Thanh Doan

@JaidCodes a little bit overthinking but i rarely read generated code so it’s ok

One prompt to GPT-5.4 and the codebase is full of these for some reason.

@nkalra0123 @daniel_nguyenx try disabling the telemetry in your settings.json if you do it it the TTL will reduce from 1h -> 5min: github.com/anthropics/cla…

@daniel_nguyenx this is not true.. i just attached http toolkit on claude code.. and it shows ttl 1 hour.

It looks like Anthropic changed claude code’s cache TTL from 1h to 5m in March, causing significant quota and cost inflation.

@tomosman they're building a half of yc's startups

Anthropic are building Replit.

@emanueledpt @cjayls that’s a beauty of open source, just dropped you one star! great work

@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

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

@cjayls @emanueledpt not better than the original, but probably better than its own previous version

@emanueledpt Do you not think calling XYZ better is subjective and also a bit disrespectful whilst tagging the guys in 😂

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

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…

@capythanh What does that mean?

People sharing Claude Code bills with three to five zeros are scaring me. Why don't they use a monthly subscription?

how i start most days with my agent

We're delighted to announce that MiniMax M2.7 is now officially open source. With SOTA performance in SWE-Pro (56.22%) and Terminal Bench 2 (57.0%). You can find it on Hugging Face now. Enjoy!🤗 huggingface：huggingface.co/MiniMaxAI/Mini… Blog: minimax.io/news/minimax-m… MiniMax API: platform.minimax.io

@somewheresy by whom?

anthropic is 100% going to get nationalized

@oliverhenry coporates and gov

Who uses word???? Serious question. Since Google docs came out that is all I used, who is paying to write word documents?

@theo define mid tier developer

There's pretty much no reason to hire a mid tier developer now

@HSVSphere @___4o____ he could be performative but his contents are great tbh

@___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

@chelsssseeeea you should learn about risk management, or at least risk:reward ratio

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.

@thdxr @OfficialLoganK pls make gemini great again 🙏

it's kinda crazy to think the world would be in a better place if a faceless corporation like google was leading ai

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

@arena how did you benchmark multimodal models vs text-only models? really curious

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.

they built cc, codex, cursor,... to have more works. not make their lives easier