Top all-time · #24556
T
The Living Deadline
Personal blog · alexhans.github.io/posts · on HN as alexhansaiprogramming
The Living Deadline is a personal blog at alexhans.github.io about ai and programming. Since 2026, 3 different Hacker News readers have linked it 32 times, most often “Building agent skills: Intent, determinism, and stability”. It is still writing: the last post was on 2026-10-31, and you can follow it by feed.
32mentions?
3HN people?
2026–2026first – last linked?
Most-linked posts?
- Building agent skills: Intent, determinism, and stability2 people · 8 mentions · first linked 2026-02-16
What Hacker News says?
- I don't find skills, I create them - Keep them organised in software repos that you install with symlinks for all coding harnesses that you have. Progressive disclosure based on the frontmatter does the rest. - I make sure they work with AI evals. Think of them like integration tests to prove behaviour. They're useful to optimize your flows. I try to make my skills be mostly a translation between natural language…
Comment linking /posts/series/evals/building-agent-skills-incrementally.html
on “Ask HN: How do you manage skills files?”Submitted Set a Meeting Budget as a story · 2 points
HN discussionNice to see you here (Just reached out on bluesky over sandboxing - gandolin). I follow your work and agree and am hoping that you and others who have well earned audiences based on awesome open source work, can help with the advocacy on mental shifts, not just for developers but also non Devs that become builders. I'm very focused on their minimalistic building experience as a way to make me and other traditional d…
Comment linking /posts/series/evals/measure-first-optimize-last.html
on “Writing code is cheap now”Submitted To Bin or Not to Bin: A Tutorial on Fast Feedback Loops for AI Capabilities as a story · 1 points
HN discussionIt doesn't disappear but it does easy up some instances of fighting configuration, documentation, syntax or even comparing three approaches that are similar but you don't know their full effect. I think it's a very fun space, finally being able to empower many people who in the past wouidve been bottlenecked unless they were using very simple tools for their domain and upskilled enough. Those 2 things will still be…
Comment linking /posts/series/evals/measure-first-optimize-last.html
on “Writing code is cheap now”Submitted Building agent skills: Intent, determinism, and stability as a story · 1 points
HN discussionI am pushing for this judicious Eval [1] Driven Development where tech/non tech users use intent when coding to minimally design some known aspects and try to build simply and using common standards across the team (that should be in the context of the agent) to produce the minimal amount of human readable and clean code that would do the job. The more the building blocks they work with are simple, easy to validate…
Comment linking /posts/series/evals/building-agent-skills-incrementally.html
on “Writing code is cheap now”Isn't the title editorialised? Probably for clicks? I think that most of the adoption around Agent Skills would have a focus on ease of use, standarization and context management and not correctness. My own thoughts on how to approach skill building target people who are adopting LLM development now more than ever although this was definitely possible (in a non standard way before) [1] [1] https://alexhans.github.io…
Comment linking /posts/series/evals/building-agent-skills-incrementally.html
on “Study: Self-generated Agent Skills are useless”I haven't had the analysis paralysis problem because I've always been quite decent at restructuring environments to avoid bureocracy (which can one of the most dangerous things for a project) but one thing I've observed is that If operations are not ZeroOps then whoever is stuck maintaining systems will suffer by not being able to deliver the "value adding cool features that drive careers". Since shipping prototypes…
Comment linking /talks/airflow-summit/toward-a-shared-vision-of-llm-evals-in-airflow-ecosystem.html
on “Management as AI superpower: Thriving in a world of agentic AI”I had a similar experience trying to get feedback on my attempt to help different role families adopt AI evals as a common language (hands on tutorial or tool comparison). https://news.ycombinator.com/item?id=47026263 I attribute it mostly to my own inability to pitch something that is aimed for many audiences at once and needs more UX polishing and maybe a bit on timing. It's tough when you're not looking to sell a…
Comment linking /posts/series/evals/building-agent-skills-incrementally.html
