tecoholic

Along this line of thought. I think the "internal tools" product category is dead. I remember trying to deploy one of these things - Tooljet, Retool.. I can't remember exactly, and thinking, maintaining the stack and the tools is not worth the effort. But then I didn't work in a big enterprise company. So maybe others had a reason or manpower to maintain them. Now I doubt anyone wants a programmable drag and drop form builder - aka no-code/low-code software factory.

He should be, right? Not fair but that’s how liability works. Gym sues the guy using AI, the guy then sues the AI company for selling him a product that does criminal things without him asking to? Like a car accident where car owner pays for the damages and after multiple accidents involving the same break-pedal, car company pays damages to owners and does a recall or faces class action?

Seeing Nix these days is such a whiplash experience. We have fully deterministic systems and then we have LLMs. God ;)

Let me share 2 words - Doom Emacs, Spacemacs.

I am with you. For example - this post has a comparison of a recipe app from 5.6 and 6 for comparison. They look different. Now if every time I ask for a recipe, it decides to render a new UI because of either the model changing or the recipe goes from stove to oven or something, it’s going to become annoying very quickly. It just seems like he current generation of models have been tuned to create better UIs than previous one and people interested in the UI are getting hit with excitement.

One thing I don’t get about “personal software” is - why would you want something photoshop shaped, when you can describe what your image should look like? Most common issue - passport photos with specific background requirements and aspect ratios. Just take a photo on your phone, ask Gemini to meet the specs - you are done.

Wow. This is genuinely the first time I have come across this idea. Are there Kernels build to be completely async? I understand they would be experimental. And the whole stack runs in a async environment from say the web server rendering templates - down to the kernel loading data into the cpu cache? Does it offer performance advantages? I got so many questions…

There was a Jon Stewart podcast on this a couple of weeks ago on Machine Learning and custom pricing. It was an illuminating one. It all looks like a lead up to big consumer action and lawsuit in the future. TBH, McDonald’s pricing might survive as it seems to charge the same for everyone at the same store.

Go to gnome.org, scroll down to "Developer Platform" and look at the title bar of the screenshot there. If you see a clean interface, then no reason other people give you will help.

But, if you do see the arrows there and think - why are there so many arrows and dots? It looks like bad UX. They you can see the issues others are talking about.

Short answer is GitOps. Other reasons include ghost services in nomad, random CSI volume lock-ups (which might just be AWS's fault), lack of deployment options for self-hosting 3rd party applications. K8s Helm charts are available for everything and ArgoCD visibility with SSO makes everything easy to see.

I think you are right. The memory of an empty claude.ai session is more than Slack in my browser right now. Just trading places.

Great! Now can you also optimize the memory usage please?

The blog post with all of the images, animations and embeds shows 167MB on my Firefox tab, while a plain claude.ai page is 297MB. For a text box with a few icons and some words, it a heck a lot of bloat.

For context, my Slack tab with "Threads" open is 239MB. Yup, Slack of all things is using less memory than a zero-chat Claude.ai landing page.

Similar to what others have said, we have had big changes in our systems, thanks to LLMs. Some examples of what we have done:

  - Rewrote a data extraction and PDF bounding box algorithm - LLM provided the tooling to visualize the output of algorithm and find the right rules for our needs.
  - Migrated an old SciBERT model that was bundled into a 6GB docker container that needed GPU, with to an ONNX based inference container about 900MB running on CPU.
  - Setup a K3S cluster to replace our Nomad cluster.
  - Optimized an algorithm that used SQLite with better indexes and optimized querying with some 60-80% performance gains.

We have reduce resource usage in specific areas of the application drastically. These were all possible before, but LLMs provided the tooling to iterate and deliver it in time and cost that seemed prohibitive before.

Now are the end users going to see the benefit and is the product magically better? Well no. The chicken answer is I am not involved in that side to know. But a more realistic answer is, user experience and product fit is not something LLMs can solve. That's still upto the humans to figure out and I think that's where this "nothing has improved" feeling comes from.