Thanh Doan

9.5K posts

Thanh Doan banner
Thanh Doan

Thanh Doan

@capythanh

software engineer

Hồ Chí Minh, Việt Nam Joined Temmuz 2017
547 Following341 Followers
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
27
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
56
7.7K
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
191
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
22
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
157.3K
Thanh Doan
Thanh Doan@capythanh·
how i start most days with my agent
Thanh Doan tweet media
English
1
0
3
135
∿
@somewheresy·
anthropic is 100% going to get nationalized
English
65
30
1.3K
55.9K
Theo - t3.gg
Theo - t3.gg@theo·
There's pretty much no reason to hire a mid tier developer now
English
319
78
3.2K
718.3K
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
251
12.3K
SPEC
SPEC@___4o____·
SPEC tweet media
ZXX
17
24
1K
108.6K
Thanh Doan
Thanh Doan@capythanh·
@chelsssseeeea you should learn about risk management, or at least risk:reward ratio
English
0
0
1
5.4K
chl$
chl$@chelsssseeeea·
Maybe I’m dumb but why don’t people just put money in prediction markets on events that are 90% certain or higher? Seems like a very simple way to make money with very low risk.
English
372
16
3.8K
1.5M
dax
dax@thdxr·
it's kinda crazy to think the world would be in a better place if a faceless corporation like google was leading ai
English
73
18
943
69.2K
Thanh Doan
Thanh Doan@capythanh·
many people feel good about ai now write tests for them, but when those tests failed in ci, they don't read why - just ask ai to fix them the slop cycle nevers end
English
0
0
1
44
Thanh Doan
Thanh Doan@capythanh·
@arena how did you benchmark multimodal models vs text-only models? really curious
English
0
0
1
371
Arena.ai
Arena.ai@arena·
With GLM-5.1, Z.ai maintains the #1 open model rank in Code Arena and is now within ~20 points of the top overall while outperforming Claude Sonnet 4.6, Opus 4.5, GPT-5.4 High, and Gemini-3.1 Pro. Open models are now competitive at the frontier.
Arena.ai tweet media
Arena.ai@arena

GLM-5.1 by @Zai_org is now #3 in Code Arena - surpassing Gemini 3.1 and GPT-5.4, and now on par with Claude Sonnet 4.6. The first frontier level open model to break into the top 3. It’s a major +90 point jump over GLM-5, and +100 over Kimi K2.5 Thinking. Huge congrats to @Zai_org on pushing open model progress forward 🚀

English
40
98
1.1K
166.1K