Skip to content
Source material

Complaints database

29,255 raw documents, unedited and searchable. This is what everything else on the site is built from — nothing here is generated.

  • Hacker News2026-07-09source ↗

    Rewriting Bun in Rust

    I did some more sizeable work with GLM 5.2 on Max reasoning (planning and implementing 8 features end to end) and it performed pretty well, but worse than Opus 4.8, with largely the same adversarial agent review loop. Opus 4.8 still found some real issues afterwards and spent about an hour fixing things, before the co…

  • Hacker News2026-07-09source ↗

    I think I have LLM burnout

    If you can't review the code faster than you could write it yourself, write it yourself.

  • Hacker News2026-07-09source ↗

    Rewriting Bun in Rust

    > The rust compiler is very slow. It's not “very slow”, that's a tired meme. It's slower than it could/should, but complaining about rustc being “very slow” is a clear misrepresentation, especially when everybody seems to have been fine with tsc's historical performance for instance. It could be nice if it was fa…

  • Hacker News2026-07-09source ↗

    Beyond Git: Real-Time Version Control for Godot – Lilith Duncan – GodotCon 2026 [video]

    This is so cool. One of the thing that was truly missing in Godot.

  • Hacker News2026-07-09source ↗

    Rewriting Bun in Rust

    500k lines in 11 days? With 8-hour working days that's 100 lines per minute. There's no way you're comprehensively reviewing code that quickly. The code was generated by a LLM, and the output wasn't even read by its user. That's definitely vibe coding.

  • Hacker News2026-07-09source ↗

    Rewriting Bun in Rust

    > C++ instead of Zig would be a reasonable choice for Bun. We would get constructors & destructors. We could delete lots of extern "C" wrapper code. > But, we would still be reliant on style guides enforced through code review, and even with ASAN, memory corruption and memory leaks would still happen. Tell me you didn…

  • Hacker News2026-07-09source ↗

    Most slopcode projects are abandoned and deleted within months of release

    separate topic, separate comment i agree with your point: "we" always wrote code and abandoned it the claim here is made against flatpak submissions, which involve pr reviews i think a point being missed is that open source has always written code that was going to be reused by corps, but PRs in it were likely to help…

  • Hacker News2026-07-09source ↗

    I think I have LLM burnout

    I'm building something for that. I've taken a bit longer than I wanted but it will be open sourced soon. It's a durable orchestration engine that takes in specs/requirements and coordinates agents externally (meaning the engine drives the loop, not an agent) until the work is fully implemented/verified and r…

  • Hacker News2026-07-09source ↗

    Most slopcode projects are abandoned and deleted within months of release

    let's be clear op doesn't provide code, so my effort stays at throwing in a claude session and providing code without ANY review trust my numbers as much as you usually trust claude code trust the original numbers as you usually trust no code yes unfortunately there is no baseline once you get past the article reporti…

  • Hacker News2026-07-09source ↗

    We made Grok 4.5, GPT-5.5, and Claude build the same apps

    Half year ago I tried to use Codex, Claude and Gemini build the same scripts to automate various things on my machine. Claude was the clear winner back then, making the most reasonable assumptions, presenting results in the easiest-to-read format, writing runnable script with minimum dependency. Half year later I thin…

  • Hacker News2026-07-09source ↗

    I Think I Have LLM Burnout

    Current AI is like the film company producing TV series or movies Review AI code line by line is like watch movies frame by frame, and is impossible, very difficult, terribly boring, or abandoned sooner or later.

  • Hacker News2026-07-09source ↗

    I think I have LLM burnout

    > My job has changed from designing and writing code to designing code, describing the design to an LLM, reviewing code the LLM produces As a long-time engineering manager, PM and, eventually, product owner my response is, "Congrats! You've just been promoted to management." :-) As a new manager, your first challenge…

  • Hacker News2026-07-09source ↗

    I think I have LLM burnout

    From my experience, there are mainly 3 burnout reasons. 1. Multi-tasking is the top one. I usually have to frequently switch between 3 to 5 agent windows which are on different things. It's extremely exhausting when each round takes a few minutes. Before coding agent era, I believe most developers had chance to spend…

  • Hacker News2026-07-09source ↗

    FAANG Simulator

    > things like employer matches in retirement accounts seems completely reasonable to model this as income. > health insurance contributions If your employer provides a health insurance benefit that would otherwise cost you $X / yr, you could model that as +$X / yr income and +$X / yr expenses. Simple FI…

  • Hacker News2026-07-09source ↗

    Ask HN: Is anyone experimenting with different ways of using LLMs for coding?

    The tab model makes sense here: with Claude Code or Codex, the bottleneck often isn’t generation speed, it’s the constant context-switching between waiting, reviewing, and re-prompting.

