Viewing profile — computerex

Absolutely. Although DeepSeek started announcing "Peak valley" pricing which started making me nervous. I have spent $50 usd in July on deepseek and for that much spend I got SO MU…

Not really. I test the output thoroughly, I examine the thinking process, I go through the diff to see if anything jumps out but I my thinking process/the way I work has changed. L…

I think it's because python is far more approachable/ubiquitous than go/rust. It's the entry level language for many people from all disciplines of life. Scientific community uses …

People know it’s happening. What do you expect an average consumer to do about it? Pay more out of pocket due to the potential national security risks?

I know GLM is relatively expensive and so is Kimi, in comparison to those DeepSeek V4 pro and flash are a godsend and are absolutely good value.

That’s not remotely true. They did distillation as a cheap solution to the cold start problem. You need data/trajectories to hill climb to higher capabilities. All large Chinese la…

Why not ? They are relatively easy to make so why not. Even I made one: https://github.com/computerex/z

Not really. I have spent 163M deepseek v4 flash tokens in July and it literally just started. https://i.postimg.cc/MHhgwsv0/image.png

It's for mathematics. There is this programming language: https://lean-lang.org/ If you can express a solution in Lean you can formally prove or disprove it. Formal verification is…

You may be ok with the harness doing 100 things that are not what I am using it for. But none everyone is, and it’s hardly hysterical. Perhaps you are simply careless.

I made my own! https://github.com/computerex/z

Llama was great for research and propelling the opensource community but they haven't been a serious competitor in a while. Whereas Google is one of the top 3 AI labs in America.

I don't want my harness doing sneaky stuff like this. I don't want my harness data mining me. I want my harness to implement the agentic loop and I want it to be transparent.

To be honest, OpenCode on Windows has not been the most pleasant experience either.

I have had bad experience with neuralwatt GLM 5.2. Seems like they may be using quantized version of the model.

It's very simple. I have told Claude that it's my chief of staff and that it must delegate all tasks to subagents. That as my COS it must show initiative and only come to me for vi…

I work in a completely different manner. I have a chief of staff agent, which is one Claude code instance that orchestrates work across all my projects simultaneously with sub agen…

[flagged]

> And in any case, why do people keep leaving those satisfactory countries for America? https://www.census.gov/newsroom/blogs/random-samplings/2026/... America used to be a great p…

Your point is totally and completely wrong. Germany has public benefits that actually matter. Germany's average life expectancy is ahead of Mississippi by *10 years*. Germany ranks…

Except capitalism is a zero sum game. The two people you talk about that are multimillionaires are lucky. For each person you know that has made it, there are thousands of people t…

How facetious. Are you really comparing LLMs to random word picker? What a poor counterargument.

My argument is that randomly accusing something of being AI and pretending that it's bad merely because you think it's AI, is not good/good faith. Whether you think some writing is…

Your argument is basically ad hominem. Ideas should be evaluated on merit.

I think you are going by vibes.