Yes, though this is a saying because the last mile/last 10% taking lots of time is not new with vibe coding. So getting that first 90% in an hour is a massive win!
January 23, 2026 at 9:11 PM
Yes, though this is a saying because the last mile/last 10% taking lots of time is not new with vibe coding. So getting that first 90% in an hour is a massive win!
Link to the course is here:
bit.ly/ai-coding-c...
bit.ly/ai-coding-c...
Elite AI Assisted Coding by Eleanor Berger and Isaac Flath on Maven
Make it code like you do. Turn generic AI assistants into coding partners that actually get your style and have the right context.
bit.ly
December 22, 2025 at 1:54 AM
Link to the course is here:
bit.ly/ai-coding-c...
bit.ly/ai-coding-c...
For a detailed write-up, and the full recording of this talk, go here!
elite-ai-assisted-coding.dev/p/mgrep-wit...
elite-ai-assisted-coding.dev/p/mgrep-wit...
mgrep with Founding Engineer Rui Huang
The Problem with grep for AI Agents
elite-ai-assisted-coding.dev
December 10, 2025 at 6:28 PM
For a detailed write-up, and the full recording of this talk, go here!
elite-ai-assisted-coding.dev/p/mgrep-wit...
elite-ai-assisted-coding.dev/p/mgrep-wit...
Unlike traditional RAG that vectorizes large chunks of text, @mixedbreadai 's engine represents every single word as its own vector.
This provides much more granular and accurate results.
Join @aaxsh18 tomorrow for research details on how it works: maven.com/p/0c0eed/mo...
This provides much more granular and accurate results.
Join @aaxsh18 tomorrow for research details on how it works: maven.com/p/0c0eed/mo...
Modern Multi-Vector Code Search
Mixedbread showed in their launch how much faster/better semantic search could make Claude code. Cursor also just announced semantic embedding support, and other agents are soon to follow. I got better quality with 1/2 tokens and almost 2x faster with mixedbread search.
Learn what changed from the leading researchers in the space.
maven.com
December 10, 2025 at 6:28 PM
Unlike traditional RAG that vectorizes large chunks of text, @mixedbreadai 's engine represents every single word as its own vector.
This provides much more granular and accurate results.
Join @aaxsh18 tomorrow for research details on how it works: maven.com/p/0c0eed/mo...
This provides much more granular and accurate results.
Join @aaxsh18 tomorrow for research details on how it works: maven.com/p/0c0eed/mo...
mgrep is also multimodal. It can natively index and search images, diagrams, and PDFs in your repository.
An agent can find relevant information in visual assets that are completely invisible to text-only tools
Very useful for legal, e-commerce and many other domains
And cats
An agent can find relevant information in visual assets that are completely invisible to text-only tools
Very useful for legal, e-commerce and many other domains
And cats
December 10, 2025 at 6:28 PM
mgrep is also multimodal. It can natively index and search images, diagrams, and PDFs in your repository.
An agent can find relevant information in visual assets that are completely invisible to text-only tools
Very useful for legal, e-commerce and many other domains
And cats
An agent can find relevant information in visual assets that are completely invisible to text-only tools
Very useful for legal, e-commerce and many other domains
And cats
The results from their internal tests with Claude are significant. Using mgrep led to:
🤌 53% fewer tokens used
🚀 48% faster response
💯 3.2x better quality
By getting the right context immediately, agents stay on track. I saw similar results.
elite-ai-assisted-coding.dev/p/boosting-...
🤌 53% fewer tokens used
🚀 48% faster response
💯 3.2x better quality
By getting the right context immediately, agents stay on track. I saw similar results.
elite-ai-assisted-coding.dev/p/boosting-...
Boosting Claude: Faster, Clearer Code Analysis with MGrep
I ran an experiment to see how a powerful search tool could improve an LLM’s ability to understand a codebase.
elite-ai-assisted-coding.dev
December 10, 2025 at 6:28 PM
The results from their internal tests with Claude are significant. Using mgrep led to:
🤌 53% fewer tokens used
🚀 48% faster response
💯 3.2x better quality
By getting the right context immediately, agents stay on track. I saw similar results.
elite-ai-assisted-coding.dev/p/boosting-...
🤌 53% fewer tokens used
🚀 48% faster response
💯 3.2x better quality
By getting the right context immediately, agents stay on track. I saw similar results.
elite-ai-assisted-coding.dev/p/boosting-...
Agents use mgrep for broad, semantic exploration and grep for precise symbol lookups
Instead of grep commands guessing at keywords, an agent makes a semantic query
mgrep "how is auth implemented?"
It then uses grep for precise function/class name searches.
No guessing 😁
Instead of grep commands guessing at keywords, an agent makes a semantic query
mgrep "how is auth implemented?"
It then uses grep for precise function/class name searches.
