Hacker News: reedlaw

New comment by reedlaw in "Caveman: Why use many token when few token do trick"

reedlaw — Sun, 05 Apr 2026 19:28:18 +0000

Chinese omits articles, verbs aren't conjugated, and individual characters carry more meaning than English letters, but other than those differences I don't have the impression that Chinese communication is inherently more concise. Some forms of official speech are wordy. Writing is denser, but the amount of information conveyed through speech is about the same. There are jokes about ambiguous words or phrases in both Chinese and English. So I was surprised at your take, but no objection to your points above. Ancient Chinese, on the other hand, is extremely concise, but so are other ancient languages like Hebrew, although in a different way. So it seems that ancient languages are compressed but challenging and modern languages have unpacked the compression for ease of understanding.

New comment by reedlaw in "Caveman: Why use many token when few token do trick"

reedlaw — Sun, 05 Apr 2026 16:56:06 +0000

Are you saying Chinese is more concise than English? Chinese poetry is concise, but that can be true in any language. For LLMs, it depends on the tokenizer. Chinese models are of course more Chinese-friendly and so would encode the same sentence with fewer tokens than Western models.

New comment by reedlaw in "Show HN: I built a frontpage for personal blogs"

reedlaw — Fri, 03 Apr 2026 15:35:06 +0000

I've come to the conclusion that Hacker News is the best aggregator out there. Substack knows my interests yet gives terrible recommendations. Youtube constantly recommends the same videos or exaggerates my interest in a topic based on a few views, spamming me with related content until I watch something unrelated. The only downside of Hacker News is that its focus is narrower than other sites. But perhaps because the focus is "Anything that good hackers would find interesting" there is a bias towards things I find interesting with less noise than more commercial offerings.

New comment by reedlaw in "Universal Claude.md – cut Claude output tokens"

reedlaw — Tue, 31 Mar 2026 14:16:21 +0000

Claude has trained me on the use of the word 'invariant'. I never used it before, but it makes sense as a term for a rule the system guarantees. I would have used 'validation' for application-side rules or 'constraint' for db rules, but 'invariant' is a nice generic substitute.

New comment by reedlaw in "A sufficiently detailed spec is code"

reedlaw — Fri, 20 Mar 2026 11:29:53 +0000

Then I would say this is another proof that LLMs lack intellect or ability to reason about universals. See https://michaelmangialardi.substack.com/i/186405810/test-4-p...

New comment by reedlaw in "A sufficiently detailed spec is code"

reedlaw — Thu, 19 Mar 2026 17:30:23 +0000

Why is Haskell irrelevant to the argument that LLMs can't reliably permute programming knowledge from one language to another? In fact, the purity of the language and dearth of training data seems like the perfect test case to see whether concepts found in more mainstream languages are actually understood.

New comment by reedlaw in "Get Shit Done: A meta-prompting, context engineering and spec-driven dev system"

reedlaw — Wed, 18 Mar 2026 15:35:21 +0000

This is the second endorsement I've seen today. I gave OpenSpec a shot and was dismayed by the Explore prompt. [1] Over 1,000 words with verbose, repetitive instructions which will lead to context drift. The examples refer to specific tools like SQLite and OAuth. That won't help if your project isn't related to those.

I do like the basic concept and directory structure, but those are easy enough to adopt without all the cruft.

1. https://github.com/Fission-AI/OpenSpec/blob/main/src/core/te...

New comment by reedlaw in "Ask HN: What Are You Working On? (March 2026)"

reedlaw — Mon, 09 Mar 2026 17:40:32 +0000

Do you have examples of the task maturation cycle? I'm not sure how it would work for tasks like extracting structured data from images. It seems it could only work for tasks that can be scripted and wouldn't work well for tasks that need individual reasoning in every instance.

New comment by reedlaw in "Tell HN: I'm 60 years old. Claude Code has re-ignited a passion"

reedlaw — Sat, 07 Mar 2026 15:37:15 +0000

How do you even begin to define objective measurements of software engineering productivity? You could use DORA metrics [1] which are about how effectively software is delivered. Or you could use the SPACE Framework [2] which is more about the developer experience.