on “Is Show HN Dead? No, but It's Drowning”Many of us were saying it a year ago but now with model restrictions (e.g. fable) and pricing changes it should be obvious to people that part of the economics is avoiding vendor lock-in with evals (so you can easily switch providers/models/optimize) and increasing control by investing in local models which could be good enough for your tasks, at whatever the price for your cloud compute is. Eventually consumer hard…
Comment linking /posts/find-the-loop-story-first.html
on “I burned all my tokens researching how to save tokens”I'd say that's almost fine if they can start expressing intent correctly and thinking what good looks like. They (or some automated thing if you're building "think for them" type of products instead of "give them tools and teach them to think how to use them") can then freeze determism more and more were useful I wrote this to help people (not just Devs) reason about agent skills https://alexhans.github.io/posts/ser…
Comment linking /posts/series/evals/error-compounding-genai-systems-approach.html
on “Schedule Claude Code tasks on the web”You can also use PI with local models like Qwen3.5-35B-A3B [1] and they can be surprisingly good if you development in minimalistic/simple ways. One game changer when it comes to tweaking configs that are optimized for your use case is that you can easily use a "more powerful" cloud model to identify a good enough config for your local server/pi settings combination [2] in a pattern that applies pretty much anywhere…
Comment linking /posts/find-the-loop-story-first.html
on “Pi's Minimalism Is Its Advantage”Hey, sorry for the late reply. I looked superficially at your site/repo and based on that initial impression: - Your approach of comparing different parts of the "black box" which affects agent behaviour (Harness, foundation model, skills, context (in your case the loaded on AGENTS.md context) is closely aligned with how I both think and operate. - You're both tackling the "regression" and the "answer hypothesis eas…
Comment linking /posts/series/evals/building-agent-skills-incrementally.html
on “A Claude Code and Codex Skill for Deliberate Skill Development”Skills are just a good standard to describe repeatable workflows saving context through progressive disclosure, prompt sharing and, very underused feature, also bound the non deterministic parts with determism (which could be scripts). Conceptually, you should treat them as incremental software instead of magic you grab from others [1] The killer feature is that coding harnesses tend to have SkillBuilder agent skill…
Comment linking /posts/series/evals/sketch-to-text-skill.html
on “A Claude Code and Codex Skill for Deliberate Skill Development”This is what AI evals [1] and local llms should be a focus of your investment. If you can define good enough for you and local llms can meet that you'll get: - no vendor lock-in (control) - price - stability (you decide when to hot swap with newer models) - speed (control) - full observability and predictability. - Privacy / Data Locality (Depending on implementation of infrastructure). - [1] https://alexhans.github…
Comment linking /posts/series/evals/measure-first-optimize-last.html
on “Claude Code Routines”I think it's important to be able to do both so you can stay in control of the price to value created relationship. In last year, some people were publishing aider /ollama/open router [1] and now thankfully people are publishing all around about pi/qwen/llama.cpp/openrouter. It's widespread. [1] https://alexhans.github.io/posts/aider-with-open-router.html
Comment linking /posts/aider-with-open-router.html
on “RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8”Sync meetings can help some people feel pressure but it's an extremely inefficient mechanism. You're waiting a whole week for an update or to push people. I'm a huge proponent of "async over sync" and "sync as soon as necessary". Don't wait to the next meeting in 3 days to escalate. People whose calendar looks like meetings only and are always willing and able to throw complexity to others won't feel the pain of not…
Comment linking /posts/meeting-budget.html
on “Meetings Are Forcing Functions”You're right. Control is the big one and both privacy and cost are only possible because you have control. It's a similar benefit to the one of Linux distros or open source software. The rest of your points are why I mentioned AI evals and regressions. I share your sentiment. I've pitched it in the past as "We can’t compare what we can’t measure" and "Can I trust this to run on its own?" and how automation requires…
Comment linking /posts/series/evals/error-compounding-genai-systems-approach.html
