I've got an agent in a loop optimizing a renderer with the goal to minimize frame times (and tests to measure). It got times down from 88ms to 2ms and allocations down from ~150K to 500. Sounds good, right? Wrong. This is exactly why agent psychosis is a big fucking problem. As an experiment, I rewrote the Ghostty core render state in Go, with access to identically laid out data structures as Ghostty and the exact same validation tests. I made a purposely naive renderer (simple, correct, but slow). 88ms per frame with 150,000 allocations (horrendous, lol)! I then kickstarted a Ralph loop to bring the frame times down. I told it it can't modify input data structures or the public API or tests (they're correct), but it can do anything else it wants. It got to work. It has worked for about 4 hours. I've spent around $350 on this experiment so far. The results? 88ms => 1.5ms 150K allocs => ~500 allocs Incredible right? Nope. My hand-written renderer I ported has frame times (same benchmark) of ~20us (0.020ms) and 0 allocations in the update path. This is the problem with psychosis and lacking systems understanding. If you don't understand the system, you're going to accept that this is an incredible result. If you understand the system, you'll see better solutions immediately and can do roughly 75x better on throughput. The people who blindly trust agent output are in the former camp. They're sheeple, overdrinking from a fountain of mediocrity. Standard disclaimer: I use AI all the time. I like AI. The point I'm making is to not blindly accept results. Think. Analyze. Learn.

Watching CI/CD mind virus dying in real time

desperately want Odin or Zig to feel as ergonomic as Go for writing web servers with a frontend

I was testing Deepseek V4 Flash running locally building something, and I forgot I wasn't using a cloud model. It was doing things fast and well enough that it felt normal. First time that's happened.

Converting nearly all of Bun from Zig to Rust in just 6 days is undeniably impressive no matter what your opinion on either language or agentic coding is.

作为一个写了二十多个rust库的人，我越来越不喜欢这个语言，这个语言的膨胀能力比其他语言是次方级别的 当我的代码量超过3万行的时候，调整代码需要1分钟不到，然后cargo test、 build等要10分钟，并且这个时间算短的 而且这是一个非常吃硬盘的语言，你随便写写东西，build一下，几个g就没了，开几个worktree轻松吃掉百G空间 当然性能上如果是直接和ts对比，绝对是秒杀，但和go比起来，他没有那么大的优势，go的编译很快，几万行代码也很快

someone asked Beej how sockets work in C. he got tired of explaining it. so in 1995 he put it all online. it's been the definitive socket programming guide for 30 years. it covers everything: TCP, UDP, IPv4, IPv6, non-blocking I/O, select(), poll(). graduate OS courses worldwide assign it. it's funnier than any technical book has a right to be. it's free and always will be.

i never make plans i hate looking at markdown i don't wanna read markdown files i just plan by having it make changes to the code then i look at the code to see what sucks then i prompt again

They call them SPAs because every time you hear about another RSC vulnerability you can just continue to relax

Opencode x Deepseek v4 pro x High 800 million tokens = $10 The Chinese can have all my data

Why are you still using React when you could use ArrowJS instead? arrow-js.com

Facts dont care about your feelings

Crazy how backwards this is. The "yes guy" is now in infinite supply, just type `claude` and you've got a new one. The "no guy" is the one in demand: the one who points out all the problems with all the slop your slopcannons are trying to merge to prod.

The programming language is English but the compiler is very creative and becomes unavailable after a while 😬

How it started. How it is going.

Its the beginning of the end of subsidized AI subscriptions. GH Copilot is moving to usage-based billing, as has Claude (for business customers.) Fair to assume more will follow. I expect this change will also be a great boost for open models - cheaper, and pretty good already

looks like token subsidization is ending GitHub Copilot is going to start charging API model pricing

To everybody's surprise, you cannot build a complex successful production app with 0 employees and $200 claude code.

it’s official - china’s fucking dominating AI. they’ve caught up. new DeepSeek v4 matches GPT-5.5, costs 86% less. 100% open source. don’t take my word for it: -> deepseek v4 flash is 99% cheaper than opus 4.7 (not a typo). $0.28 per million tokens -> ranks #1 on code forces benchmark beating gpt 5.4. competitive to 5.5 and opus. in the last week: → Mon: Moonshot drops Kimi K2.6 → Wed: Alibaba drops Qwen 3.6-27B → Thurs: DeepSeek drops V4 3 chinese labs, 3 frontier OPEN source models in < 4 (FOUR) days there is no way you can argue china hasn’t caught up. gg

deepseek v4 is now the cheapest sota model available at 1/20th the cost of opus 4.7. for perspective, if uber used deepseek instead of claude their 2026 ai budget would have lasted 7 years instead of only 4 months.