Hacker News: ritzaco

Our scheduler is so fast it can rickroll you

ritzaco — Thu, 13 Aug 2026 11:31:44 +0000

Article URL: https://bryntum.com/blog/our-scheduler-is-so-fast-it-can-rickroll-you/

Comments URL: https://news.ycombinator.com/item?id=49284436

Points: 2

# Comments: 0

Gmail will end send-as support from third-party email addresses

ritzaco — Tue, 04 Aug 2026 13:49:57 +0000

Article URL: https://support.google.com/mail/answer/17101213?hl=en

Comments URL: https://news.ycombinator.com/item?id=49168988

Points: 4

# Comments: 4

I abused PostHog's wizard to get free Claude tokens

ritzaco — Sun, 02 Aug 2026 19:53:26 +0000

Article URL: https://techstackups.com/articles/i-abused-posthogs-setup-wizard-to-get-free-claude-access/

Comments URL: https://news.ycombinator.com/item?id=49147696

Points: 2

# Comments: 0

New comment by ritzaco in "Claude Is Not a Compiler"

ritzaco — Tue, 21 Jul 2026 15:25:26 +0000

how many do you add before they become more fancy at auto complete than humans though

LLMs for technical editing: The good, the bad, and the ugly

ritzaco — Thu, 09 Jul 2026 13:10:48 +0000

Article URL: https://techstackups.com/articles/llms-for-technical-editing-the-good-the-bad-and-the-ugly/

Comments URL: https://news.ycombinator.com/item?id=48845274

Points: 20

# Comments: 0

Pro Max Ultra Fable Sol: AI Model Names Have Escaped Containment

ritzaco — Wed, 08 Jul 2026 19:16:09 +0000

Article URL: https://techstackups.com/articles/ai-model-naming-is-a-mess/

Comments URL: https://news.ycombinator.com/item?id=48836200

Points: 3

# Comments: 0

Agent Draw: An agent draws while you talk, built on TLDraw

ritzaco — Wed, 08 Jul 2026 14:18:25 +0000

Article URL: https://techstackups.com/articles/tldraw-agent-draw/

Comments URL: https://news.ycombinator.com/item?id=48832305

Points: 1

# Comments: 0

Are LLMs good enough for Document Extraction?

ritzaco — Wed, 08 Jul 2026 13:34:35 +0000

Article URL: https://www.unsiloed.ai/blog/are-llms-good-enough-for-document-extraction-in-2026

Comments URL: https://news.ycombinator.com/item?id=48831764

Points: 1

# Comments: 0

New comment by ritzaco in "Fable 5 Is Back"

ritzaco — Wed, 01 Jul 2026 20:39:39 +0000

yeah I'm also getting this for standard dev work, anything with kubernetes etc

completely nerfs the model because you can't let it do stuff over a few hours unattended because 90% it's going to switch to opus in first 10 minutes anyway

so seems best thing now is to have it write plans and then default to using opus for work anyway?

New comment by ritzaco in "Claude Science"

ritzaco — Tue, 30 Jun 2026 17:53:48 +0000

A lot of the soft and hard sciences use hacky matplotlib code to produce results and visualisation, without being necessarily data science

From the bits I've seen, I'd take claude-generated code any time over that written by maths, physics, biology, linguistics people. Even though I've seen Claude make some super-big mistakes while doing data analysis I'd guess it's already more reliable than most academics trying to code.

Useful LLM Prompts for Editing Your Own Technical Writing

ritzaco — Tue, 30 Jun 2026 17:47:25 +0000

Article URL: https://techstackups.com/articles/useful-llm-prompts-for-editing-your-own-technical-writing/

Comments URL: https://news.ycombinator.com/item?id=48736393

Points: 3

# Comments: 0

Bryntum: For Agents

ritzaco — Tue, 23 Jun 2026 14:11:39 +0000

Article URL: https://bryntum.com/agents/

Comments URL: https://news.ycombinator.com/item?id=48645273

Points: 1

# Comments: 0

New comment by ritzaco in "GLM 5.2 vs. Opus"

ritzaco — Mon, 22 Jun 2026 07:44:01 +0000

sure that's why we look at a mix of formal benchmarks, one longer analysis of a side-by-side, and various other people who we trust to form an opinion, all covered in the article - not intended to be a formal benchmark, there are enough of those.