Hacker News: pineapple_opus

New comment by pineapple_opus in "Age verification is just a precursor to automated attribution of speech"

pineapple_opus — Mon, 29 Jun 2026 05:21:09 +0000

Mask in real life then, mask in social internet now. Meaning stays the same. I like this analogy.

New comment by pineapple_opus in "Age verification is just a precursor to automated attribution of speech"

pineapple_opus — Mon, 29 Jun 2026 05:14:43 +0000

They already have started right ? Like example - bluesky (bsky.social)

New comment by pineapple_opus in "Good clarity on AI observability and in simple terms"

pineapple_opus — Thu, 25 Jun 2026 13:45:02 +0000

They have gone and described in really simple terms on AI observability. This is the best page on AI observability I've come across. Some other pages are just giving us some pills to digest, like look at these new three pillars as opposed to old three pillars and whatnot.

Even section like "How tools instrument your code" makes sense for an AI forward company employee to understand and act on.

Good clarity on AI observability and in simple terms

pineapple_opus — Thu, 25 Jun 2026 13:45:02 +0000

Article URL: https://posthog.com/blog/what-is-ai-observability

Comments URL: https://news.ycombinator.com/item?id=48673299

Points: 4

# Comments: 1

New comment by pineapple_opus in "When AI Builds Itself: Our progress toward recursive self-improvement"

pineapple_opus — Fri, 05 Jun 2026 06:17:52 +0000

Eye catching - "Open ended problems" claude code session success rate jumped from 20% (pre opus 4.5 release) to 70% after sometime after opus 4.6 was released.

New comment by pineapple_opus in "Alphabet announces $80B equity capital raise to expand AI infra and compute"

pineapple_opus — Tue, 02 Jun 2026 08:23:11 +0000

Yeah this seems true. Claude Code are famously dubbed as best AI coding agent, but google doesn't care about that niche I guess. Somehow, I still rely on google search as they have diversified it.

If you ask questions, it will enable "AI overview" , but if we search about particular object/platform like "Google stock" or "bbc news", it will give the old classic search experience and we woulnd't need to swallow "AI overview" pill in that case.

New comment by pineapple_opus in "Using AI to write better code more slowly"

pineapple_opus — Tue, 26 May 2026 06:00:45 +0000

> This is the opposite of the “10x productivity” slop-cannon style of development that most people imagine when they think of vibe coding, but I find it very satisfying.

I can relate to this. When I spend time on writing unit test , even the one which takes 1% of code coverage, it will be honestly wholesome moment for me to ship it confidently.

New comment by pineapple_opus in "The last six months in LLMs in five minutes"

pineapple_opus — Tue, 19 May 2026 06:39:54 +0000

All I see is mention of how various models generate image of "pelican riding bicycle(s)"

New comment by pineapple_opus in "What I'm Hearing About Cognitive Debt (So Far)"

pineapple_opus — Tue, 05 May 2026 06:10:56 +0000

As you said it's distributed across - People, conversations, AI agents , tooling, etc... , can't the LLM Knowledgebase/ wiki ( a.k.a. org's second brain) solve this ? I think if , second brain exists, no one needs to pay cognitive debt.

New comment by pineapple_opus in "Bun is being ported from Zig to Rust"

pineapple_opus — Tue, 05 May 2026 06:00:13 +0000

I use to do this and then do test manually to validate everything works as expected in my small open source project. But then over the time I saw that some bugs crept in which I was unable track since I was doing manual testing. So I wrote some e2e tests with playwright and I think that gives a bit relief (at least).