Viewing profile — 00deadbeef
00deadbeef
HN member- Joined
- Fri, Jan 01, 2016, 12:15 AM UTC
- HN karma
- 476
- Public activity
- 239 items
- HN profile
- View on Hacker News ↗
About 00deadbeef
No profile information was provided.
Recent public activity
-
comment
Comment #49164865
My non-technical cofounder managed to vibe code a holding page with Claude Design and it walked him through deploying it to Netlify. However for some reason it had him deploy a sin…
-
comment
Comment #49001602
It’s cool. One issue I have is that the colours for “Castle & château” and “Ruin” are very similar. When you tap a marker often you can’t see the castle in the photo because it’s c…
-
comment
Comment #48689525
It’s still easy to understand as the more capable the model the bigger the celestial body they’re named after.
-
comment
Comment #48520053
One good thing to come of vibecoding is native apps are less effort, so hopefully there will be more alternatives to Electron crap apps.
-
comment
Comment #48513364
I don't understand the point you're making. It can be both the most powerful LLM on the market, and have no adoption in critical infrastructure.
-
comment
Comment #48513343
I think this could kill LLM development. What's the point in pushing boundaries, when your business model is already hard to profit from, only to be blocked from selling your work …
-
comment
Comment #48470707
The first number is which generation of their LLMs it belongs to. Fable is the first model in the 5th generation. The second number is an incremental release, not a generational le…
-
comment
Comment #48470676
They do https://platform.claude.com/docs/en/build-with-claude/struct... > Structured outputs are generally available on the Claude API for Claude Opus 4.8, Claude Mythos Preview, C…
-
comment
Comment #48470651
I doubt they'll phase out Haiku, some work needs speed more than intelligence. Haiku can answer a lot faster than Sonnet.
-
comment
Comment #48470595
I haven't tried Fable yet but my experience with Claude is it does not engineer things well. Without direction from me, it will either over-engineer things to the point of absurdit…
-
comment
Comment #48470544
But it doesn't make you the good guy, it makes you the best of a bad bunch. The least bad. Dario gets a boner every time he talks about taking your job.
-
comment
Comment #48470507
Opus 4.8 already drops to Sonnet when you ask it cybersecurity or biology questions
-
comment
Comment #48470487
Of course. You use their AI to ship code full of bugs and security holes and then they conveniently have the tool to fix them, for an extra fee.
-
comment
Comment #48146923
5 minutes to load and it just dumps me to a documentation site with no useful information about that this is, who made it, what it can do, etc.
-
comment
Comment #47830296
What if they have an actual back-end with long-running processes and scheduled tasks?
-
comment
Comment #47830290
Maybe that's why all these vibe coded slop apps also use Clerk for auth alongside Supabase etc
-
comment
Comment #47781597
I bought a 24TB for £365 last June. It's £905 now.
-
comment
Comment #47749559
I like it so far. Some features I'd like: - XL bar size - even large feels a bit small on a 6K display - I have grouped windows off, but it would be nice if there was an option to …
-
comment
Comment #47749502
I leave it there because I have a large screen and it looks pretty
-
comment
Comment #47259161
But the Mac has a huge trick up its sleeve: it can run iOS and iPadOS apps. Meaning developers only have to make relatively minor adjustments to make it nice in the desktop and bin…
-
comment
Comment #47259146
WhatsApp has a native Mac app
-
comment
Comment #47259132
> I wouldn’t even care about the 8GB of ram if I could just add some myself. I think that’s pretty unreasonable when they’re using an iPhone SoC to keep it cheap because they have …
-
comment
Comment #47103259
What everyone else said, plus the cuteness factor
-
comment
Comment #46942056
Opus 4.5 successfully ignored the first line of my CLAUDE.md file last week
-
comment
Comment #46908598
Yeah it's way too vague. This morning: (new chat) 42 seconds of thinking, 20 lines of code changed in 4 files = 5% usage Last night: 25 minutes of thinking, 150 lines of code gener…