code_biologist

I agree that resin cartridges don't handle the resin handling problem.

Nitrile/latex gloves + eye protection + respirator are the absolute minimum for resin printing PPE. A long sleeve shirt wouldn't go amiss for rare flicked resin droplets. If you're not confident in your ability to prevent skin contact with resin, you shouldn't be doing resin printing.

I just wanted to thank you for the followup and the clarity on your pattern. So many people say "it's working great for me" without explaining how they go beyond "tell claude to implement feature".

Indeed, the changes around socialization and community formation during the last 30 years perfectly discourage meaningful class solidarity. Everybody will continue scrolling angry content while the middle class hollowing out proceeds.

Not asking for answers to these questions, just frustration dumping:

The biggest things I've struggled with are models having taste. For spec writing I was having a lot of issues with them making statements that were interpretable in a superposition of ways, eg "we'll do XYZ with entities that support and need it" when there's 3 possible entities and the model hand-waved at exactly the wrong tokens.

I added AGENTS.md guidance + memories to be unambiguous (with short but good examples) and "no coined shorthand". Now I'm getting a marked increase in specificity, but it's places that don't matter (claude explaining existing code to itself). I'm having difficulty controlling the spew of new text, but feature writing/research still gets fuzzy and lazy around the difficult underspecified aspects of the problem/feature.

Do I just keep dumping examples into reviewer subagent context and have them rewrite and simplify the research subagent spew?

I repeatedly have "Risks and gotchas" sections have a whole paragraph dedicated to things that don't matter, and then a single sentence bullet point that's actually a huge problem when I dig into it.

Do I have a generic hook to make subagents to review bullet points and size them commensurate with impact? If I tell them to "have taste", do they have taste?

I'm just trying to get good code done. I hate these things.

I'm having bad results with SotA models. Some questions, if you're up for it:

In your workflow, who implements the review feedback - the review subagent or the code-writing-subagent?

Do have a baseline styleguide (like Google's Go style guide) for the review subagents, or is it entirely the subjective things and specific corrections? I remember 6 months ago it seemed like piling general "good taste" code advice into AGENTS.md was considered bad.

Do you move between harnesses or have you gone all in on claude? I've bounced between claude/codex/omp, maybe to my detriment.

Is anybody getting good code out of these things reliably without a bunch of additional legwork? Like, what a 2020 mid-level software engineer would write? I know it's old fashioned to read code these days.

To be clear, SotA models/harnesses are really good at making things that work one-shot, and their code golf and debugging game is insane.

When I go to implement, even with a good spec, I end up with code that's 80% of the way there in a fractal manner. The modular decomposition is 80% of the way to good code. The function decomposition is 80% of the way there. The computation structure and variable naming within functions is 80% of the way there. I can walk the AI through it and address each level of issues, but it's tedious as hell, and not clearly faster than doing it myself in some cases.

This is with omp/claude/codex, with Fable 5.1/Opus 5.5/6 Astra. The Chinese models do better at staying coherent, but they're a little less smart IME. I've tried many permutations of "fable planning, opus sub-agent implementation"; "pass a branch back and forth between opus and astra, as reviewers and feedback implementers". I haven't tried the "software factory with an architect and 2 juniors" thing. I haven't tried AGENTS.md beyond the /i-have-adhd, iso-24495 (lol at the Opus 5 induced PTSD), "No cleft constructions or Latinate absolutes" and general project orientation. Model character seems to change too fast to make agents worth it, and I see stuff about skills and excessive AGENTS reducing model capabilities.

Am I holding it wrong?

Getting recognition is a fundamental human motivation to work on hard problems. Being first is a really important part of getting recognition, measuring by the last few hundred years.

You might as well say "the obsession with sex has always held humanity back". Maybe, but it's complicated...

In absence of a good enforcement mechanism, it absolutely does apply. Is Slack going to strip Mullenweg of admin control in absence of court order, as long as the Slack bills are paid? It would set a terrible precedent for them to do so unilaterally. Whatever the legal process this battle follows, it will be a year or two before it's even possible for a final ruling + court order for the handover of Slack admin control to happen. That's de facto Slack control for at least a year or two.

If employees can be persuaded to move themselves + systems to a board controlled chat instance, that's an angle, but Mullenweg has stronger cards if he's liked by employees.

Possession is 9/10ths of the law.

YouTube is infested with lede burying as well. I hate it.

Opus 4.7/4.8/5 have a built-in nitpicking as anti-syphcophancy. Fable too. The models are structurally incapable of not nipicking.

I suspect the nitpicking helps engagement metrics and it doesn't harm RLVF outcomes, so there's just not good signal against it.