Viewing profile — sagarpatil
sagarpatil
HN member- Joined
- Sat, Jan 04, 2014, 5:43 AM UTC
- HN karma
- 304
- Public activity
- 217 items
- HN profile
- View on Hacker News ↗
About sagarpatil
Recent public activity
-
comment
Comment #48829125
Spot on. OpenAI releases GPT 5.6 on Thursday.
-
comment
Comment #48583088
1) what?
-
comment
Comment #48524869
Doesn’t Amazon own 14% of Anthropic?
-
comment
Comment #48513279
They should be happy this happened before their IPO.
-
comment
Comment #48471185
Did you hit your weekly limit ?
-
comment
Comment #48456674
Go Genmoji!
-
comment
Comment #48203784
Frontpage, Dreamviewer, flash, photoshop lol. We are old.
-
comment
Comment #47802469
Same. I’ve lived in Claude Code since the beta release and last couple of weeks was horrible. I’ve been using codex for last couple of days and it’s much smarter than 4.6.
-
comment
Comment #47802446
It worked. Although I have a Claude Code subscription, I got the ChatGPT Pro plan, and 5.4 xHigh at 1.5x speed was better than 4.6 with adaptive thinking disabled. I was working al…
-
comment
Comment #47774524
Absolutely right! You must be fun at parties .
-
comment
Comment #47374913
This has been my experience too.
-
comment
Comment #47305685
Looks good. I’ll give it a try.
-
comment
Comment #47272355
Or CLI.
-
comment
Comment #47258397
I used Claude in chrome and Claude Code. It did everything for me.
-
comment
Comment #47227631
Anyone who has all three and found iPad still useful? I’m mostly on my MacBook and use iPhone when I’m not on my MacBook, or Apple TV.
-
comment
Comment #47204866
Agreed. I removed it.
-
comment
Comment #46882294
So the only difference between slash custom command and agent skills is that they can be invoked only when needed instead of stuffing the whole markdown file? I’m trying to underst…
-
comment
Comment #45146456
I was blown away by this model. It was definitely comparable to sonnet 4. In some of my tests, it performed as good as Opus. I subscribed to their paid plan, and now the model seem…
-
comment
Comment #44872546
I’ve been using it and I think it’s on par with sonnet.
-
comment
Comment #44872539
Not OP. Chutes.ai charges $0.20 per 1M tokens. I don’t think it uses caching though because I ended up burning $30 in an hour or two. I had to move back to Claude Code.
-
comment
Comment #44794039
Claude Code recently showcased how powerful it can be when you don’t have to memorize commands. My AI agent works similarly. It finds the right CLI commands instead of relying on P…
-
comment
Comment #44547137
I strongly agree with you. I’m more of a CLI guy, and Claude Code just works. Most good projects have a CLI anyway (gcloud, GitHub CLI, Vercel, etc.). I prefer CLI vs MCP’s. I’m on…
-
comment
Comment #44547107
All the AI models are no using em-dashes. ChatGPT keeps using them even after explicitly told not to. Anybody know what’s up with these models?
-
comment
Comment #44383737
You might want to give this a try: https://github.com/opencode-ai/opencode
-
comment
Comment #44351997
https://chorus.sh/ has a BYOK version Openwebui