小柠陪你学懂车

选一台开着顺手的车，每天通勤都是享受｜选车思路 @mothio1201

[小柠陪你学懂车 @afiq_line11]

@Yarilo7brigada long term knee care matters more to every chunk this good

[小柠陪你学懂车 @afiq_line11]

@Yarilo7brigada landed the low kick today short and changed tonight rather

[小柠陪你学懂车 @afiq_line11]

@Yarilo7brigada long term knee care matters more to every chunk this good

[小柠陪你学懂车 @afiq_line11]

@googlechrome teep inside then trade a right and janky knee today

[luna 💜 @plklunaa]

Vient me parler ici👇
https://t.co/Bg4LpgR4q3

[Gresham @Greshamtrade]

THIS IS F*CKING DANGEROUS

ex-SpaceXAI employee leaked a second-brain template for Grok Bot. 99% of Grok Bot users don’t know this setup exists

your documents, voice notes, research, and past decisions become connected memory. ask why you rejected an idea six months ago, and it retrieves the reasoning and sources. less repeated work, fewer wasted tokens, and answers grounded in what you already know

20 GitHub repos to recreate the setup:

01 Basic Memory → keep knowledge in readable Markdown files that an AI can search and update through MCP. your notes stay accessible outside the chat
https://t.co/CSUXMn7mf6

02 Cognee → turn documents and conversations into persistent knowledge graphs, connecting decisions to the discussions and evidence behind them
https://t.co/SAHO7NltPD

03 MemOS → add a memory layer that stores, retrieves, and manages information across tasks, with feedback for correcting what the system remembers
https://t.co/Z1v04sIuaK

04 Mem0 → retain useful preferences, facts, and interaction history so connected workflows can retrieve relevant memories in later sessions
https://t.co/iGhtPCz7jS

05 Graphiti → track relationships and how facts change over time, preserving the difference between what was true before and what is true now
https://t.co/G6lBZWAN10

06 LightRAG → combine graph relationships and vector retrieval to find connected information across documents, with support for incremental updates
https://t.co/hfyhBcbr7j

07 PageIndex → build a navigable tree of a long document so retrieval can find relevant sections with traceable page references
https://t.co/ErswLbyfZO

08 Karakeep → collect links, notes, images, and PDFs in a searchable library, with optional automatic tagging and summarization
https://t.co/EPsZIrI4ej

09 Linkwarden → preserve useful web pages as archived copies, keeping the source available even when the original link disappears
https://t.co/sFV98AM6KP

10 Paperless-ngx → turn scanned documents and paperwork into an organized, searchable archive that can feed your knowledge workflow
https://t.co/Q4gDUCWyV9

11 Unstructured → break documents into structured elements so your ingestion pipeline can separate useful content before indexing it
https://t.co/OuGpBRb2qV

12 MinerU → extract readable content from complex PDFs, scans, tables, and office documents, with references back to document locations
https://t.co/6G71QYPo70

13 whisper.cpp → transcribe recordings locally so spoken ideas and meeting discussions can become searchable text in your archive
https://t.co/Iaw2wMj05D

14 pgvector → store embeddings alongside your structured data in Postgres, then retrieve related passages with metadata and filters
https://t.co/4beLJw96qZ

15 sqlite-vec → add vector search to a lightweight SQLite database for a local memory store without a separate database server
https://t.co/uCivMCTJW2

16 Meilisearch → combine keyword and semantic search so your archive can find both an exact project name and a related idea
https://t.co/ibsGumnESl

17 Neo4j → store explicit connections between people, projects, sources, and decisions, then query how those pieces relate
https://t.co/wa1ZLUqpHX

18 watchfiles → detect changed files and trigger updates in your indexing scripts, keeping the archive current without repeatedly processing everything
https://t.co/0QUy4UgkDS

19 Syncthing → synchronize your knowledge files between computers so the notes you capture and the files your workflow reads stay aligned
https://t.co/JP8wodP5Ph

20 restic → create encrypted backups and recover previous snapshots when a bad edit or accidental deletion damages your knowledge collection
https://t.co/Zf9ZxB6lGb

start with one project and one memory backend. connect it to Grok Bot through supported MCP tools, APIs, or local scripts, then add the capture and retrieval pieces you need

test it with a question you already know the answer to: “why did we reject this approach?” a useful second brain should bring back the original reasoning, its evidence, and any later decision that replaced it

that’s when an old conversation becomes something you can build on months later

save this. the work you’ve already done should keep paying you back

the article below shows how to reuse that knowledge without loading your entire archive into every Grok Bot conversation ↓

[Bambu Lab @BambulabGlobal]

Bambu Lab R1, the CO₂ laser built with the same motion control as our printers.

Every cut lands where it should.

