Harness engineering for self-improvement

Join the discussion

• Hacker News
• We've using auto-research for harnesses and it's surprisingly powerful. It's amazing how many problems are easy to spot and fix from traces.

  Few key things were required to get it working well: 1) let it read a heap of prod traces to spot real issues. 2) let it write it's own tools (example "loading context" goes from 20k tokens across 15 tool calls to 800 tokens and 1 call to session_context tool). 3) you need evals and val/test splits, it will reward hack. 4) you need proper tooling (synthetic users, synthetic tools) for it to be able to crunch for 12 hours and produce something. 5) you need the optimization target to be a reasonable size: not your 1M line codebase, but a lighter agent harness (pi harness, skill only, Kiln harness).

  by scosman
• What is the fitness function , eval?
  by lerchmo
• I've been working with self improvement harness a little bit and one thing i've come to conclusion is harness task fit. The learning can be significantly improved if we understand the behaviour of task and how it should be learned. I'm pretty sure a general solution will definitely exist which will do fine, but we are yet to see one.
  by manojbajaj95
• I haven't understood a bit.

  Can you make an example?

  by epolanski
• Agree with the sibling comment that an example would be useful. I'm also curious what kinds of tasks you have in mind. Theoretically almost every knowledge work task boils down to the file editing that agent harnesses already are built around (which probably explains the second half of your comment).
  by djsavvy
• one form of very effective self-improvement that coding agents do all the time:

  install or build stuff that they can then use

  it changes the environment instead of the agent/harness but in a sense how separate is the agent from its environment and why do we apply this distinction re self-improvement?

  animals and humans do the same thing and are great at it, without 'self-improvement' with emphasis on the 'self'

  by tosh
• Blame Descartes? I don't know. Extended theories of cognition all get shot down, even analytic philosophers who are accused of being more "continental" still primarily hold mind-body dualisms
  by sigbottle
• Very enjoyable article.

  Isn't the harness basically where the frontier model companies can capture value and create a moat of sorts? I am also curious about building a harness for fun but would expect it to be more interesting in a scenario where I can self host an open weight model.

  What motivates the people who build their own ChatGPT/Claude harness for example? And how do you keep it tuned with the rapid development of frontier models.

  by kriro
• I don't think so. A basic consumer-oriented harness is a commodity (zero moat: you can ask one harness to write you another).

  State-of-the-art models have more of the workflow sensibilities built in, and don't need as much help from the harness.

  Where harness helps the most is very customised personal workflows (not a textbox for a prompt, but an end-to-end IDE for how you develop software) But then it's best to have your own, rather than some closed-source rigid product.

  Harnesses help smaller models, and very tightly hand-holding harnesses are needed for models runnable locally. I think that is very valuable to users, but avoiding paying for the biggest models is the opposite of what the frontier labs want.

  by pornel
• > Isn't the harness basically where the frontier model companies can capture value and create a moat of sorts?

  They're trying. I see a few main avenues:

  1. Fitting the models to their specific harness, so that if you want peak model performance, you're stuck with their harness. But this only works if there aren't alternative models that are similar in capability or good enough that don't have that restriction.

  2. Locking you out of the harness so that you eventually are just letting it do "stuff" with your data and system, although you don't get to see what the stuff is or why it's doing it. This is the pattern discussed in that Earendil blog post, "The session you cannot take with you." Encrypted reasoning tokens, secret agent prompts, perhaps eventually not even seeing what files are being read or what data is being sent back to their server. This way, you are also shackled to their harness because nothing is portable. But it only works if you trust them implicitly and don't have alternative models and harnesses that don't treat you this way.

  3. Tying subscription pricing to the use of their harness, so that it's financially punitive to use another one. This is what Anthropic does. But again, it only works if there aren't alternative models and harnesses that work similarly well for you and don't have that restriction.

  4. Marketing. Anthropic is leaning into this one heavy, from what I can tell, based on the constant ads I see for Claude Code. Can it work? People do overpay for things like vodka in fancy bottles that are chemically identical to the cheap stuff. Is Veblen-good AI a trillion dollar business, though?

  I think the pressure from open source innovation in models and model tooling is going to make it a tough row to hoe. But I'm biased, as I'm actively rooting for Openthropic's demise.

  by anon373839
• There is a really good video by the author of pi.dev (which I have used to build some of my own harnesses): https://www.youtube.com/watch?v=RjfbvDXpFls

  The basis of the argument is that the labs are constantly pushing updates to their system prompts that are used in claude code or codex, which are exceptionally bloated and change the sand beneath your feet with every update.

  By rolling your own harness, as long as you keep up with the latest advances and changes in the ecosystem, you capture a lot of the 'control' that LLM-based development feels like it strips from you.

  Obvious disclaimer that I use pi.dev when I am aiming for consistency, not absolute quality. Custom harnesses on pi are what I ship, claude code is still my fallback if I need to make sure a PR is the highest absolute quality

  by sbysb
• Thanks for the really nice in-depth post! Hoping for a future one about:

  "Much recent work on auto-research, self-improving agents, and evolutionary program search can be organized around this question. Other work on model self-play, synthetic data, test-time training and a broader theme of continual learning also matches the RSI vision (e.g. Yuan et al. 2024, Chen et al. 2024), Zhao et al. 2025, Choi et al. 2026)) but they will not be the focus of this post."

  by erwincoumans
• Great article! I am currently writing my second harness (first was in Emacs Lisp, using Emacs as UI; second is a command line coding agent written in Common Lisp).

  If anyone wants to argue that it is inefficient writing your own AI coding harness, I wouldn’t disagree. That said it is satisfying to have long coding sessions using my own tools.

