Hacker News: sagarpatil

New comment by sagarpatil in "Amazon CEO's talks with U.S. officials triggered crackdown on Anthropic models"

sagarpatil — Sun, 14 Jun 2026 07:03:44 +0000

Doesn’t Amazon own 14% of Anthropic?

New comment by sagarpatil in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

sagarpatil — Sat, 13 Jun 2026 04:44:11 +0000

They should be happy this happened before their IPO.

New comment by sagarpatil in "Claude Fable 5"

sagarpatil — Wed, 10 Jun 2026 03:47:26 +0000

Did you hit your weekly limit ?

New comment by sagarpatil in "Apple reveals new AI architecture built around Google Gemini models"

sagarpatil — Tue, 09 Jun 2026 05:04:47 +0000

Go Genmoji!

New comment by sagarpatil in "Gemini 3.5 Flash"

sagarpatil — Wed, 20 May 2026 06:19:54 +0000

Frontpage, Dreamviewer, flash, photoshop lol. We are old.

New comment by sagarpatil in "Claude Opus 4.7"

sagarpatil — Fri, 17 Apr 2026 04:32:12 +0000

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.

New comment by sagarpatil in "Claude Opus 4.7"

sagarpatil — Fri, 17 Apr 2026 04:27:45 +0000

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 all day, about 8 hours, and did not run into any limits. 5.4 surprised me many times by doing things I usually would not do myself, because I am lazy, so yeah, I am sticking with 5.4 for now until all the Claude drama is over.

New comment by sagarpatil in "Turn your best AI prompts into one-click tools in Chrome"

sagarpatil — Wed, 15 Apr 2026 03:54:03 +0000

Absolutely right! You must be fun at parties .

New comment by sagarpatil in "1M context is now generally available for Opus 4.6 and Sonnet 4.6"

sagarpatil — Sat, 14 Mar 2026 09:37:16 +0000

This has been my experience too.

New comment by sagarpatil in "Agent Safehouse – macOS-native sandboxing for local agents"

sagarpatil — Mon, 09 Mar 2026 07:10:15 +0000

Looks good. I’ll give it a try.

New comment by sagarpatil in "GPT-5.4"

sagarpatil — Fri, 06 Mar 2026 08:16:06 +0000

Or CLI.

New comment by sagarpatil in "Google Workspace CLI"

sagarpatil — Thu, 05 Mar 2026 06:50:25 +0000

I used Claude in chrome and Claude Code. It did everything for me.

New comment by sagarpatil in "New iPad Air, powered by M4"

sagarpatil — Tue, 03 Mar 2026 03:28:35 +0000

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.

New comment by sagarpatil in "MCP server that reduces Claude Code context consumption by 98%"

sagarpatil — Sun, 01 Mar 2026 08:37:18 +0000

Agreed. I removed it.

New comment by sagarpatil in "Agent Skills"

sagarpatil — Wed, 04 Feb 2026 06:39:06 +0000

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 understand how is this different from what we already have in markdown files.

New comment by sagarpatil in "GLM 4.5 with Claude Code"

sagarpatil — Sat, 06 Sep 2025 03:53:56 +0000

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 seems dumb? I asked it to find and replace a string. It only made the change in one file. Codex worked fine. Can Z.ai confirm if this is the model we get through their API or is it quantized for Claude Code use?

New comment by sagarpatil in "GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models [pdf]"

sagarpatil — Tue, 12 Aug 2025 04:57:19 +0000

I’ve been using it and I think it’s on par with sonnet.

New comment by sagarpatil in "GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models [pdf]"

sagarpatil — Tue, 12 Aug 2025 04:56:34 +0000

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.

New comment by sagarpatil in "Ask HN: What trick of the trade took you too long to learn?"

sagarpatil — Tue, 05 Aug 2025 03:29:38 +0000

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 Playwright or an MCP server to perform tasks. What’s interesting is that even the agent doesn’t know many commands upfront; it simply uses the help option to discover what’s available.

New comment by sagarpatil in "OpenAI’s Windsurf deal is off, and Windsurf’s CEO is going to Google"

sagarpatil — Sun, 13 Jul 2025 03:01:08 +0000

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 the $200 plan, and it’s absolutely worth it (never thought I’d say this for a CLI app).