Tweet Disematkan
I migrated chmonitor.dev from @nextjs Nextjs 15 to Tanstack Start @tan_stack in about 37 hours with a long Claude code session, ~ $728, 12 tickets, and 79 PRs created.
github.com/chmonitor/chmo…
English
Duyet
2K posts
Duyet
@_duyet
Data/AI Engineer. Building https://t.co/0fNpexLha2 | https://t.co/O4SBARlAxJ | https://t.co/L4GcjJgKs3
Earth Bergabung Ekim 2011
1.7K Mengikuti697 Pengikut
Meituan released LongCat-2.0, a new 1.6T parameter model with 1M context window
Meituan LongCat@Meituan_LongCat
Introducing LongCat-2.0 🐱 1.6T parameters · MoE with ~48B active · 1M context The full model behind Owl Alpha on @OpenRouter — now available. Built for agentic coding from the ground up: ◆ LongCat Sparse Attention (LSA) — scales efficiently for 1M-context tokens ◆ Zero-Compute Experts — dynamic activation 33B–56B per token, zero wasted compute ◆ MOPD — three specialized expert groups (Agent / Reasoning / Interaction), gate-routed per task How it stacks up: → Terminal-Bench 2.1: 70.8 → SWE-bench Pro: 59.5 (GPT-5.5: 58.6) → SWE-bench Multilingual: 77.3 → FORTE: 73.2 · RWSearch: 78.8 · BrowseComp: 79.9 📖 Tech Blog: longcat.chat/blog/longcat-2… Try it across different scenarios 🧵👇
English
@Cloudflare How can I monitor or set usage limits for Workers AI? I accidentally burn through these without notice, and Billing is also saying $0, which makes no sense
English
Boris sat down with Spotify VP of Engineering Niklas Gustavsson.
Spotify ships 4,500 production deploys a day, and 73% of PRs are now AI-assisted.
English
Spotify ships 4,500 production deploys a day 🤓
ClaudeDevs@ClaudeDevs
Boris sat down with Spotify VP of Engineering Niklas Gustavsson. Spotify ships 4,500 production deploys a day, and 73% of PRs are now AI-assisted.
English
We need to hire 3 engineers in the next 2 weeks and I'm not reading a single resume. (We're paying $150–250k base + equity for ML, AI, and Software)
Instead:
1. Sign up free → workweave(dot)ai
2. See your code output data
3. Post a screenshot
If you're cracked, I'll reach out directly. Takes 2 minutes, and your code does the talking.
English
Duyet me-retweet
Duyet me-retweet
Announcing the hosted X MCP.
Agents now have access to the best real-time information source in the world.
Connect Grok, Cursor, or any MCP-compatible AI tool to the X API without any setup!
Check it out here: docs.x.com/tools/mcp
English
@MarcosHernanz It was slow on dev and using 10GiB+ of memory is really annoying
English
I migrated chmonitor.dev from @nextjs Nextjs 15 to Tanstack Start @tan_stack in about 37 hours with a long Claude code session, ~ $728, 12 tickets, and 79 PRs created.
github.com/chmonitor/chmo…
English
English
@laurentlahmy @nextjs @tan_stack Wall time is the total real-world calendar duration from the first Claude session to the last (~36h 54m).
API time which only counts active AI processing (~20h).
English
English
love to see this when I wake up
Thanks to everyone who is supporting and building
I appreciate you all 🙏
#buildinpublic
English
Prepare a whole new astro blog for the v0.3 release of chmonitor.dev using a simple prompt on my iPhone. I am really much a PM now rather than an engineer 😂
English
In the next version of Claude Code: subagents run in the background by default, so you can keep talking to Claude while your subagents work
If you want your agent to run in the foreground, just tell Claude
English
