Hacker News Reader

rsaluson The labor share of income in the US is at its lowest post-war level

he's referring to labor productivity, e.g., the economic value produced per unit of labor input. it also _has_ changed significantly, as seen here: https://fred.stlouisfed.org/series/OPHNFB

however, unit labor costs has also been increasing (although they remain variable): https://www.bls.gov/opub/ted/2026/productivity-up-0-3-percen...

rsaluson Previewing GPT‑5.6 Sol: a next-generation model

agree, from my POV the constraints are still there but we've optimized now. still haven't solved the core problems.

rsaluson Loreline – Tools for writing interactive fiction

eh, they're a publishing business. choicescript is part of their business model - there's nothing inherently wrong with that.

rsaluson Loreline – Tools for writing interactive fiction

so cool! how does this compare to ChoiceScript?

https://www.choiceofgames.com/make-your-own-games/choicescri...

rsaluson Leaked OpenAI financials show $38.5B loss and compute burn

they are forecasting $25-30B this year, so if anything they look to be neutral or even profitable.

rsaluson Qwen-Robot Suite: A Foundation Model Suite for Physical World Intelligence

> The TAM for robots is much, much larger than for coding or services

how do you figure?

rsaluson LLMs are eroding my software engineering career and I don't know what to do

AI usage will directly impact said margins. Moreover, for the scenario you describe, companies need to have the capability to precisely estimate the cost of a given deliverable - not something possible with current tooling + models. You're also underestimating the market trend towards vertical integration: companies are not going to be constrained by a sector or niche. They will expand to capture as much value as they can, because now their capacity to do so is partially decoupled from labor.

It will certainly be a cutthroat landscape for engineers, but companies will be building _more_ capacity, not less. In other words, the demand won't disappear for skilled technical labor, it will just move higher up the value chain.

rsaluson LLMs are eroding my software engineering career and I don't know what to do

I don't know, even if AI allows two engineers to do the work of six, companies will likely just use that efficiency to expand their scope. I think we'll see short-term layoffs and a more stratified engineering field during the transition, but the fundamental need for deep technical expertise isn't going away.

rsaluson My Agent Skill for Test-Driven Development

tests are an important signal of course, but the use case you describe doesn't necessarily mean you need to follow TDD. the data suggests that creating the tests after the code is just as or even more effective, and at significantly cheaper input cost.

I've been finding enforcing integrations and behavior structurally (e.g., through codegen/schemagen, e2e tests, etc) more reliable than simply instructing the models to write tests. oftentimes these tests are pretty low quality anyway, and results in its own form of tech debt.

rsaluson My Agent Skill for Test-Driven Development

this is not really backed by any empirical evidence. there are simply more efficient means of verifying outputs than TDD.

rsaluson My Agent Skill for Test-Driven Development

for LLMs, TDD amounts to little more than ceremony. there is a study on this exact topic: https://arxiv.org/pdf/2602.07900

rsaluson My Agent Skill for Test-Driven Development

not necessarily, TDD has little bearing on output quality

rsaluson My Agent Skill for Test-Driven Development

I was a big proponent of encoding TDD red-green-refactor methodology into my agent workflows until recently when I made the same realization after reading this study: https://arxiv.org/pdf/2602.07900

TLDR; it found test-writing volume only weakly correlates with success and that encoding test-writing principles did not move resolution rates but _did_ materially change cost. Encouraging tests cost +19.8% output tokens for 0% gain; discouraging them saved 33–49% input tokens for ≤2.6pp accuracy loss. Separately, imposing the TDD procedure specifically seems like it can backfire: it actually _increased_ regressions from 6.08% to 9.94%.

IMO, where tests clearly help is primarily as an "oracle" applied after generation. It gives the models a signal that enables them to verify and self-correct if necessary.

rsaluson Redis 8.8: New array data structure, rate limiter, performance improvements

agreed but depends on then language. for instance, the .NET equivalent (MemoryCache) is pretty poor.

rsaluson SQLite is all you need for durable workflows

not really true, SQLite supports WAL mode which allows concurrent writes (technically write _attempts_, but these writes are exceptionally fast and are serialized to the file-system anyway, so functionally equivalent to concurrent writes for p50 use case).

also, use-case for massively concurrent writes is pretty narrow, and SQLite is not optimizing for that anyway.

rsaluson OpenRouter raises $113M Series B

functionally they operate as a marketplace for cloud providers. I feel like there is value there, especially as API costs rise and companies explore cost-saving/efficiency. IMO, this is a particularly attractive value prop in the SMB space, where it is common to interoperate between multiple SaaS/software stacks.

rsaluson SQLite is all you need for durable workflows

there is a difference between concurrency in a distributed environment and concurrency on a single machine across processes. SQLite is incredibly useful for the latter.

you seem like the inexperienced one to me..

rsaluson SQLite is all you need for durable workflows

mirrors my own experience creating a persistent event log. I started with JSON, then JSONL, etc until finally landing on SQLite.

rsaluson I think Anthropic and OpenAI have found product-market fit

they need to make 5t-10t back, but not necessarily through selling tokens. as we can see, the frontier labs are making vertically integrated products. their revenue is no longer strictly tied to inference.

rsaluson Archaeologists find Egyptian mummy buried with the 'Iliad'

often times the classical Greeks + Romans would cite their family lineage using works of Homer and other poets

rsaluson Ask HN: What are you working on? (May 2026)

https://github.com/lvlup-sw/exarchos

It's an SDLC workflow harness for agents. Instead of using skills to encode my typical workflows (e.g., create PRD, then create plan using TDD, then dispatch subagents, etc) I've built a concurrent event-sourced process manager to handle it.

rsaluson Principles for agent-native CLIs

not really.. I never understand the inclination to be reductive. the patterns emerging can be fairly novel.

rsaluson Principles for agent-native CLIs

agree, although the pattern I've been following is to provide a self-contained CLI for portability and usability purposes, and then an "mcp" subcommand which launches an MCP server over stdio. ultimately the "CLI" and "MCP" surfaces act as thin facades over the same functional layer.

rsaluson Principles for agent-native CLIs

the real solution is to simply provide hints in responses so that the model may self-correct, e.g., recommended next actions, describe commands to get schema definitions, etc.

rsaluson Commenting and approving pull requests

100p agree. Most code reviews devolve to nitpicking anyway. I think it's much more valuable for teammates to review the _design_ and _intent_ rather than the explicit artifacts.

rsaluson The AI Layoff Trap

Great paper.

> If AI displaces human workers faster than the economy can reabsorb them

Big if.

rsaluson Chrome DevTools MCP

mostly by virtue of being a common standard. MCP servers are primarily useful in a remote environment, where centralized management of cross-cutting concerns matters. also its really useful for integrating existing distributed services, e.g., internal data lakes.

I think it's clear a self-describing CLI is optimal for local-first tooling and portability. I personally view remote MCP servers as complementary in the space.

rsaluson Chrome DevTools MCP (2025)

that's a pretty interesting idea. It would be nice if there was such a standard. the approach I'm taking right now: a CLI that accepts structured JSON as input, with an 'mcp' subcommand that starts a stdio server. I bundle a 'help' command with a 'describe' action for self-service guidance scoped to a particular feature/tool.

rsaluson Chrome DevTools MCP (2025)

yes, but clis thus need self-service commands to provide guidance, and their responses need to be optimized for consumption by agents. in a sense, this is the same sort of context tax that MCP servers incur. so in my view cli and MCP are complementary tools; one is not strictly superior over the other.