Same spot. Same instant. 0.42 m apart. That happened at my college gate in Bhopal, so I built Crossing Watch: one phone video in, measured near-miss proof out, with Meta SAM 3.1 and Muse Spark. Video: AI-generated with Google Veo. @AIatMeta@MetaforDevs
An 82K-star GitHub repo is built around one painfully obvious idea:
Your coding agent should map the codebase once, not grep it forever.
Graphify turns an entire project into a queryable knowledge graph.
Functions, classes, files, SQL schemas, infrastructure, docs, PDFs, images and videos become connected nodes that an agent can traverse instead of repeatedly opening files and reconstructing the architecture.
So instead of:
→ search for authentication
→ open twelve files
→ follow imports manually
→ lose the trail as the context fills up
The agent can ask:
> What connects authentication to the database?
> Trace the path from UserService to DatabasePool.
> Explain RateLimiter.
> Which concepts does everything flow through?
Graphify returns the relevant subgraph and the path connecting the concepts, not another list of keyword matches.
For source code, this is not RAG:
→ No embeddings
→ No vector database
→ No LLM required
→ Code is parsed locally using tree-sitter
→ Calls, imports and inheritance become graph edges
Every relationship is also marked as EXTRACTED, INFERRED, or AMBIGUOUS, so the agent can distinguish what exists explicitly in the source from what Graphify resolved or guessed.
The cleverest part is what happens next.
Graphify can install hooks or persistent instructions for Claude Code, Codex, Cursor, Gemini CLI, Copilot and 20+ other assistants.
Before the agent starts blindly grepping or reading files one by one, it is nudged to query the existing graph first.
The graph can be committed to Git, automatically rebuilt after commits, shared across the team and exposed through MCP.
Long context windows help agents read more code.
A persistent knowledge graph helps them know where to look.
The next improvement in coding agents may not come from stuffing more files into the prompt.
It may come from making them stop rereading the repository.
Here's the GitHub Repo: https://t.co/4ify3X8urp
Meta solved RAG's biggest bottleneck.
30× faster decoding. Zero accuracy loss.
The problem nobody talks about:
When you feed an LLM 80 retrieved passages, only 5-10 are actually useful.
The rest? Dead weight. But you're computing attention for ALL of them.
The math is brutal:
Traditional RAG with 16K context: → 100+ seconds to first token → 10× throughput drop → Massive memory waste
What REFRAG does:
Compresses context chunks into single embeddings.
Instead of processing 16,384 tokens → Process 1,024 chunk embeddings.
The results:
✓ 30.85× faster time-to-first-token
✓ Zero perplexity loss
✓ 16× context extension (4K → 64K tokens)
✓ 3.75× better than previous SOTA
Why it works:
RAG contexts have sparse attention patterns. Most retrieved passages don't interact. REFRAG exploits this with:
1./ Precomputable embeddings - Cached from retrieval, reused across inferences
2./ RL-based compression - Smart policy decides what to compress
3./ Works anywhere - Unlike previous methods, compresses at any position
Real impact:
• 8 passages at single-passage latency
• Better accuracy with weak retrievers
• Handles unlimited conversation history
• No model architecture changes needed
This changes RAG economics: More context + Lower latency.
(Link to the Meta paper in comments)
♻️ Repost to save someone $$$ and a lot of confusion.
✔️ You can follow @techNmak, for more insights.
Data Structures and Algorithms (C, C++, Java, Python)
https://t.co/zf0ac4newz
Computer Science Fundamentals
https://t.co/zJSdpT4bWB
AI, ML, and Data Science
https://t.co/YnZtD8S5vq
Aptitude Materials
https://t.co/eFzwpNBiTW
More drive links are added on this doc - https://t.co/GrDJcOkLUw
Bookmark it!
Good morning ,
So my target for today is detection of cycle using bfs and dfs in undirected graph
revise cycle detection of linkedlist and few stack problems
I will be just griding on DSA, revise my ML/GenAI concepts, System design & CS Fundamentals.
Daily I will be updating my progress.
If youo guys have any feedback now or even later kindly share it with me.
Thanks.
HEY FAM!,
I just completed my 3rd in in https://t.co/aGnd5O8WS9 and my summer vacations are on being from a core branch & aspiring to in software after failing 4 interviews still was not able to make it throgh.
From today to next 50 days I am starting learn in public for me.
@RailMinIndia@RailMadad@rail_seva@drmjabalpur
Name: Aayush Dubey
PNR:8936571945
Train no: 13380,Coach: B1 ,seat no:71
Journey: LTT to BKRO
I'm in coach no B1, seat no: 71 of Train no: 13380, Ltt Dhanbad express.
There is no water coming in the bathrooms of this coach.
HOLY SH*T… This AI Agent does everything 🤯
Built in n8n :
🔁 Clones viral TikToks
✍️ Rewrites w/ GPT-4o
🎥 Auto creates avatar videos
🎬 Adds captions & edits
📤 Posts to 9 platforms (TikTok, IG, YT, X…)
🔁 Like+RT
✅ Reply “Steal”
🤝 Follow me & I’ll DM you workflow FREE.