Hacker News: beydogan

New comment by beydogan in "Qwen3.7-Max: The Agent Frontier"

beydogan — Wed, 20 May 2026 13:12:05 +0000

honestly, initial version of Opus-4.6 was much better than whatever we are being served right now as 4.7. If it performs same level to that, i'm totally willing to switch.

New comment by beydogan in "Claude Opus 4.5"

beydogan — Mon, 24 Nov 2025 19:44:35 +0000

100% dumber, especially since last 3-4 days. I have two guesses:

- They make it dumber close to a new release to hype the new model

- They gave $1000 Claude Code Web credits to a lot of people, which increased the load a lot so they had to serve quantized version to handle the it.

I love Claude models but I hate this non transparency and instability.

New comment by beydogan in "Claude Sonnet 4.5"

beydogan — Mon, 29 Sep 2025 19:05:09 +0000

Me too. I have Claude Max and 2 ChatGpt accounts for Codex.

I was a huge claude fan but recently find myself using only codex. When it gets stuck, I try Claude for some simple tasks, sometimes ask same questions in parallel, Claude Code with Opus performs really bad comparing to codex.

New comment by beydogan in "Claude now has access to a server-side container environment"

beydogan — Tue, 09 Sep 2025 17:00:13 +0000

Instead of building random features, they have to fix their quality first.

I'm on 100$ Max plan, I would even buy 2x 200$ plan if Opus would stop randomly being dumb. Especially after 7am ET time.

New comment by beydogan in "Ask HN: Is anyone using Function Calling with LLMs in production?"

beydogan — Tue, 21 Jan 2025 16:55:16 +0000

I do.