  • Hacker News2026-07-09source ↗

    China sentences official to death for taking $325M in bribes

    I've spent a lot of time in the EU working with tech companies, have a lot of friends there in tech companies and am on the board of a Swiss company at the moment. While it's true the average corporate worker generally has more protected rights in the EU, in my experience that additional government regulation doesn't…

  • Hacker News2026-07-09source ↗

    I think I have LLM burnout

    I do not have the burnout but I certainly operate similarly to the author. I continue to be unable to establish a workflow where allowing the LLM to generate code that I review is faster than writing the code myself. Literally the only two ways out of this dilemma is to blindly trust what was generated or to generate…

  • Hacker News2026-07-09source ↗

    A Roomba recorded a woman on the toilet. How did screenshots end up on Facebook? (2022)

    Article spends many words on [training during product development] and few words on [security issues with devices sold to consumers]. Risks are the exact opposite. 'Guinea pigs' in this case were company employees, who at least gave permission to be recorded. And aware of that. Consumers often don't give such permissi…

  • Hacker News2026-07-09source ↗

    Rewriting Bun in Rust

    I have found LLMs struggle with Rust's constraints - they are optimized to produce code that passes the tests, not necessarily good code. So instead of working out lifetimes and borrowing, it will be happy to copy a buffer many times without thought. This means I have to still go through line by line to review and oft…

  • Hacker News2026-07-09source ↗

    Rewriting Bun in Rust

    Sure, reasonably well at first glance, but to quote the article: > I rewrote Bun in Rust using about 50 dynamic workflows in Claude Code run continuously over the course of 11 days. > Excluding comments, Bun is 535,496 lines of Zig. > How do you review a PR with +1 million lines added? How do you start to build the co…

  • Hacker News2026-07-08source ↗

    Rewriting Bun in Rust

    > to exhaustively come up with reasons why the changes create bugs or do not work My biggest issue currently, is I can't seem to get a code review that's about the simplicity of the code, and no /simplify ain't it. Removing certain bugs and generally working seems to be doing alright, especially if it's following…

  • Hacker News2026-07-08source ↗

    The classifiers Anthropic puts in front of Fable are too zealous

    Try asking it to do a simple code review. Literally no prompt other than their own code-review skill. It triggers a safety flag almost 80-90% of the time.

  • Hacker News2026-07-08source ↗

    Grok 4.5

    > You use the previous gen model to prepare datasets for the next model iteration I've read multiple times that this approach is harmful in training. You're essentially describing what many call distillation, but it's only useful in post training to guide behavior, it teaches how to behave, not how to think. I might b…

  • Hacker News2026-07-08source ↗

    Tenda firmware (multiple versions) contains hidden authentication backdoor

    > I assume it's probably a software bug, they assume it's an exploit. They're not mutually exclusive. I suspect you and the security team are arguing the same thing but with different terminology. When vulnerabilities (which, in the vast majority of cases, are accidental) are published, or when static analysis tools r…

  • Hacker News2026-07-08source ↗

    Separating signal from noise in coding evaluations

    Either DeepSWE [0] or FrontierCode [1], depending on personal goals and requirements. The later is more interesting for me personally, due to the design of the benchmark heavily grading "mergability", i.e. how the provided output is to review and whether a serious developer can easily parse it and'd be willing to merg…

  • Hacker News2026-07-08source ↗

    Python 3.14 compiled to metal – no interpreter

    I've been doing some reading recently around what the literature expects a professional software engineer to produce in a day. In ~1976 Mythical Man Month era it was around 5 lines of fully debugged assembly. Code Complete 2nd edition ~2004 bumped that up to 10-50 delivered lines of code per day. I found other estimat…

  • Hacker News2026-07-08source ↗

    Fable is not a useful model

    I've had mixed results with downgrading on Fable. I was able to do a complete audit of my OAuth implementation without any issue. But when I asked for an OWASP top-ten review of my code base it got through 5 of 6 tasks and tripped in the final summary, which Opus had to finish. I had one completely random trip when I…

  • Hacker News2026-07-08source ↗

    The classifiers Anthropic puts in front of Fable are too zealous

    I'm working on cryptography, all from academic research papers. Started well, but it eventually got some word into its context that is on the banlist. I found that if you tell it to fire off clean Fable subagents and you instruct it to check the Claude Code billing data to check for downgrades, you can get most high-s…

  • Hacker News2026-07-08source ↗

    OpenBSD has a use-after-free allowing local privilege escalation to root

    I suspect the easier option is to use AI to review your own code. The arms race between developers and attackers might even make some of the AI valuations come true.

  • Hacker News2026-07-08source ↗

    TypeScript 7

    I've been writing code since the 80s, professionally since the mid 90s, in almost every major language, platform and operating system, from 8 bit microcontrollers to large scale web platforms. So, not sure that counts as "serious" in your estimation, but I would definitely argue that dynamically typed languages are su…