Hacker News: aforwardslash

New comment by aforwardslash in "ProgramBench: Can language models rebuild programs from scratch?"

aforwardslash — Thu, 07 May 2026 20:58:47 +0000

Yes, something like "analyze throroughly the @datasheet.pdf and create a plan to implement x"

New comment by aforwardslash in "ProgramBench: Can language models rebuild programs from scratch?"

aforwardslash — Thu, 07 May 2026 08:18:16 +0000

They are - probably more proficient than with some high-level languages. I've used it for embedded stuff, including TI sitara PRU assembly, with great results. Frontier models can also easily "learn" directly from the manuals; asm is quite easy for them to pick up due to its "flat" (non-structured) nature.

New comment by aforwardslash in "Ghostty is leaving GitHub"

aforwardslash — Wed, 29 Apr 2026 00:47:21 +0000

Funny how windows updates are never postponed for lack of "scaling". I know, I know, completely different stuff here - but arent test vms and ci vms being updated constantly?

Im old enough to remember the hotmail migration to win2k (then 2k3) and the postmortem. I was also old enough to look at the rotor source code. Yah, that one, running managed code in freebsd.

New comment by aforwardslash in "Ghostty is leaving GitHub"

aforwardslash — Wed, 29 Apr 2026 00:41:49 +0000

Im still waiting for... Basically anyone that has used TFS (what microsoft had/pushed before acquiring github) to do a similar post, detailing how they miss the tool original concept. I'm sitting down, don't worry about me.

New comment by aforwardslash in "Ghostty is leaving GitHub"

aforwardslash — Wed, 29 Apr 2026 00:34:35 +0000

We all understand that. We had some piece of software we still cling on to it (in my case is a copy of paint shop pro 5, corel draw 7 and Delphi 7), despite being completely obsoleted or assassinated by "big industry". I could add CoolEdit 2000 to it, but havent really opened it in a decade.

To be honest, I never understood the fascination with github. Its a hub, of git repos. Not to piss on your parade, because your complaints are valid, but maybe isnt github that as gone sour as much as you have grown out of it. This was your passion, now its over and you move on.

New comment by aforwardslash in "Agentic AI systems violate the implicit assumptions of database design"

aforwardslash — Sun, 26 Apr 2026 23:43:41 +0000

Wide tables and rich data. Dozens to hundreds of columns, some of them a json dimension. Way easier to explore these datasets with AI

New comment by aforwardslash in "Agentic AI systems violate the implicit assumptions of database design"

aforwardslash — Sun, 26 Apr 2026 23:39:37 +0000

How is this different from "people that cant write sql should not use orms"? With code agents you can write raw sql better than most developers; and if you want, you can basically ask for the same implementation using whatever orm you want. Lastly, AI generated code is supposed to be reviewed by a human, just like code done by your colleague. Thing is, with AI, you can establish automatic review guidelines, and even ask for proper benchmarks and optimizations, at zero cost.

New comment by aforwardslash in "I cancelled Claude: Token issues, declining quality, and poor support"

aforwardslash — Sat, 25 Apr 2026 01:19:12 +0000

One of the simple "reasons" is to keep context clean; if you're doing planning, you're not loading source code, its just the plan. Also, it may happen that if you're running parallel manual sessions, cache expires after 1h, so a prompt on an idle session will re-trigger re-evaluating the whole context (something quite heavy on a 1M context window). This burns a lot of credit.

New comment by aforwardslash in "I cancelled Claude: Token issues, declining quality, and poor support"

aforwardslash — Sat, 25 Apr 2026 01:14:29 +0000

> It is NOT the way to work with humans basically because most software engineers I worked with in my career were incredibly smart and were damn good at identifying edge cases and weird scenarios even when they were not told and the domain wasn't theirs to begin with.

I have no clue what AI you're using, but both Claude and Codex, you just explain the outcome, and they are pretty smart figuring out stuff on complex codebases.You don't even need a paragraph, just say "doing this I got an error".

> NO guarantee either because these models are NOT deterministic in their output. Same prompt different output each time.

So, exactly like humans. But a bit more predictable and way more reliable.

> That's why every chat box has that "Regenerate" button.

If you're using the chat box to write code, that's a human error, not an LLM one. Don't blame "AI" for your ignorance.

> no matter how smart and expensive the model is, the underlying working principles are the same as GPT-2.

Sure. Every machine is a smoke machine if operated wrong enough. This tells me you should not get your insight from random YT videos. As a bit of nugget, some of the underlying working principles of the chat system also powered search engines; and their engineers also drank water, like hitler.

New comment by aforwardslash in "I cancelled Claude: Token issues, declining quality, and poor support"

aforwardslash — Sat, 25 Apr 2026 01:01:20 +0000

Have you created a plan where the requisite is not to bother you with x and y, and to use some predetermined approach? What you describe sometimes happens to me, but it happens less when its part of the spec.

