web browser was Mosaic and I think I saw this. I used a provider called Texas MetroNet that served up dial-up PPP connections for $45 a month on a speedy 28.8K baud modem. Days of wonder, I tell ya.
New days of wonder seem to be ahead, though. That said, there's about 100X more angst involved these days.
On a related note, when the sales and popularity of the automobile really started to take off, some farmers and rural residents would deliberately block roads with wagons and refused to yield right-of-way.
Ask this question in the 1940s and they would tell you it’s math. We are making machines that do math to kill Nazis. Now take this vacuum tube and plug it in over there and then go get me a cigarette.
It is like SQL injection. Probably worse. If you are using unsupervised data for context that ultimately generates executable code you will have this security problem. Duh.
It was kind or that way in early days of high end personal computing. I remember seeing an ad in the early 90s for a 486 laptop that was $6,000. Historically prices have always gone down. You just have to wait. SoTA is always going to go for a premium.
Yeah, the problem is if you don't understand the problem space then you are going to lean heavy on the LLM. And that can lead you astray. Which is why you still need people who are experts to validate solutions and provide feedback like Op.
My most productive experiences with LLMs is to have my design well thought out first, ask it to help me implement, and then help me debug my shitty design. :-)
DRY is more about support and maintenance than anything else.
I see a lot of attacks on DRY these days, and it boggles my mind. Maybe it is being conflated with over-engineering/paramterization/architecting. I don't know.
But I do know that having to fix the same bug twice in the same code base is not a good look.
I experimented with cc65 and wrote a simple game that ran on my actual C64 hardware. It was a lot of direct memory access, unrolling loops, and avoiding stack usage. A fun time overall, and it ultimately ran smoothly, but I see do why people who attempt anything serious on a C64 tend to focus on using ASM.
That is correct. I have lived in Tornado Alley for a half century. Serious tornadoes have landed all over my local area over the years, but I have also never even seen so much as a funnel cloud. They can be devastating though, but are also very localized and do not last long. That said, I do take tornado alerts seriously.
The OpenAI/Huggingface debacle is patient-zero. Huggingface used GLM 5.2 to help mitigate and were unable to use more capable closed sota models for the analysis due to guardrails. It is a foot gun of the highest order. We should all be concerned. I feel like Captain Obvious saying this.