Links
Things worth reading, saved as I go. 1495 links so far, newest first.
martinfowler.com
Fowler puts numbers on why cleaning up code pays for itself.
fermisense.com
A reinforcement-learning fine-tune of a 9B open model beats every frontier configuration tested on a catalog-review workflow, at 40x less cost than the cheapest.
earendil.com
inference APIs make session state non-portable, and that is lock-in.
refp.se
A shell colon does nothing. Use it anyway - the colon as no-op, placeholder and guard. Short, immediately usable.
vectoral.com
An Inside Look at the Relay Market Powering Token Resellers and Fraud - the grey market reselling model access, and the fraud running through it.
blog.cloudflare.com
BGP ORIGIN attribute manipulation and its impact on the Internet - a rarely examined routing attribute, and how it redirects traffic at internet scale.
magazine.sebastianraschka.com
Controlling Reasoning Effort in LLMs - Raschka on dialing reasoning up and down, and what each notch costs.
github.com
GigaToken: ~1000x faster language model tokenization - a thousandfold speedup on the least glamorous step in the pipeline, with benchmarks in the repo.
"Go Home Copilot, You're Drunk": Understanding Developer Responses to Agent-Generated Code Review Comments
arxiv.org
"Go Home Copilot, You're Drunk": Developer Responses to Agent-Generated Code Review - what developers actually reply to review comments written by an agent. The title is the finding.
huggingface.co
An open-weight multimodal model of 2.8T parameters with a one-million-token context and native vision.
matklad.github.io
Memory Safety's Hardest Problem - matklad on why aliasing and concurrency, not buffer overflows, are the part nobody has solved.
theregister.com
Model Context Protocol prepares to break with its stateful past - MCP moves toward a stateless transport. Protocol design decisions you will be living with.
images.nvidia.com
An open letter arguing that leadership will be decided by how widely AI diffuses rather than by one frontier model, and that open weights are how that happens.
openai.com
OpenAI and Hugging Face address security incident during model evaluation - a swarm of pre-release agents compromised Hugging Face during an eval. Primary account.
anthropic.com
States that Anthropic does not advocate banning open-weight models, and argues instead for chip export controls, distillation limits and mandatory safety testing.
nikolays.github.io
PGSimCity: How PostgreSQL Works - the database rendered as a city you can walk through. Best Postgres explainer in years, and it only works on the site.
astral.sh
Ruff v0.16.0, 413 default rules up from 59 - the Python linter changes what it means by "default". Check your CI before it checks you.
