News for hackers. Stuff that matters.

weisser

would you describe yourself as particularly good or the models as particularly bad?
Re:Live agent face-off in CivBench: Claude Opus 4.6 vs. GPT-5.2 on Thursday February 05, 2026 @07:15PM (#46907351)
what do you use for memory?
Re:Live agent face-off in CivBench: Claude Opus 4.6 vs. GPT-5.2 on Thursday February 05, 2026 @04:34PM (#46905687)
What sort of context do you give the APIs when you are starting the game? Does it need to learn the rules as it goes?
Re:Django Reinhardt on Thursday February 05, 2026 @04:31PM (#46905664)
an unbelievably cool style — excited for new generations to "discover" him
Re:SF Microclimates API on Tuesday January 27, 2026 @02:53AM (#46776755)
Re:SF Microclimates API on Monday January 26, 2026 @07:11PM (#46773693)
thanks I will update the homepage to reflect this.
Re:SF Microclimates API on Monday January 26, 2026 @06:31PM (#46773236)
thanks for catching this. just fixed.

note that I also have a system where if the temperature seems outlier compared to direct neighbors it averages the 3 nearest neighbors. this usually occurs in neighborhoods with a single sensor that can skew the results heavily at certain times of the day, etc.

Re:SF Microclimates API on Monday January 26, 2026 @02:57AM (#46762955)
Good flag. I've just added add fallback to the nearest location with a sensor to the repo.
Re:SF Microclimates API on Monday January 26, 2026 @02:16AM (#46762740)
This was directly inspired by Mr Chilly which was designed by my friend Anna Bleker.

It's an excellent iOS app: https://mr-chilly.com/

My goal was to do something similar as a Claude Code skill

Re:SF Microclimates API on Monday January 26, 2026 @02:08AM (#46762687)
submit a PR
Re:SF Microclimates API on Monday January 26, 2026 @02:07AM (#46762686)
no I made this primarily for a Claude Code / Clawdbot skill so I am not making it super sophisticated.

You should use Purple Air if you want to make it more focused https://www2.purpleair.com/

Re:SF Microclimates API on Monday January 26, 2026 @02:05AM (#46762676)
> I don't understand why it includes indoor sensors at all let alone by default.

Add location_type=0 to only get outdoor sensors

Re:SF Microclimates API on Monday January 26, 2026 @02:00AM (#46762646)
Fork the Github! Would love to see it elsewhere :)
Re:SF Microclimates API on Monday January 26, 2026 @01:59AM (#46762644)
I made this primarily to use inside Claude Code in terminal but maybe I'll make a little demo on the website if you put in an SF zip code.
Re:SF Microclimates API on Monday January 26, 2026 @01:55AM (#46762621)
Purple Air is the primary source but it's open source and you could try other providers https://github.com/solo-founders/sf-microclimates
Re:Ask HN: I underestimated how lonely building solo can be on Monday November 03, 2025 @05:49PM (#45805410)
There's another option other than solo or co-founder.

It's called "solo, together"

Spend time around others who are also building solo and develop meaningful relationships with them.

Re:Bench Accounting Acquired by Employer.com on Tuesday December 31, 2024 @02:11AM (#42557058)
> It's very possible it has been a deal long time in the making.

No.

From the acquirer:

“It fits our product roadmap. It was super serendipitous…I saw that news. I was like, ‘This is perfect.’ It checks a lot of boxes for us. It was just a really good synergistic opportunity, so we went for it.”

https://multitudes.weisser.io/p/how-employercom-acquired-ben...

Re:Employer.com acquired Bench Accounting in under 48 Hours on Tuesday December 31, 2024 @02:08AM (#42557046)
These are quotes from a conversation with the acquirer that happened <2 hours ago. Should it be included in that older post?
Re:A bill to designate the bald eagle as America's national bird on Wednesday December 18, 2024 @03:10PM (#42454524)
The bald eagle seems the natural choice but if for some reason that were not an option would would the next best pick be for national bird?
Re:Show HN: Mem0 – open-source Memory Layer for AI apps on Wednesday September 04, 2024 @02:16PM (#41448772)
Congrats on the launch!

I messed around with the playground onboarding...here's the output:

With Memory Mem0.ai I know that you like to collect records from New Orleans artists, and you enjoy running.

Relevancy: 9/10

Without Memory I don’t have any personal information about you. I don’t have the ability to know or remember individual users. My main function is to provide information and answer questions to the best of my knowledge and training. How can I assist you today?

Relevancy: 4/10

--

It's interesting that "With Memory" is 9/10 Relevancy even though it is 100% duplication of what I had said. It feels like that would be 10/10.

It's also interesting that "Without Memory" is 4/10 — it seems to be closer to 0/10?

Curious how you thinking about calculating relevancy.

Older »