on “Claude Code: connect to a local model when your quota runs out”Useful tip. From a strategic standpoint of privacy, cost and control, I immediately went for local models, because that allowed to baseline tradeoffs and it also made it easier to understand where vendor lock-in could happen, or not get too narrow in perspective (e.g. llama.cpp/open router depending on local/cloud [1] ). With the explosion of popularity of CLI tools (claude/continue/codex/kiro/etc) it still makes se…
Comment linking /posts/aider-with-open-router.html
on “Claude Code: connect to a local model when your quota runs out”This frames MCP vs Skills as an either/or, but they operate at different layers. MCP exposes capabilities and Skills may shape how capabilities are used. Both are useful to different people (and role families) in different ways and if you don't feel certain pain points, you may not care about some of the value they provide. Agent skills are useful because they're standardized prompt sharing but more than that, becau…
Comment linking /posts/series/evals/building-agent-skills-incrementally.html
on “I Still Prefer MCP over Skills”I'd be curious to see if my blog posts/titles feel like AI slop to you. https://alexhans.github.io/ No need to read them, just a vibe check would be insightful. It's weird how branding, even before AI had a lot of the same catchy patterns, and now it's hard to define what is the right prose (engineers might want one thing and other role families others) and sometimes you're trying to write almost with the "everyone…
Comment linking /
on “The Git Commands I Run Before Reading Any Code”It really depends on the type of agent and problem but your path resonates as a way to slowly build more complexity as you start understanding the uncertain space. I've written about it in my blog with the intent of helping non tech users [1] and also created a site with cookbooks and eval tool comparisons [2]. I've successfully managed to get non technical users into the terminal, even before Agent Skills were a th…
Comment linking /posts/series/evals/building-agent-skills-incrementally.html
on “Ask HN: How do you build internal agents at work?”I'd argue that the moment one cares about accuracy and blast radius, one would natural want to reduce error compounding from a combination of LLM calls (non deterministic) and it's very natural to defer to well tested determinist tools. Do one thing and do it well building blocks and the LLM acts a translation layer with reasoning and routing capabilities. Doesn't matter if it's one or an orchestrated swarm of agent…
Comment linking /posts/series/evals/error-compounding-genai-systems-approach.html
on “OpenClaw: When AI Agents Get Full System Access. Security nightmare?”> Has anyone tried this yet? If not, why not? Yes (in a minimalistic TDD like way?). [1] I agree that the company as code can be tested without too much risk if you think about as "model your world drawing a circle around what you own". You can be your own auditor constantly so that you pre-answer questions you would ask in an audit. I would advise against the always tempting "we are the everything platform" because…
Comment linking /posts/series/evals/automate-audits.html
on “Company as Code”Agreed. Even in the case of a single agent, the compounding of errors [1] can easily make your "flow" unacceptable for your use case. The deterministic where possibe/decoupled/well tested approach is key. With such a fast moving space I'm always wary of adopting optimization techniques that I can't easily prove and pivot from (which means measuring/evals are necessary). Slowly but surely, abstractions allow us to us…
Comment linking /posts/series/evals/error-compounding-genai-systems-approach.html
on “Towards a science of scaling agent systems: When and why agent systems work”> Curious what peeple are doing in the real world It's hard to answer this as the right thing to do might depend a lot on the environment. My pitch would be that automation is not a new problem and the fundamentals still apply: - We can’t compare what we can’t measure - I need to ask myself, can I trust this to run on its own? - I need to be able to describe what I want - I need to understand my risk profile Once yo…
Comment linking /posts/series/evals/error-compounding-genai-systems-approach.html
on “Evaluations for Testing Agentic AI”Thanks for the insight. This resonates with the same explanation I tried to give around non determinism tasks that feed into each other [1]. If you don't break the cycle with determinism or, in your case, CPCs, you get to a stage where error is almost guaranteed. Now you have the very useful and opinionated sochratic method. Are you playing around with teaching meta thinking as well? E.g. helping your daughter also…
Comment linking /posts/series/evals/error-compounding-genai-systems-approach.html
on “Show HN: I built a "Socratic" AI to stop my daughter from copy-pasting homework”