The specs you've been asked about:
• 55W CO₂ Laser - cuts up to 20mm single-pass cutting
• 600 × 300 mm bed, 3m throughput with conveyor
• 1000 mm/s max speed without losing detail
• Auto laser alignment, first for a CO₂ laser cutter
• Cameras, lasers and encoders work as one, within 0.2mm positioning accuracy

Big job. Light work.

Explore R1 https://t.co/1S13tO2TWj

[小柠陪你学懂车 @afiq_line11]

@beatrix_trisha 这个说到点子上了，高转后渗油我这两天也留意着。你要是有空一起看看，多个人多点眼力。

[小柠陪你学懂车 @afiq_line11]

舟山这台二手阿普利亚街车像成熟舞者，车身状态不错，发动机也没显疲，油门依然很醒。宁波、杭州、绍兴想看更多，完整试驾在主页。

[小柠陪你学懂车 @afiq_line11]

@ECARPENTER64 杭州过来不远，坐姿这事照片真说不准，上车站一下最直接。你大概多高？我好提前说下你的脚够不够地。

[小柠陪你学懂车 @afiq_line11]

@blisssssssss 对，这座姿市区代步确实费腰，短途代步还行，跑远点得自己适应。你是习惯坐高一点的还是偏低的？

[小柠陪你学懂车 @afiq_line11]

@conradbeliconi 哈哈我自己拍的时候也怕看走眼，所以特意多拍了几处细节。你要来看实车的话我可以陪你摸摸，瞎聊几句也好。

[小柠陪你学懂车 @afiq_line11]

@MyndieV 跑了大概两万三，到我这是第二手，前车主保养记录还留着。

[小柠陪你学懂车 @afiq_line11]

@fingersman 哈哈倒三次车架还硬，这评价太到位了，你当时骑的是哪一年的？

[小柠陪你学懂车 @afiq_line11]

@marvinosas 前刹车片我也注意到了，还剩一半多点，不是什么大问题，但可以顺手换掉。

[小柠陪你学懂车 @afiq_line11]

@YaBoyHasz 冷启动确实能说明不少问题，我这两天找个早上录一段给你听，你主要听怠速还是给油那一下？

[小柠陪你学懂车 @afiq_line11]

@disgustedheart 周末可以约，宁波这边我一般周六下午方便，你想约哪天？

[Skunzu @skunzu]

THIS IS A REAL F*CKING GOLDMINE

Anthropic just shared one of the best tricks for Claude Code

The idea: run Sonnet 5.5, Haiku 5.5 and Opus 5.5 together, each one doing only the job it's best at

Better output and way fewer tokens: every task lands on the right model

You just start Claude Code like this:

CLAUDE_CODE_SUBAGENT_MODEL=haiku claude --model sonnet

here's how it splits:

→ Sonnet 5.5 runs the main session, writes the code and applies the fixes
→ Haiku 5.5 swarms the repo in parallel: search, grep, docs and test audits, each in its own context
→ Opus 5.5 sits in its own architect subagent for the big decisions and signs off on the diff
→ you stop burning Opus on routine work and stop flooding the main session with raw logs

Opus only steps in at three moments:

→ before a plan locks
→ when the same error hits twice
→ before calling it done (signing off on the git diff)

Sonnet builds, Haiku swarms, Opus reviews

JEV engineering is the same move one layer down: the forks that need no thinker (which agent, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split

the full tree
> Sonnet 5.5 runs the main session and writes the code
> search maps the repo on Haiku 5.5 (read-only)
> grep finds call sites on Haiku 5.5 (own context, only the summary comes back)
> audit checks diffs on Haiku 5.5 in a temporary worktree (isolation: worktree)
> architect runs on Opus 5.5 (its model: opus beats the haiku default), reviews the final diff
> JEV routes micro-forks in milliseconds

paste the tree and this prompt into Claude Code ↓

"Reconfigure my Claude Code setup around this tree:
1. Run the main session on Sonnet 5.5 and set CLAUDE_CODE_SUBAGENT_MODEL=haiku
2. Create four subagents in .claude/agents/: search (maps the repo), grep (finds call sites) and audit (checks diffs) on Haiku 5.5, plus architect with model: opus
3. Set isolation: worktree on audit so it never touches my working branch
4. Add one rule to CLAUDE.md: send every repo search and test run to a Haiku 5.5 subagent, and call architect before a plan locks, after the same error twice and before done
5. Route fast deterministic forks (tool choice, path selection, retries) through JEV
Show me every change as a diff first. No edits until I say go"

↳ https://t.co/neE4NaJaVj

save it, you'll need it

[小柠陪你学懂车 @afiq_line11]

@xmyttle lapas class well pergi likas site the family near ini but who the plan laju ok from

[小柠陪你学懂车 @afiq_line11]

@Lunnarsx_ when the lokal stadium roars it feels different on tv