1. https://cloud.google.com/blog/products/devops-sre/using-the-...

2. https://space-framework.com/

New comment by reedlaw in "Plasma Bigscreen – 10-foot interface for KDE plasma"

reedlaw — Sat, 07 Mar 2026 13:59:12 +0000

Plasma Bigscreen has been around for 6 years: https://itsfoss.com/news/plasma-bigscreen-comeback/

New comment by reedlaw in "Ki Editor - an editor that operates on the AST"

reedlaw — Sat, 07 Mar 2026 13:14:11 +0000

https://github.com/mickeynp/combobulate

New comment by reedlaw in "Workers who love 'synergizing paradigms' might be bad at their jobs"

reedlaw — Fri, 06 Mar 2026 15:27:04 +0000

Isn't this the premise behind Dilbert?

New comment by reedlaw in "The L in "LLM" Stands for Lying"

reedlaw — Thu, 05 Mar 2026 12:41:49 +0000

LLM-generated snippets of code are a breath of fresh air compared with much legacy code. Since models learn probability distributions they gravitate to the most common ways of doing things. Almost like having a linter built in. On the other hand, legacy code often does things in novel ways that leave you scratching your head--the premise behind sites like https://thedailywtf.com/

New comment by reedlaw in "Nobody gets promoted for simplicity"

reedlaw — Wed, 04 Mar 2026 18:09:20 +0000

Whatever agent I tried would include thousands of tokens in tool-use instruction. That would use up most available context unless running very low-spec models. I've concluded it's best to use the big 3 for most tasks and qwen on runpod for more private data.

New comment by reedlaw in "Nobody gets promoted for simplicity"

reedlaw — Wed, 04 Mar 2026 16:53:17 +0000

This seems like a perfect use case for a local model. But I've found in practice that the system requirements for agents are much higher than for models that can handle simple refactoring tasks. Once tool use context is factored in, there is very little room for models that perform decently.

New comment by reedlaw in "Nobody gets promoted for simplicity"

reedlaw — Wed, 04 Mar 2026 15:49:22 +0000

Maybe a better way to handle "minimize cyclomatic complexity" would be to set an agent in a loop of code metrics, refactor, test and repeat.

New comment by reedlaw in "GPT‑5.3 Instant"

reedlaw — Tue, 03 Mar 2026 22:29:11 +0000

I don't know about Opus, but Codex suddenly got a lot better to the point that I prefer it over Sonnet 4.6. Claude takes ages and comes up with half baked solutions. Codex is so fast that I miss waiting. It also writes tests without prompting.

New comment by reedlaw in "Show HN: Geo Racers – Race from London to Tokyo on a single bus pass"

reedlaw — Fri, 13 Feb 2026 15:29:35 +0000

Great feedback. On the Inverness to Gibraltar race the leaderboard has impossible times, including some negative numbers. According to Google Maps the best time is 1 day 8 hours, but this requires leaving Inverness at 6:44. The race starts at 9:00. Then the earliest arrival time in Paris is 22:19. According to Google Maps the best time from Paris to Gibraltar at this time of night is 1 day 2 hours. Despite all this, there are several 1 day records. The best I can do is 2 days 5 hours. Of course I may be missing some better route, but I suspect cheating, especially from names like AdolfHitler.

New comment by reedlaw in "Experts Have World Models. LLMs Have Word Models"

reedlaw — Tue, 10 Feb 2026 13:00:24 +0000

I'm using the Aristotelian definition of my linked article. To understand a concept you have to be able to categorize it correctly. LLMs show strong evidence of this, but it is mostly due to the fact that language itself preserves categorical structure, so when embedded in geometrical space by statistical analysis, it happens to preserve Aristotelian categories.

New comment by reedlaw in "Experts Have World Models. LLMs Have Word Models"

reedlaw — Tue, 10 Feb 2026 02:48:49 +0000

Yes, LLMs mimic a form of understanding partly through the way language embeds concepts that are preserved when embedded geometrically in vector space.