  The article is a valuable resource, thanks to the author.

  by mark_l_watson
• The dream of the AI lisp machine ! Did you build in the functionality that the agent can on the fly rewrite its own (harness)-code?
  by lmf4lol
• I'm curious to learn more about your experiences here, what you've learned, if you've enjoyed using the REPL with agents
  by sroerick
• Thanks for the post. For https://Document.bot (Kinda Cursor IDE for knowledge workers), im already trying to improve the harness (besides spotting bugs) using hillclimb experiments. More and more i'm using a AI harness engineering skill in Codex to further improve the app. This blog post helped me to improve the skill a bit.
  by cahaya
• Very interesting, will give it a demo.
  by robbru
• I did something similar. It started off as a "self-improving agent" project, inspired by autoresearch, then later on I reframed it as "harness training" (discrete program search) borrowing the mental model from ML training.

  I "trained" the harness on a subset of Terminal-Bench 2.0 tasks while keeping the LLM (local Qwen3.6-35B A3B) frozen. Making LLM inference and the task environments fully deterministic was necessary for clean credit assignment. I learned this the hard way after spending the initial 1 month on experiment noise.

  My final results showed that on the full 89-task Terminal-Bench 2.0 suite, the trained harness matched or beat the official Terminus 2 harness for four LLMs that it never collaborated with during training (e.g. GPT-OSS-120B score increased from 18.7% to 36%, while using 55% fewer input tokens per solve). A harness trained only on SWE-bench improved Terminal-Bench scores too. Here's the write-up: https://www.henrypan.com/blog/2026-07-18-harness-training/

  I packaged the training loop as a PyTorch-style framework. https://github.com/workofart/harness-training

  by megadragon9
• Really good points Lillian. Agreed on keeping the evaluator outside the loop that evolves the harness.

  One practical failure mode I’ve have experienced in my agentic harness tasks similar to the “weak evaluators” point: an incomplete check suite that still reports full success. That’s was worse than a weak evaluator, because it made it look correct and decisive.

  After several trial and error, what helped was fail-closed on coverage i.e if the fixed checks for each operation aren’t all there, nothing ships / nothing gets sent. Otherwise you can “pass” while never running the cases that would have failed.

  by gopalraja
• The quest for Torment Nexus continues
  by Kinrany
• Eagerly waiting for the TormentBench.
  by grim_io
• If we don't create the Torment Nexus first, somebody else who is much less responsible is gonna create the Torment Nexus before us. It's outright irresponsible to not take the lead, we might have to even give up on all safety concerns to make sure we make it to Torment Nexus IPO first.
  by Drakim
• IMHO training weights has peaked and now it is time for a training paradigm for prompts and code. We don't have the gradient descent here - but I think it can be more sample efficient because causal theories can be better than just correlations.

  I am working on a unified theory in https://zby.github.io/commonplace/ - it is all agent edited so it might be hard to read, but hopefully we are catching most logical errors. Some day the llm prose will improve.

  I have even a preliminary theory on what is needed for the positive feedback loop: https://zby.github.io/commonplace/articles/reflective-self-i... - (this is not stable yet - but I think you can give it to your agent to read :).

  by zby
• What date was the peak? If it is today it’s not something you can know so I assume you think the peak was many months ago.
  by victorbjorklund
• Is there any reason to think that training weights has peaked rather than is accelerating? It feels like now they are increasingly able to pick some low hanging fruit by using the models in order to improve themselves and test optimizations.
  by ianm218
• I’ve been thinking about how we practically implement this at an organizational layer for large codebases. There’s clearly alpha to be had in optimizing AGENTS.md / skills / tools / … to improve performance, quality, and cost efficiency of an agent. The problem is defining what quality means, and providing a way for agents to optimize the harness using that lever.

  The first step I see towards this is building a generic, reliable, and accurate *fitness function* for codebases - turning PRs into gradeable tasks that an agent can solve, and improve on.

  I’m pretty curious how others are optimizing the coding agent harness now, as this has been a huge pain point for my company (we’re pretty much relying solely on vibes).

  by bisonbear
• > The problem is defining what quality means, and providing a way for agents to optimize the harness using that lever.

  I've built and my team uses plannotator [1] for specs and code review. It stores all human annotated feedback, which we compile from time-to-time and iterate on coding standard skills for automated review (that seems to get better with the more feedback we provide).

  You could write a script that does the same for your PR review comments, which it sounds like you maybe do with a bit more structure.

  [1] https://github.com/backnotprop/plannotator

  by ramoz
• maybe a bit counter-intuitive but:

  I found that removing

    - system prompt
    - skills
    - agents.md
    - mcps
  

  + reducing tools to just 1 (sh)

  gives better results than having 'more' of them

  (e.g. look at these traces to see more vs less in action:)

  https://smolenv.com/t/nested-template-includes-60636/

  not saying the right context does not help

  (it definitely does!, but it's not trivial to provide the right context)

  by tosh
• You've just described what the AI industry refers to as "evals", a collection of which forms a particular benchmark. I definitely encourage you to define your own evals, because the public benchmarks are often either saturated (largely solved and only going to see small improvements going forward) or seemingly not predictive of real world performance. I could also go further and speculate that they are in the training data, although credible benchmarks avoid this, I'm just not sure how successful they are.
  by sulam
• Trying something like this in a reusable way at https://github.com/mateffy/gesetz

  It only tries to solve the „quality“ aspect of that equation tho, at least for the code output.

  But I think for actual evals, some heuristics about a coding agent session are needed. But since the input tasks are always different, it’s hard to make any KPI actually comparable.

  Did the agent needing 3 rounds of feedback on a big task perform worse than the one that needed none, but only worked on a small change?

  by capevace