Mtinie

That it works is testimony to the intelligence put towards the code. That no one else can grep it tells me it was solved in a manner which was suboptimal.

I cannot believe Figma hired engineers who could not follow along already-tread footsteps. That’s a nonsensical assertion. Novel code may be inscrutable but the problem-solving and techniques should have been clear and repeatable by those who follow, even if they require adaptation.

But you cannot prove it. So what value did your comment bring? The readership of this site should always question if a comment is in good faith, legitimate, and accurate.

Your commentary may only be one of those.

Could she be correct in her assertion? Are we spending more on areas of physics which don’t require it?

Not as easily Goolge’d as “IFTTT” with five characters versus six.

Minor chronological point but Zapier is an IFTTT-type glue provider.

IFTTT was announced Dec. 14, 2010 and launched on Sept. 7. 2011.

Zapier was first pitched Sept. 30, 2011 and their public beta launched May 2012.

Presumably those needs are handled on the habitat where the orbital maintenance team lives when they aren’t visiting satellite data centers.

Treat each maintenance trip like an EVA (extra vehicular activity) and bring your life support with you.

Given the audience on HN I expect will be up on Hugging Face within an hour or so… :)

You know it’s old school when it’s not “built with love”. :)

Your unexpected anecdote perfectly encapsulates why I love HN!

If I was in power and wanted to continue said rule, I’d definitely discourage the adoption of any standardized formatting for election results.

Not, you know, for any nefarious purpose…but because what we’ve used forever was good enough for grandpappy, so it’s obviously good enough for us.

/cough

As far as I can tell, the ingredients described by Cennini[1] is close to the “traditional” preparation:

* Gypsum (Hydrated calcium sulfate)

* Zinc white pigment

* Clean tap water or distilled water

* Rabbit skin glue

—-

[1] Cennini, Cennino d'Andrea, The Craftsman's Handbook "Il Libro dell Arte," Daniel V. Thompson, Jr., trans. (New York: Dover Publications, 1960) pp. 69–74.

…but don’t click this button.

Multiple impressions per interstitial domain, I imagine.

Cargo culting.

> If the password length is 12 to 15 characters, it will be valid for 180 days

> If the password length is 16 to 32 characters, it will be valid for 365 days

Madness.

> Key thing is that we hire them.

I do not feel heartened by this sentence, even though I should be. We're choosing from a pre-curated menu rather than truly "hiring" representatives. The real power lies with party gatekeepers, donors, and institutional barriers that determine who even makes it onto the ballot, not with voters making the final selection. It's more like being asked to pick your favorite from two restaurants that a food critic already chose for you, rather than having genuine choice over where to eat.

This is where emergent behaviors within a game's world building becomes very interesting. Perhaps asking the right questions leads to a quest line not previously discovered or triggers social actions in support of/against the player.

Not every NPC would have something deeper to offer, much like not everyone in our world would have something that would pique my interest (in a general sense -- I'm sure I could learn something from anyone I spoke with), but it would also make me interested in conversations with NPCs at a deeper level than I currently engage with.

Your stationary plane example highlights a divide I've seen across my work experience in different domains; teams defaulting to ML when fundamental engineering would work better.

I'm curious: do you think there's any amount of high-quality data that could make the learning-based approach viable for orientation estimation? Or would it always be solving the wrong problem, regardless of data volume and delivery speed?

My sense is that effective solutions need the right confluence of problem understanding, techniques, data, and infrastructure. Missing any one piece makes things suboptimal, though not necessarily unsolvable.

Your comment only questioned why OpenAI cares about Windsurf from a first party perspective. I expanded the rationale for why the acquisition makes sense at a different level.

Now they also get to see what is sent to Anthropic, Google, DeepSeek, etc., and what is returned. At scale, for a prime area of concern.

Advertising. You are talking about advertising while attempting to call it something else.

It may not require money if that is banned but value will be exchanged and we’ll be back to square one.

I have an API project in development where the majority of the code has been written through Claude Code. It offers an integration of the Congress.gov and GovInfo.gov APIs, and analysis tools for their respective (somewhat overlapping but not always) public information.

I put significant effort in constructing the product & project requirements beforehand and have built a number of simple tools as I ran into roadblocks or inefficiencies, so I can attest to there being a large amount of hype. I can also comfortably state that without the use of LLMs, I would not be this far along.

Having a background in software development (UX side) and a deep interest in technology gives me some insight in to which questions to ask and when to “throw a flag” and ask the LLM to explain why it’s doing something. I don’t believe the hype around one-shot enterprise applications, but the current state of AI programming is usable if people take the care they hopefully would with their own output.

This particular MCP server? No idea. I suspect it is just a different way, rather than a better way.

For tasks like that I personally use pre- and post-commit scripts to run all of my test validation, coverage, Ruff, etc. and output the results as “Current Code Quality” summary reports that are shared with my agents for context.

What software development world do you live in where significant refactoring and rewrites aren’t commonplace? Every project I’ve ever had insider knowledge about started as a prototype and then was extensively reworked until it met the needs of the team…until the next set of requirements dropped and the cycle repeats.

If agent systems allow teams to spin up and test prototypes faster than they previously could do without the agents, isn’t that a useful and valuable step in the right direction?

Addendum: After rereading my comment I realize it may come off as argumentative when it was intended to offer a perspective of not requiring more from the current state of the tech than it offers. “Early days” and all that :)

> I never have and I never will!

That’s an odd flex to roll with for someone who has long been a member of a community of technology enthusiasts, but you be you.

LLMs are tools, not religions. They don’t need to be elevated to a dogmatic level.

When I catch an agent falling into a “debug loop” I ask it to summarize its understanding of the error. Next, I ask it to shift its context to a higher level in the code and look for patterns across my files which would impact {summary of error).

It isn’t foolproof but it has a much better success rate for me than letting it spin.

My mom discovered Champlain Valley about 10 years ago, so now every time she visits (we’re in VA, she’s from CA), she sends an order with a two pound jar ahead so she has a honey she likes in our pantry. I don’t complain at all, because it means we have excellent honey to consume once she leaves :)

Double-secret misdirection. The new stealth!

That reminds me of the escalating “trace buster” scene in “The Big Hit.”

https://youtu.be/2VY_xxL2jL0?si=9hf6ibvtHFCGuCNL

Higher dimensional investigations.