Hacker News: selestify

New comment by selestify in "Results from the ASIC puzzle"

selestify — Sun, 04 Oct 2026 20:31:11 +0000

How is this any more of an upwards money funnel than the prohibitively expensive spreads and commissions that hindered lay access to the markets?

New comment by selestify in "GPT-6.1 Sol replaces GPT-6 Sol after just 7 days, with near-Astra intelligence"

selestify — Wed, 30 Sep 2026 11:25:41 +0000

So that some team at Google can hit their OKRs for user adoption and get promoted.

New comment by selestify in "When did Google get so weird?"

selestify — Mon, 28 Sep 2026 12:52:14 +0000

Because some people care a lot more about Ukraine than about a side with pretty unsavory combatants and a radicalized population that supports said unsavory combatants?

New comment by selestify in "When did Google get so weird?"

selestify — Mon, 28 Sep 2026 12:49:54 +0000

Any good descriptions of what it feels like to take part in a formal Turing test, and why it is so humbling?

New comment by selestify in "When did Google get so weird?"

selestify — Mon, 28 Sep 2026 12:41:25 +0000

Geez that's even worse. Google has a deterministic conventional programming fix to the problem and still can't be arsed to fix it?

New comment by selestify in "ASML says it sold 'absolutely nothing' in Europe in 2026"

selestify — Sun, 27 Sep 2026 06:25:30 +0000

Why would the turnaround time need to be so small?

New comment by selestify in "More questions about whether researchers can trust OpenAI with unpublished math"

selestify — Fri, 11 Sep 2026 03:06:19 +0000

What a great analogy, can't believe I haven't heard it before

New comment by selestify in "Claude, change the “Add to Cart” button to blue"

selestify — Thu, 10 Sep 2026 20:42:22 +0000

Ok, but my problem is that what it builds is not right. It's never right on the first try, or the second or third tries. There's always a ton of incremental corrective feedback needed.

Do you run into this problem? If not, then I need to figure out how to stop running into it myself.

If so, then how do you give it all the incremental corrective feedback without a conversation?

New comment by selestify in "Claude, change the “Add to Cart” button to blue"

selestify — Wed, 09 Sep 2026 16:18:55 +0000

The behavior, while slightly exaggerated, rings entirely true for me. From the other comments in this thread, it seems I am prompting poorly in a similar way to the options offered.

I am guessing you prompt differently than what is shown in the game?

New comment by selestify in "Claude, change the "Add to Cart" button to blue"

selestify — Wed, 09 Sep 2026 16:15:57 +0000

Is your harness available for install somewhere?

Surely you still have to give feedback to Claude. How do you do that without talking to Claude directly? By using a different model? But wouldn't that AI have no more common sense than Claude?

New comment by selestify in "Claude, change the “Add to Cart” button to blue"

selestify — Wed, 09 Sep 2026 16:14:22 +0000

What legitimate issues are there around making a fucking button blue?

New comment by selestify in "Claude, change the “Add to Cart” button to blue"

selestify — Wed, 09 Sep 2026 16:12:20 +0000

How is "Make the shopping button blue" not specific? Any human with a lick of digital common sense would be able to understand what I obviously mean. How am I supposed to anticipate every single way the AI could possibly misinterpret a simple fucking instruction like that?

New comment by selestify in "Claude, change the “Add to Cart” button to blue"

selestify — Wed, 09 Sep 2026 16:08:51 +0000

So how would you prompt it instead? Because that's exactly how I prompt it, because any reasonable human being would know exactly what I mean by "Make the shopping button blue", and I am sick and tired of getting shitty results.

New comment by selestify in "Claude, change the “Add to Cart” button to blue"

selestify — Wed, 09 Sep 2026 16:06:29 +0000

How does one learn to interact with Claude more effectively?

New comment by selestify in "Mistral raises €3B"

selestify — Tue, 08 Sep 2026 07:09:58 +0000

Care to share any more?

New comment by selestify in "Three important steps in my maturation process"

selestify — Sat, 22 Aug 2026 06:35:09 +0000

Very good in theory. In practice, how do you actually understand yourself? I have done plenty of meditation and plenty of reading on mental health and psychology. I still don't understand why I specifically act the way I do.

New comment by selestify in "Sticky wage norms and the real wage cost of unexpected inflation"

selestify — Fri, 21 Aug 2026 05:42:07 +0000

Well, with all due respect you could've worded that better. It sounded as if you were making a blanket statement over all individual jobs that involve RSUs, as opposed to a statement over all jobs as an aggregated statistic.

New comment by selestify in "Error by AI scribe during medical appointment leaves patient devastated"

selestify — Thu, 20 Aug 2026 04:59:37 +0000

Cost of medical care is already sky high (in the US). Are you sure you want to introduce even more administrative overhead?

New comment by selestify in "Sticky wage norms and the real wage cost of unexpected inflation"

selestify — Wed, 19 Aug 2026 03:54:03 +0000

This was not my experience working at FAANG. RSU's started out as 30% of my comp and ended up well over 60% by the time I left.

Either way, definitely not "might as well round to zero". I have never worked anywhere where that was the case.

New comment by selestify in "Fixing a bricked Framework laptop"

selestify — Wed, 19 Aug 2026 00:31:11 +0000

Just ask for citations by forcing the LLM to provide a verbatim quote from a linked source. If the LLM is incapable of doing so without hallucinating (cough, Gemini, cough) use a better one.

I don't get the LLM hate on this site sometimes. Just because it is easy to use an LLM irresponsibly doesn't mean all LLM usage has to be irresponsible.