Latest

Every published item, in order · 4310 items
Oct 21
How-toBuildersSelected00:30
Shopify details continual learning loop with PyTorch at PyTorchCon 2026

The pipeline turns production failures into labelled training data automatically, which explains how a small specialist model can beat a frontier model on a narrow task. Teams running LLM features in production can adapt this judge-critic-replay pattern to their own evaluation loops. It pairs with the PyTorch and vLLM stacks many ASEAN engineering teams already deploy for serving.

Official accountPyTorch@PyTorchSource
Oct 20
Tomorrow 08:00, the daily lands in your inboxTelegram channel or email. Same screening as this page, no ads.
How-toBuildersSelected12:57
vLLM KV Cache Offloading Poster at PyTorch Conference

The routing layer is the interesting part: simply offloading KV cache to CPU or storage is not enough, since a request must land on the node whose cache already holds its blocks. Engineers running multi-node inference can use this to decide between cheaper CPU offload and shared-storage tiers. The poster session is open to PyTorch Conference attendees on 20-21 October in San Jose.

Official accountPyTorch@PyTorchSource
How-toBuildersSelected03:52
LangChain's Harrison Chase Shares Agent Building Lessons on Twenty Minute VC

The model-plus-context-plus-harness decomposition gives teams a concrete decision framework for where to invest effort first, rather than defaulting to fine-tuning. Practitioners building or budgeting for agents get a tested sequence for cutting spend and a candid view that memory distillation is still the hardest unsolved piece. The claim that horizontal agents will call vertical agents also hints at where agent infrastructure investment is heading.

Official accountLangChain@LangChainAISource
How-toBuildersSelected03:52
LangChain: run agent evals through the same graph

Testing evals against the production agent graph removes the gap between what benchmarks measure and what users actually experience. Builders of conversational or multi-turn agents can reuse this pattern: simulate personas through the same entry point as live traffic, then trust the same scores in CI. It pairs well with LangSmith-style tracing workflows for regressions.

Official accountLangChain@LangChainAISource
How-toBuildersSelected00:25
Speculators v0.9.0 Adds Faster Training and FP8 Backend

Faster training and halved storage lower the cost of building custom speculative decoding models, which speed up inference without changing model weights. Teams running vLLM can now train draft models on their own workloads and deploy them in the same stack. The FP8 backend matters most for those serving large models on memory-constrained GPUs.

Official accountvLLM@vllm_projectSource
Oct 19
How-toBuildersMulti-sourceSelected23:28
Grok Bot workflows for coding, SEO and X material collection

The practical detail is the multi-model quota strategy: assigning planning, coding and review to different models spreads usage across Cursor's three separate billing tiers instead of burning one plan. Solo developers and small teams running several products can copy this bot-per-project setup directly. Verification relies on full E2E and smoke tests rather than human code review, which lowers the overhead for shipping small weekly updates.

Event
Viking@vikingmuteSource

Only the latest 2000 items are listed; for older ones see the daily archive