Viewing profile — menzoic
menzoic
HN member- Joined
- Wed, Jul 03, 2013, 3:14 AM UTC
- HN karma
- 1,016
- Public activity
- 396 items
- HN profile
- View on Hacker News ↗
About menzoic
No profile information was provided.
Recent public activity
-
comment
Comment #48081701
The difference is not that it’s “worthless”. The difference is that now it’s “practical” to implement given the low effort. I wouldn’t be sad about defeating lower complexity chall…
-
comment
Comment #47886647
API prices may be profitable. Subscriptions may still be subsidized for power users. Free tiers almost certainly are. And frontier labs may be subsidizing overall business growth, …
-
comment
Comment #47759410
I just put your question into GPT-5 Pro
-
comment
Comment #47561346
I work at Airbnb where I write 99% of my production code using LLMs. Spotify's CEO recently announced something similar, but I mention my employer not because my workflow is sponso…
- story
-
comment
Comment #47137838
I'm at Airbnb now working primarily with LLMs
-
comment
Comment #47136659
I’ve found there are two major mindset shifts that helped me start passing tech interviews consistently: 1. Study the algorithms and patterns, not the questions 2. Treat it like a …
- story
-
comment
Comment #47136563
I work at Airbnb where I write 99% of my production code using LLMs. Spotify's CEO recently announced something similar, but I mention my employer not because my workflow is sponso…
- story
-
comment
Comment #47125488
It's basically the typical SDLC boosted with LLMs. Especially the part where you can explore tradeoffs and alternative approaches rapidly.
-
comment
Comment #47125457
LOL, honestly I hated Codex when it first came out. It was backed by o3 at the time. But literally as soon as GPT-5 came out in Codex and with the "high" option, I completely switc…
-
comment
Comment #47125423
> get the best results when the context window is right around 70% I used to be trigger happy with /compact or using the hand off technique to transfer knowledge between sessions w…
-
comment
Comment #47125194
I work at Airbnb where I write 99% of my production code using LLMs. Spotify's CEO recently announced something similar, but I mention my employer not because my workflow is sponso…
- story
-
comment
Comment #46955372
I would think it’s due to the non determinism. Leaking context would be an unacceptable flaw since many users rely on the same instance. A/B test is plausible but unlikely since th…
-
comment
Comment #46510575
Leetcode problem
-
comment
Comment #45702331
Studies on rats have shown significant similarities between sugar consumption and drug-like effects, including bingeing, craving, tolerance, withdrawal, dependence, and reward. Som…
-
comment
Comment #45286222
Why does skyfall.dev block Nigeria?
-
comment
Comment #45132524
>At that point, a shared ledger implemented with traditional databases / protocols would be faster, easier, and more transparent. This is missing the fundamental idea behind blockc…
-
comment
Comment #44931221
GPT-5 is a text only model. ChatGPT uses 4o for images still
-
comment
Comment #44831155
The idea is that AGI will be able to self improve at an exponential rate. This is where the idea of take off comes from. That self improvement part isn’t happening today.
- story
-
comment
Comment #44587430
Genius transition plan
-
comment
Comment #44335597
How is the security risk propaganda?