pbowyer

Seems fair to me. The VC-backed SQLite services have been shouting about their services as if they came up with the idea, and this only balances that out.

He's right that histories start too late, and I'd like to see more posts like this that trace the history back further than the last 5 years. Like for databases, a lot can go back 20+ years and it's good to read how the idea came about (independently from many people), how it developed over time and why.

Also "Blitz Street" with Tony Robinson, where they build a street of typical 1940s houses and slowly increase the WW2 bomb size to see the damage the would do.

I'm just about to build my own external temperature and humidity sensor, using a Sensiron SHT45 sensor with integrated PTFE filter.

I've had Tuya and Aqara sensors outside, undercover and out of direct rain for the past 3 years, and every one lasts about a year before the humidity sensor gets stuck at the maximum reading. Even bringing it indoors doesn't get it working again. I'm hoping the built-in heater on the SHT45 will help when we're sat in sea mist or sea fog and keep the sensor working for longer.

What would be the correct way to do benchmarking/profiling here? I ask as I've started to run some for Vinyl cache to see what performance issues I can find, and I've quickly learned just how hard it is to get good, repeatable benchmarks that isolate the right thing.

I like seeing what people create, and you've created something with some interesting features, particularly around the path map and keeping all drafts. I'm forever duplicating a paragraph and rewording it 6 or 7 times, then deleting the rest - and the next day think "no try #2 was better than the one I kept".

Ignore the haters, they're a HN rite of passage. Good luck with your writing!

Can you say more? This sounds like it could be more useful than trying to build a knowledge base (say qmd) and then get the models to search it for the right context each time.

> I feel like this benchmark reiterates my disbelief that anyone uses the latest Anthropic models for any productive work. They seem to be the best at burning tokens and spawning unnecessary subagents even for well-defined and tightly scoped tasks.

I keep Claude around for some specific tasks:

- Linked up to Figma MCP to implement front-end stuff

- Data analysis, in the "Connect AI to a data source and ask questions" way. I've tried both Opus 4.8 high and GPT 5.5 high for this and Opus is stronger because it gets the intent in the question better

I used to keep it around for planning too, but the 4.8 plans have had more holes than swiss cheese.

> I'm only using Opus at all because GPT-5.5 in the subscriptions only has a small (400k, but 258k effective) context window.

Do you find that makes a difference in your work? I've been using 5.5 high/xhigh to optimize and benchmark a C codebase, and just reading the initial code virtually fills the first context window. A session will auto-compact 5-15 times, but it seems to do okay in spite of that because the task is mainly focused on the latest window each time.

I think for programming the strength of GPT over Opus is winning here over the context window.

The one positive of this is it seems to have livened up the open source project (Vinyl Cache). Features that haven't been added for years are now being worked on, whether they step on the toes of the commercial offering or not.

Jira is the one product I feel needs to be AI native.

AI native in the sense that it papers over the pain points.

New JIRA admin? AI will set it up to do what you want (after all, Atlassian has a great training set as they can see which Cloud installs work well)

Need to set up a workflow? Bam, AI to do that.

Need to onboard a user or manage permissions? Again, have a chatbot to do it (as a time-to-time Jira standin Admin, changing permissions always needs doing in 2+ places and devolves into a "Can you see this yet?" round of questions)