Hacker News: taytus

New comment by taytus in "Green card seekers must leave U.S. to apply, Trump administration says"

taytus — Sun, 24 May 2026 01:14:13 +0000

Signaling.

New comment by taytus in "I'm going back to writing code by hand"

taytus — Mon, 11 May 2026 14:16:26 +0000

Nice Fiction story.

New comment by taytus in "DeepClaude – Claude Code agent loop with DeepSeek V4 Pro"

taytus — Mon, 04 May 2026 15:31:03 +0000

Kimi feels almost limitless. I have the $40/month plan and I've never ever remotely close to hitting the limit. Using opus as the orchestrator.

New comment by taytus in "Tell HN: Claude 4.7 is ignoring stop hooks"

taytus — Fri, 24 Apr 2026 22:15:23 +0000

Skills are not like hooks. Skills can and will inevitably be ignored.

New comment by taytus in "Tell HN: Claude 4.7 is ignoring stop hooks"

taytus — Fri, 24 Apr 2026 22:14:43 +0000

Hooks are hard stops. In theory the model must respect them, unlike Claude.md or agents.md so yeah, it helps a lot.

New comment by taytus in "Tell HN: Claude 4.7 is ignoring stop hooks"

taytus — Fri, 24 Apr 2026 22:13:02 +0000

Yes an no. Some skills are very very tuned to our own workflows. The model providers may come up with some similar alternatives but not always. Also, sometimes you need a solution now and not in three months.

New comment by taytus in "I cancelled Claude: Token issues, declining quality, and poor support"

taytus — Fri, 24 Apr 2026 22:08:29 +0000

I don’t have the prompt at hand but basically I told Kimi (paraphrasing): I have these Claude code skills, and I know it uses different tool calls than you but read them and re-write them as your own tools.

I also created a mini framework so it can test that the skills are actually working after implementation.

Everything runs perfectly.

New comment by taytus in "I Cancelled Claude: Token Issues, Declining Quality, and Poor Support"

taytus — Fri, 24 Apr 2026 18:03:12 +0000

Straight from them, but I know other providers like io.net can be faster but I like to directly support the project.

New comment by taytus in "I cancelled Claude: Token issues, declining quality, and poor support"

taytus — Fri, 24 Apr 2026 17:15:20 +0000

I'd recommend Kimi k2.6 for your use. It is an excellent model at a fraction of the cost, and you can use Claude Code with it.

I did a 1:1 map of all my Claude Code skills, and it feels like I never left Opus.

Super happy with the results.

New comment by taytus in "DeepSeek v4"

taytus — Fri, 24 Apr 2026 10:53:51 +0000

>I asked DS itself and it denied this

Bro, seriously?

New comment by taytus in "An update on recent Claude Code quality reports"

taytus — Thu, 23 Apr 2026 23:22:41 +0000

“after evals and dogfooding” couldn’t have done this before releasing the model? We are paying $200/month to beta test the software for you.

New comment by taytus in "An update on recent Claude Code quality reports"

taytus — Thu, 23 Apr 2026 20:45:44 +0000

They should do a similar report about their communication team. This was horrible mismanaged.

New comment by taytus in "Claude Design"

taytus — Fri, 17 Apr 2026 18:11:18 +0000

Anthropic is making the exact same mistake OpenAI did: lack of focus. Release, release, release, all good apps, all full of bugs. This is a massive mess and people aren't talking enough about how bad all of this is.

New comment by taytus in "Claude Code Routines"

taytus — Tue, 14 Apr 2026 19:09:21 +0000

You are arguing something different. My point is that they must apply these restrictions. Do I think they could have calculated their growth a little better? Yes, of course, but hindsight is 20/20.

New comment by taytus in "Claude Code Routines"

taytus — Tue, 14 Apr 2026 19:07:37 +0000

Like or not, openai isn't having the same compute strain, meaning this was predictable.

New comment by taytus in "Claude Code Routines"

taytus — Tue, 14 Apr 2026 18:10:35 +0000

They are not dumb restrictions. They just don't have the compute. That is the dumb part. Dario did not secure the compute they need so now they are obviously struggling.

New comment by taytus in "System Card: Claude Mythos Preview [pdf]"

taytus — Tue, 07 Apr 2026 19:11:53 +0000

That has also been my experience. And if Mythos is even worse, unless you have a significantly awesome harness, sounds like pretty unusable if you don't want to risk those problems.

New comment by taytus in "Folk are getting dangerously attached to AI that always tells them they're right"

taytus — Sat, 28 Mar 2026 17:38:37 +0000

The stupidest people you know are getting the “you are absolutely right!!” Validation they do not need

New comment by taytus in "Iran-linked hackers claim breach of FBI director's personal email"

taytus — Fri, 27 Mar 2026 15:15:28 +0000

Who said they are the enemy?

New comment by taytus in "Goodbye to Sora"

taytus — Tue, 24 Mar 2026 20:35:48 +0000

How much money did they burn on this? And for what? Nothing?