New comment by aforwardslash in "I cancelled Claude: Token issues, declining quality, and poor support"

aforwardslash — Sat, 25 Apr 2026 00:58:42 +0000

It boils down to scope. I use CC in both very specific one-language systems and broad backend-frontend-db-cache systems. You can guess where the difficulty lies. (Hint: its the stuff with at least 3 distinct languages)

New comment by aforwardslash in "How to be anti-social – a guide to incoherent and isolating social experiences"

aforwardslash — Sat, 25 Apr 2026 00:52:47 +0000

> Is it more important to be right, or to be happy?

Im going out on a limb here, but I'd say intelligent people will tell you - without a doubt - being right. Because being happy is a perception and always a transitive state. There's nothing holding you from being both right and happy.

> Nobody likes to be told they're wrong

Thats actually a southern european way of looking at things; Its a cultural trace that varies a lot by region. Pointing flaws in plans is actually something I saw as worthy of an appraisal in Germany.

Also, I always tell people when I think they are wrong. I no longer insist or argue, just point out what lead me to the conclusion; you don't want to be in the blast radius of a deaf manager, an incompetent colleague or a delusional partner. Win-win.

New comment by aforwardslash in "How to be anti-social – a guide to incoherent and isolating social experiences"

aforwardslash — Sat, 25 Apr 2026 00:41:01 +0000

Sometimes you just have to implement them :)

New comment by aforwardslash in "How to be anti-social – a guide to incoherent and isolating social experiences"

aforwardslash — Sat, 25 Apr 2026 00:39:16 +0000

> a senior member of my team expressed the view that he'd rather someone spend three days researching than ask him a thirty-second question

I have never met a senior that would dare to take such a stance; he may be willing to learn, but we will not both cover his knowledge gap and improve his own cv at the company expense. I have no idea if you are competent or not, but it doesnt really matter if you are the one deciding. Its not a democracy, and sure as hell its not amateur day. He will do as he is told, or he will find a more suitable team elsewhere. Have no tolerance for divas, they bring zero value.

New comment by aforwardslash in "XOR'ing a register with itself is the idiom for zeroing it out. Why not sub?"

aforwardslash — Wed, 22 Apr 2026 20:26:28 +0000

Afaik xor reg,reg is optimized by the cpu as zero-out reg; sub reg, reg is quite more difficult to optimize this way; this seems to be quite important in modern cpus, where cisc is translated to micro-ops; in superscalar archs, this is probably optimized away instead of causing a stall.

New comment by aforwardslash in "S3 Files"

aforwardslash — Wed, 08 Apr 2026 04:54:35 +0000

Depends how you implement the fs layer on top of s3; as a quick example, I've done a couple of implementations of exactly that, where a file is chunked into multiple s3 objects; this allows for CoW semantics if required, and parallel upload/downloads; in the end it heavily depends on your use case

New comment by aforwardslash in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

aforwardslash — Mon, 06 Apr 2026 20:02:23 +0000

Its not about prompting; its about planning and plan reviewing before implementing; I sometimes spend days iterating on specification alone, then creating an implementation roadmap and then finally iterating on the implementation plan before writing a single line of code. Just like any formal development pipeline.

I started doing this a while ago (months) precisely because of issues as described.

On the other hand,analyzing prompts and deviations isnt that complex.. just ask Claude :)

New comment by aforwardslash in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

aforwardslash — Mon, 06 Apr 2026 19:47:22 +0000

That is generically my experience as well. Claude half-assing work or skipping stuff because "takes too much time" is something I've been experiencing since I started using it (May 2025). Forcing it to create and review and implementation plan, and then reviewing the implementation cross-referenced with the plan almost always produces consistent results in my case.

New comment by aforwardslash in "Why I love FreeBSD"

aforwardslash — Tue, 17 Mar 2026 08:22:19 +0000

Right, because linux security == init system used by some distros. My experience with FreeBSD may be somewhat dated (I've used it since the 4.x days, provided commercial support for it for more than 15 years), an that is not my experience - at all. Obviously, it depends on the threat model you are considering and how far you want to go. The default install does not have (or had) sane security defaults, at least comparing to your random $ystemd linux distro; try installing both and give local shell to a red team and see how fast they get root access.

New comment by aforwardslash in "Why I love FreeBSD"

aforwardslash — Mon, 16 Mar 2026 22:33:02 +0000

Rule of thumb, its not. Common stuff like address randomization is a recent default, afaik still doesnt have random process ids, and the base permissions arent stellar. However I would prefer jails any day of the week vs the clusterf** that are namespaces and cgroups.