Rees

203 posts

Rees banner
Rees

Rees

@ReesMorris

London, UK Katılım Eylül 2012
70 Takip Edilen142 Takipçiler
Daniel 🦔
Daniel 🦔@DanielW_Kiwi·
I'm not big on LLM skills but this is amazing.
Daniel 🦔 tweet media
English
34
22
942
85.1K
Rees
Rees@ReesMorris·
@jacobmparis but does it also work with promotional discount codes for sushi?
Rees tweet media
English
0
0
1
158
jacob paris ▲
jacob paris ▲@jacobmparis·
cursor now lets you autofill your prompt with 2FA codes
jacob paris ▲ tweet media
English
5
1
77
3.9K
Rees
Rees@ReesMorris·
@Leulaya @CastAsHuman honestly I don't think anyone does context compaction better than openai
English
0
0
0
35
Leul
Leul@Leulaya·
@CastAsHuman because larger contexts eats up more compute which means reduced limits the compaction is truly a thing of beauty no need for 1M
English
2
0
2
4.7K
Sotiris Kaniras
Sotiris Kaniras@CastAsHuman·
If Sol's context window is 1.05M tokens, why in the ChatGPT app we only get 258K?
Sotiris Kaniras tweet media
English
93
9
668
121.8K
Rees
Rees@ReesMorris·
@winglee this looks great! does it act as just a GUI or harness too? like would it cause different behaviour than the official apps?
English
1
0
1
4.1K
wing
wing@winglee·
no more electron — this is a native application using rust + gpui that lets you manage your claude and codex sessions across devices in a single view
English
160
83
2.6K
170.1K
Rees
Rees@ReesMorris·
@kdaigle @github not sure I could commit myself to a whole stack of them .. I'll see myself out
English
0
0
9
453
Rees
Rees@ReesMorris·
@github is this why the hamburger menu is now pancakes
English
2
1
112
19K
Rees
Rees@ReesMorris·
@AbdallahD3v this was my favourite update message
Rees tweet media
English
1
0
1
14
Abood
Abood@AbdallahD3v·
Time to take a nap
Abood tweet media
English
2
0
6
436
pilcrow
pilcrow@pilcrowonpaper·
I have decided to move on from my past projects I am ending my work on Lucia I am deprecating Arctic I am deprecating (most) NPM packages published under Oslo pilcrowonpaper.com/blog/18
English
25
14
504
54.5K
Yousuf K.
Yousuf K.@YousufKalim·
Did Codex make the weekly limit a new 5 hr limit? Frustrating
English
48
10
572
61.3K
Rees
Rees@ReesMorris·
too dangerous for myself
Rees tweet media
English
0
0
0
20
Rees
Rees@ReesMorris·
YouTube's layout feels more and more compact every day
English
0
0
0
10
Rees
Rees@ReesMorris·
@uwukko there are definitely more wheels than doors
English
0
0
0
41
wukko
wukko@uwukko·
do people even read what they reply to on twitter anymore
English
63
6
492
14.1K
Kal Grinberg
Kal Grinberg@KalGrinberg·
if your portfolio site has a chat box, you've lost the plot
English
9
0
39
4.2K
Rees
Rees@ReesMorris·
Does Claude Code fast mode affect sub agents?
English
0
0
0
50
Anthony Kim
Anthony Kim@yellow_fellowz·
Our @awscloud bill is $100 Billion What happened here?
Anthony Kim tweet media
English
15
0
59
6K
Rees
Rees@ReesMorris·
@Jakubantalik love these! there is a small bug where once the "Get Pro" screen shows for CSS/React then even non-pro transitions will show that same screen too until you refresh the page
English
1
0
1
632
Jakub Antalik
Jakub Antalik@Jakubantalik·
Added 12 new transitions to transitions.dev 33 total You can copy as CSS or React code or use as a skill for Claude, Cursor or Codex or use with Refine tool npx skills add jakubantalik/transitions.dev
English
28
94
1.7K
71.5K
Rees
Rees@ReesMorris·
@bruvimtired is this the equivalent of it deleting the tests because they failed
English
0
0
0
41
ahmet
ahmet@bruvimtired·
so opus 4.8 just deleted comments on a pr 🤣🤣🤣🤣 ive never seen that before. now wtf do i do?!?!
English
9
0
36
2.2K
Ivan
Ivan@ivanvitiaev·
@vladikk You should seriously consider switching to local computing resources. At this point, it's already cheaper than the cost of API tokens.
English
2
0
1
637
Vlad Khononov
Vlad Khononov@vladikk·
When Claude writes code, it signs the commit: Co-Authored-By: Claude. I'm paying for the model, and it still takes a credit line. Okay, fine. But co-authorship is a claim about contribution. And that logic should work both ways. So what about all those people who involuntarily "contributed" the training data? You know, half the internet. Don't they deserve co-authorship on the models?
Vlad Khononov tweet media
English
141
83
2.3K
144.2K