Components of A Coding Agent
How coding agents use tools, memory, and repo context to make LLMs work better in practice
Latest
AI Daily Brief — 3 April 2026
Gemma 4 benchmarks land: the 31B Dense scores 89.2% on AIME 2026 and ranks top-three globally on Arena AI among open models.
Gemma 4 and what makes an open model succeed
Hint: it's not benchmark scores.
Wan 2.7 video model suite now available on Together AI
A four-model video suite for generation, continuation, reference-driven workflows, and editing, rolling out on Together AI starting with text-to-video.
AI for Systems: Using LLMs to Optimize Database Query Execution
New research shows LLMs can optimize database query execution plans—achieving up to 4.78x speedups by correcting the cardinality estimation errors that statistical heuristics miss.
Claude Code’s Source Leaks, OpenAI Exits Video Generation, Gemini Adds Music Generation, LLMs Learn at Inference
The Batch AI News and Insights: Voice-based AI that you can talk to is improving rapidly, yet most people still don’t appreciate how pervasive voice UIs…
AI Daily Brief — 2 April 2026
Cursor 3 ships an agent-first IDE with eight parallel agents on Composer 2 (built on Kimi K2.5). Google releases Gemma 4 — four open multimodal variants…
The Storyteller’s Gap is a black hole that eats every narrative that never sees the light of day. It’s been there since the beginning of time. Until…
The Storyteller’s Gap is a black hole that eats every narrative that never sees the light of day.It’s been there since the beginning of time. Until…
LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. …
LLM Knowledge BasesSomething I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large…
Oh Memories, Where'd You Go
Two weeks of dogfooding Engram, Weaviate's memory product, in daily Claude Code sessions. This surfaced where a dedicated memory product adds value, and the specific mechanics…
Deepgram speech-to-text and voice models now available natively on Together AI
Production STT and TTS from Deepgram, available on Together AI Dedicated Model Inference for real-time voice agents.
Pinecone Assistant: A Managed Knowledge Layer for Production AI Applications
Pinecone Assistant: A Managed Knowledge Layer for Production AI Applications
Meet the new Cursor
Cursor 3 is a unified workspace for building software with agents.
AI Daily Brief — 1 April 2026
Oracle terminates 30,000 employees to fund a $50B AI-infra pivot. Perplexity makes Computer in Slack public. Amazon Science publishes on LLM-TTS robustness.
Improving quality and robustness in LLM-based text-to-speech systems
Low-rank adaptation, data augmentation, and chain-of-thought reasoning are among the techniques enabling accent-free polyglot outputs, improved expressiveness, and reliable synthesis.
[skill] glmv-stock-analyst (#263)
[skill] glmv-stock-analyst (#263) * add stock analyst Signed-off-by: JaredforReal * rename Signed-off-by: JaredforReal * update Signed-off-by: JaredforReal --------- Signed-off-by: JaredforReal
LWiAI Podcast #238 – GPT 5.4 mini, OpenAI Pivot, Mamba 3, Attention Residuals
OpenAI ships GPT-5.4 mini and nano, faster and more capable but up to 4x pricier, DLSS 5 looks like a real-time generative AI filter for video…
Fine-tuning experiments on CoT controllability
p:has(> img) { margin-bottom: 0; } .content img { margin: 0.75em 0; } Kei Nishimura-Gasparian is an Astra fellow and was the primary contributor to this…
Multimodal Embeddings and RAG: A Practical Guide
Multimodal embeddings allow AI systems to search and reason across text, images, audio, and video in their native formats. This blog covers the key intuitions behind…
Inside the Together AI kernels team
The team behind FlashAttention and ThunderKittens — how Together AI's kernel researchers close the gap between GPU hardware and production AI.
Computer in Slack: From Shared Context to Finished Work
Computer in Slack: From Shared Context to Finished Work
AI Daily Brief — 31 March 2026
Oracle executes the largest workforce reduction in its 49-year history — ~30,000 employees cut via 6 a.m. emails to free $8–10B annual cash flow for AI…
Claude Dispatch and the Power of Interfaces
We often lack the tools for the job, even if the AI is capable enough
The anti-AI coalition continues to maneuver to find arguments to slow down AI progress. If someone has a sincere concern about a specific effect of AI…
The anti-AI coalition continues to maneuver to find arguments to slow down AI progress. If someone has a sincere concern about a specific effect of AI,…