pasrom 🚵🏻🤖❤️💉

613 posts

pasrom 🚵🏻🤖❤️💉

pasrom 🚵🏻🤖❤️💉

@pasr0m

@[email protected]

Österreich Katılım Kasım 2017
1.7K Takip Edilen206 Takipçiler
Peter Steinberger 🦞
Peter Steinberger 🦞@steipete·
@reikon_io I've been working on getting the claude -p fallback feature working after Boris confirmed that it's a classifier bug and not intentional. We're still blocked and seems that got me banned too.
English
5
0
16
5.9K
Peter Steinberger 🦞
Peter Steinberger 🦞@steipete·
Yeah folks, it's gonna be harder in the future to ensure OpenClaw still works with Anthropic models.
Peter Steinberger 🦞 tweet media
English
541
248
5.5K
1.4M
pasrom 🚵🏻🤖❤️💉 retweetledi
Fidji Simo
Fidji Simo@fidjissimo·
If there is one good thing that can come out of having my health issues exposed to the world, it’s raising awareness for complex chronic conditions like POTS, MECFS, Long Covid or EDS. 🧵 businessinsider.com/what-is-pots-f…
English
135
189
1.6K
233.1K
pasrom 🚵🏻🤖❤️💉 retweetledi
Claude
Claude@claudeai·
New in Claude Code: auto mode. Instead of approving every file write and bash command, or skipping permissions entirely, auto mode lets Claude make permission decisions on your behalf. Safeguards check each action before it runs.
English
2.1K
2.9K
39.3K
7.7M
pasrom 🚵🏻🤖❤️💉 retweetledi
Fabian Pimminger
Fabian Pimminger@i_am_fabs·
Sie haben auch erstmals ein AI-generated Video aus den vorher nachher Bildern online gestellt, was das Ausmaß finde ich nochmal deutlicher macht. Die Gletscher Österreichs sind in der Endphase.
Deutsch
4
26
75
3.3K
pasrom 🚵🏻🤖❤️💉 retweetledi
Claude
Claude@claudeai·
A small thank you to everyone using Claude: We’re doubling usage outside our peak hours for the next two weeks.
English
1.9K
3.5K
48.4K
12.7M
pasrom 🚵🏻🤖❤️💉 retweetledi
Mario Zechner
Mario Zechner@badlogicgames·
Yes, I'm very european. Still outclanking most of you.
English
3
1
51
2.4K
pasrom 🚵🏻🤖❤️💉
@steipete @badlogicgames what if instead of people submitting LLM-generated PRs, they just submit well-described feature specs? maintainers evaluate the idea first, then generate code themselves with full project context. maybe let people donate compute tokens instead of code.
English
1
0
0
16
Fabian Pimminger
Fabian Pimminger@i_am_fabs·
WO IST DIESE PERSON ÜBERGEWICHTIG??????
Deutsch
6
0
38
1.6K
Fabian Pimminger
Fabian Pimminger@i_am_fabs·
Ob Radsport toxisch ist habe ich gefragt
Fabian Pimminger tweet media
Deutsch
7
0
54
4.6K
pasrom 🚵🏻🤖❤️💉 retweetledi
Michael Stingl
Michael Stingl@neurostingl·
Wenn man diesen Podcast hört, bleibt man etwas erstaunt zurück, dass solche Erklärungsmodelle von ME/CFS 2026 noch immer ernst genommen werden. Man muss Realität und Stand der Wissenschaft schon sehr selektiv wahrnehmen, damit das plausibel scheint.
Bettina Grande@GrandeBettina

1/ Der „Klinisch Relevant Podcast“ mit Prof. Yesim Erim und Prof. Volker Köllner wird von vielen Ärztinnen und Ärzten gehört. Umso wichtiger ist es, genau hinzuhören, wenn über #MECFS gesprochen wird. Ein paar Punkte aus der aktuellen Folge.

Deutsch
8
70
317
7.1K
JB
JB@JasonBotterill·
It’s so annoying that shutting down my macbook takes extra 2 mins now since Claude MacOS comes with its own VM.
JB tweet media
English
29
4
1.4K
112.9K
pasrom 🚵🏻🤖❤️💉 retweetledi
Thariq
Thariq@trq212·
We've reset rate limits for all Claude Code users. Yesterday we rolled out a bug with prompt caching that caused usage limits to be consumed faster than normal. This is hotfixed in 2.1.62. Make sure you upgrade to the latest and hope you enjoy using Claude Code this weekend!
English
726
448
11.1K
1M
pasrom 🚵🏻🤖❤️💉 retweetledi
Felix Rieseberg
Felix Rieseberg@felixrieseberg·
Also, since we're already busy shipping: Update your Claude Code to the latest version, run /remote-control, and then just remote-control your Claude Code from your mobile phone. Coding on your computer but from your phone so you can go and touch grass and still push code
English
24
10
393
24K
Peter Steinberger 🦞
Peter Steinberger 🦞@steipete·
Been wrangling a lot of time how to deal with the onslaught of PRs, none of the solutions that are out there seem made for our scale. I spun up 50 codex in parallel, let them analyze the PR and generate a JSON report with various signals, comparing with vision, intent (much higher signal than any of the text), risk and various other signals. Then I can ingest all reports into one session and run AI queries/de-dupe/auto-close/merge as needed on it. Same for Issues. P rompt R equests really are just issues with additional metadata. Don't even need a vector db. Was thinking way too complex for a while. There's like 8 PRs for auto-update in the last 2 days alone (still need to ingest 3k PRs, only have 1k so far).
Peter Steinberger 🦞 tweet media
English
425
210
4.1K
569.9K
Manuel Oberhuber
Manuel Oberhuber@manu_oberhuber·
Morgendlicher AT-Alert heute auch für 400.000 Menschen in Vorarlberg.
Manuel Oberhuber tweet media
Deutsch
3
6
53
3.1K