Wrong. There can be a lot of subjectivity and pretending that some golden answer exists does more harm and narrows down the scope of what you can build.

My other main problem with data extraction tasks and why I'm not satisfied with any of the existing eval tools is that the schemas I write change can drastically as my understanding of the problem increases. And nothing really seems to handle that well, I mostly just resort to reading diffs of what happens when I change something and reading the input/output data very closely. Marimo is fantastic for anything visual like this btw.

Also there is a difference between: the problem in reality → the business model → your db/application schema → the schema you send to the LLM. And to actually improve your schema/prompt you have to be mindful of the entire problem stack and how you might separate things that are handled through post processing rather than by the LLM directly.

> Abstract model calls. Make swapping GPT-4 for Claude a one-line change.

And in practice random limitations like structured output API schema limits between providers can make this non-trivial. God I hate the Gemini API.

---

Summary: What Is Objectively Provable

- The extension stores its config under the key changedetection_config

- 16 API endpoints in the extension are 1:1 matches with changedetection.io's documented API

- 16 data model field names are exact matches with changedetection.io's Watch model (including obscure ones like time_between_check_use_default, history_n, notification_muted, fetch_backend)

- The authentication mechanism (x-api-key header) is identical

- The default port (5000) matches changedetection.io's default

- Custom endpoints (/auth/, /feature-flags, /email/, /generate_key, /pregate) do NOT exist in changedetection.io — these are proprietary additions

- The watch limit error format is completely different from changedetection.io's, adding billing-specific fields (current_plan, upgrade_required)

- The extension ships with error tracking that sends telemetry (including user emails on login) to the developer's GlitchTip server at 100% sample rate

The extension is provably a client for a modified/extended changedetection.io backend. The open question is only the degree of modification - whether it's a fork, a proxy wrapper, or a plugin system. But the underlying engine is unambiguously changedetection.io.

https://news.ycombinator.com/item?id=47349069

> yeah they're shipping too fast and everything is buggy as shit

- fork conversation button doesn't even work anymore in vscode extension

- sometimes when I reconnect to my remote SSH in VSCode, previously loaded chats become inaccessible. The chats are still there in the .jsonl files but for some reason the CC extension becomes incapable of reading them.

-- this issue happens so frequently that I ended up making a skill to allow CC to dig up info from the bugged sessions

I'm gonna switch some workflows to qwen3.5.

There's a lot of tasks that benefit from just having a mildly capable LLM and 2.5 Flash Lite worked out of the box for cheap.

Can we get flash lite lite please?

Edit: Logan said: "I think open source models like Gemma might be the answer here"

Implying that they're not interested in serving lower end Gemini models?

yeah they're shipping too fast and everything is buggy as shit

- fork conversation button doesn't even work anymore in vscode extension

- sometimes when I reconnect to my remote SSH in VSCode, previously loaded chats become inaccessible. The chats are still there in the .jsonl files but for some reason the CC extension becomes incapable of reading them.

But there's some irony in this happening to Anthropic after all the constant hawkish fearmongering about the evil Chinese (and open source AI sentiment too).

Comments URL: https://news.ycombinator.com/item?id=47061793

Points: 3

# Comments: 0

I feel like this applies for many of you.

Google doesn't even provide a tokenizer to count tokens locally. The results of this stupidity can be seen directly in AI studio which makes an API call to count_tokens every time you type in the prompt box.

I have a SKILL.md for marimo notebooks with instructions in the frontmatter to always read it before working with marimo files. But half the time Claude Code still doesn't invoke it even with me mentioning marimo in the first conversation turn.

I've resorted to typing "read marimo skill" manually and that works fine. Technically you can use skills with slash commands but that automatically sends off the message too which just wastes time.

But the actual concept of instructions to load in certain scenarios is very good and has been worth the time to write up the skill.

How do I seek to the exact first frame of a timestamp with mux? I've tried a few things but it seems to always go to the nearest keyframe rather than the first frame at e.g. 00:34. This is sensible default behaviour but bad for my use case.

Ralph loops are also stupid because they don't make use of kv cache properly.

---

https://github.com/steveyegge/gastown/issues/503

Problem:

Every gt command runs bd version to verify the minimum beads version requirement. Under high concurrency (17+ agent sessions), this check times out and blocks gt commands from running.

Impact:

With 17+ concurrent sessions each running gt commands:

- Each gt command spawns bd version

- Each bd version spawns 5-7 git processes

- This creates 85-120+ git processes competing for resources

- The 2-second timeout in gt is exceeded

- gt commands fail with "bd version check timed out"