No guessing 😁
December 10, 2025 at 6:28 PM
Agents use mgrep for broad, semantic exploration and grep for precise symbol lookups
Instead of grep commands guessing at keywords, an agent makes a semantic query
mgrep "how is auth implemented?"
It then uses grep for precise function/class name searches.
No guessing 😁
Instead of grep commands guessing at keywords, an agent makes a semantic query
mgrep "how is auth implemented?"
It then uses grep for precise function/class name searches.
No guessing 😁
mgrep is a command-line tool that brings semantic search to your codebase, letting agents search by intent, not just keywords.
It's much faster than grep alone, and works much better than traditional semantic search.
It's much faster than grep alone, and works much better than traditional semantic search.
December 10, 2025 at 6:28 PM
mgrep is a command-line tool that brings semantic search to your codebase, letting agents search by intent, not just keywords.
It's much faster than grep alone, and works much better than traditional semantic search.
It's much faster than grep alone, and works much better than traditional semantic search.
For all the code, charts, and a deeper dive into the mechanics, check out the full blog post
isaacflath.com/blog/2025-1...
isaacflath.com/blog/2025-1...
Quantization Fundamentals for Multi-Vector Retrieval - Blog
An thorough and complete introduction to Quantization for Multi-Vector Search Architectures
isaacflath.com
December 1, 2025 at 7:13 PM
For all the code, charts, and a deeper dive into the mechanics, check out the full blog post
isaacflath.com/blog/2025-1...
isaacflath.com/blog/2025-1...
This two-stage compression (PQ + residual quant) means you get token-level understanding in fraction of the space
The Mixedbread team has 2 free eng and research talks soon for more info on research and how to use
Talk 1: maven.com/p/9c51af/th...
Talk 2: maven.com/p/0c0eed/mo...
The Mixedbread team has 2 free eng and research talks soon for more info on research and how to use
Talk 1: maven.com/p/9c51af/th...
Talk 2: maven.com/p/0c0eed/mo...
Modern Multi-Vector Code Search
Mixedbread showed in their launch how much faster/better semantic search could make Claude code. Cursor also just announced semantic embedding support, and other agents are soon to follow. I got better quality with 1/2 tokens and almost 2x faster with mixedbread search.
Learn what changed from the leading researchers in the space.
maven.com
December 1, 2025 at 7:13 PM
This two-stage compression (PQ + residual quant) means you get token-level understanding in fraction of the space
The Mixedbread team has 2 free eng and research talks soon for more info on research and how to use
Talk 1: maven.com/p/9c51af/th...
Talk 2: maven.com/p/0c0eed/mo...
The Mixedbread team has 2 free eng and research talks soon for more info on research and how to use
Talk 1: maven.com/p/9c51af/th...
Talk 2: maven.com/p/0c0eed/mo...
Step 5: Extreme Quantization
ColBERT goes one step further. After PQ, it calculates the "residual" error (the small difference between the original and the approximation). Then, it quantizes that error, often down to just 1 or 2 bits per value!
ColBERT goes one step further. After PQ, it calculates the "residual" error (the small difference between the original and the approximation). Then, it quantizes that error, often down to just 1 or 2 bits per value!
December 1, 2025 at 7:13 PM
Step 5: Extreme Quantization
ColBERT goes one step further. After PQ, it calculates the "residual" error (the small difference between the original and the approximation). Then, it quantizes that error, often down to just 1 or 2 bits per value!
ColBERT goes one step further. After PQ, it calculates the "residual" error (the small difference between the original and the approximation). Then, it quantizes that error, often down to just 1 or 2 bits per value!
Step 3: Store which cluster/centroid each piece belongs to
Step 4: reconstruct by looking up centroids and combining
Step 4: reconstruct by looking up centroids and combining
December 1, 2025 at 7:13 PM
Step 3: Store which cluster/centroid each piece belongs to
Step 4: reconstruct by looking up centroids and combining
Step 4: reconstruct by looking up centroids and combining
Step 2: Cluster each collection of sub-vectors separately to find the centroids
December 1, 2025 at 7:13 PM
Step 2: Cluster each collection of sub-vectors separately to find the centroids
Step 1: Split each embedding in half (make sub-vectors).
December 1, 2025 at 7:13 PM
Step 1: Split each embedding in half (make sub-vectors).
However, AI embeddings aren't single numbers; they're vectors (long lists of numbers). This is where Product Quantization (PQ), comes in. It's specifically designed to compress these vectors.
It "refactors" similar embeddings to reduce duplication by using k-means clustering. Let's break it down.
It "refactors" similar embeddings to reduce duplication by using k-means clustering. Let's break it down.
December 1, 2025 at 7:13 PM
However, AI embeddings aren't single numbers; they're vectors (long lists of numbers). This is where Product Quantization (PQ), comes in. It's specifically designed to compress these vectors.
It "refactors" similar embeddings to reduce duplication by using k-means clustering. Let's break it down.
It "refactors" similar embeddings to reduce duplication by using k-means clustering. Let's break it down.