Hacker Newsnew | past | comments | ask | show | jobs | submit | Foobar8568's commentslogin

These days, at work, I need to support applications build on Azure and Power Platform. Both are a hot mess. We get notifications that our APIM is down for at least 15min every weeks at random times. Power Platform is just a "preview" mess, things break and are not functional.

I complained about it and basically was told to shut up, the industry is using them, so they must be right.

No one is testing anything anymore.


What were the issues behind "APIM down"?

It's a bit astounding to realize Ballmer was good.

At this stage, it's more like Musk and self driving cars, but at least QC around the corner is from mid 1990s

And isn't the response already known in the validation process?

I don't understand your question. Can you elaborate?

Replication of quantum factorisation records with a 8bits home computer, Abacus and a dog

What are you trying to say here? This makes no sense.

That's a famous paper that debunk a lot of things related to marketing announcements. Basically nothing has truly factorized 15, let alone 21.

Look at Xbow which spawned a few "open source" competitors.

Considering that Trump models are Hitler and Putin, how surprising...

More employees to release less stuff.... Smell like consultancy.

Why do you need to do it at the client side? You are leaking so much information on the client side. And considering the speed of Claude code, if you really want to do on the client side, a few seconds won't be a big deal.

Depends what its used by, if I recall theres an `/insights` command/skill built in whatever you want to call it that generates a HTML file. I believe it gives you stats on when you're frustrated with it and (useless) suggestions on how to "use claude better".

Additionally after looking at the source it looks like a lot of Anthropics own internal test tooling/debug (ie. stuff stripped out at build time) is in this source mapping. Theres one part that prompts their own users (or whatever) to use a report issue command whenever frustration is detected. It's possible its using it for this.


> a few seconds won't be a big deal

it is not that slow


Somehow I missed that one. Are there any competition on this?

I always had difficulties with ML and time series, I'll need to try that out.


https://www.datadoghq.com/blog/datadog-time-series-foundatio...

https://moment-timeseries-foundation-model.github.io/

https://arxiv.org/abs/2403.07815

A friend at work used one to predict when our CEO would post in Slack, which is verry entertaining to see if correct.


Many thanks for the links!

There are some other transformer based models on the GIFT leaderboard: https://huggingface.co/spaces/Salesforce/GIFT-Eval


there is TabPFN [1] which also has time series capabilities.

[1] https://priorlabs.ai/tabpfn


I fully agree, I run that one with Q4 on my MBP, and the performance (including quality of response) is a let down.

I am wondering how people rave so much about local "small devices" LLM vs what codex or Claude code are capable of.

Sadly there are too much hype on local LLM, they look great for 5min tests and that's it.


Just train it better with AGENTS.md

This is why I am programming now in Ocaml, files themselves are AI ( ml ).

I am sure you did not forget that pattern matching.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: