Thanh Doan

9.5K posts

Thanh Doan banner
Thanh Doan

Thanh Doan

@capythanh

software engineer

Hồ Chí Minh, Việt Nam Inscrit le Temmuz 2017
547 Abonnements341 Abonnés
Thanh Doan
Thanh Doan@capythanh·
one almost full codex 5h session burns just ~10% of the weekly limit honestly codex is insanely good value tbh
English
0
0
0
11
kache
kache@yacineMTB·
neural networks are amazing
English
9
3
60
2.3K
Thanh Doan
Thanh Doan@capythanh·
@asaio87 it's faster for multiple experiments before ai we could only commit to one solution within a limited time, and it would eventually turn into a dead end or tech debt now i have more time to try things, compare options and iterate
English
0
0
0
14
andrei saioc
andrei saioc@asaio87·
I come to the conclusion that AI doesn’t really make development quicker. Only a tiny fraction of cases at most.
English
41
2
71
3.4K
Thanh Doan
Thanh Doan@capythanh·
@jdorfman luckily it didnt ask how green in the backend was though
English
0
0
0
2
Thanh Doan
Thanh Doan@capythanh·
how i start most days with my agent
Thanh Doan tweet media
English
1
0
3
145
Thanh Doan
Thanh Doan@capythanh·
@JaidCodes a little bit overthinking but i rarely read generated code so it’s ok
English
0
0
0
127
Jaid
Jaid@JaidCodes·
One prompt to GPT-5.4 and the codebase is full of these for some reason.
Jaid tweet media
English
15
0
271
26.9K
Nitin Kalra
Nitin Kalra@nkalra0123·
@daniel_nguyenx this is not true.. i just attached http toolkit on claude code.. and it shows ttl 1 hour.
Nitin Kalra tweet media
English
2
0
4
2.4K
Daniel Nguyen
Daniel Nguyen@daniel_nguyenx·
It looks like Anthropic changed claude code’s cache TTL from 1h to 5m in March, causing significant quota and cost inflation.
Daniel Nguyen tweet mediaDaniel Nguyen tweet mediaDaniel Nguyen tweet media
English
29
55
940
86.9K
Emanuele Di Pietro
Emanuele Di Pietro@emanueledpt·
@capythanh @cjayls it’s up to you to say if it’s better than t3code i like to see it that i added more features but those wouldn’t have been possible without the strong architecture it already has
English
1
0
1
32
Emanuele Di Pietro
Emanuele Di Pietro@emanueledpt·
DP Code v0.0.18 just shipped! 🚀 → cleaner git action picker → better commit / push / PR flow → stronger Claude interrupt handling → cleaner interrupted states → Ctrl+C interrupt in composer on Mac → faster, stabler state syncing → less noisy tool/work logs → cleaner inline tool calls → better right-panel persistence → clearer completion/error toasts → sidebar reopen button when collapsed → project rename + Finder actions → better sidebar search → safer folder picker flow → cleaner browser panel status → better desktop browser controls → cleaner chat header actions → better picker UI → app-wide font scaling → more consistent typography → better diff code fonts → cleaner image-only messages → better queued follow-up restore → clearer git warnings/states → safer sync/pull behavior → polish across the whole app These has been a quite nice 12h of work @theo @jullerino
Emanuele Di Pietro tweet media
Emanuele Di Pietro@emanueledpt

DP Code v0.0.17 just shipped! 🚀 → smoother scrolling in chat → cleaner Plans step-by-step UI → custom UI font, code font, and chat text size → tighter message spacing → cleaner tool/work log summaries → better composer image attachments → improved terminal link detection → terminal close confirmation prompts → less clutter in the sidebar → safer destructive actions → lots of polish across the whole chat experience Enjoy! @theo @jullerino great work as always

English
10
7
60
8.1K
CJS
CJS@cjayls·
@emanueledpt Do you not think calling XYZ better is subjective and also a bit disrespectful whilst tagging the guys in 😂
English
2
0
1
194
Thanh Doan
Thanh Doan@capythanh·
just dug through digital notes and found this almost a year ago: anthropic.com/engineering/cl… didnt think we'd get this far. back then `thinking` was a tool, not something native inside the models, and we were still laying the groundwork for agentic features
Thanh Doan tweet media
English
0
0
1
34
Thanh Doan
Thanh Doan@capythanh·
if you're using their models daily through any fixed subscription, the output can feel inconsistent. sometimes it's great, sometimes it isnt im on their team premium plan (= max 5x), and it's great during off-peak hours but otherwise it can get very slow / output can be worse than haiku then i switch to api usage (through openrouter) - the quality comeback, but the cost is (much) higher x.com/om_patel5/stat…
English
0
0
13
2.5K
BURKOV
BURKOV@burkov·
People sharing Claude Code bills with three to five zeros are scaring me. Why don't they use a monthly subscription?
English
89
7
1.3K
157.6K
∿
@somewheresy·
anthropic is 100% going to get nationalized
English
65
30
1.3K
56K
Theo - t3.gg
Theo - t3.gg@theo·
There's pretty much no reason to hire a mid tier developer now
English
321
79
3.2K
731.4K
HSVSphere
HSVSphere@HSVSphere·
@___4o____ Andrej is so fucking retarded. I've never liked him or found him a good visionary in anything. Why do people still listen to him or follow him? All he posts is slop
English
11
0
252
12.3K
SPEC
SPEC@___4o____·
SPEC tweet media
ZXX
17
24
1K
108.7K