A community file distilling Karpathy's coding-agent observations hit 60K stars on four principles. I opened my own CLAUDE.md to compare. I'd independently written two of them. The two I hadn't are the ones that matter most.
Read more →
Boris Cherny, who built Claude Code, says engineering, product, design and data science are melting into one role, and what's left is five archetypes: Prototyper, Builder, Sweeper, Grower, Maintainer. I read the list and realised I'm all five, because building solo with agents leaves no one to hand a phase to. The framework is thirty years old. What's new is that it just became the primary axis instead of the secondary one.
Read more →
OpenAI shipped a Mythos-class frontier model on June 26, then handed the guest list to the US government. Twenty approved customers, classified criteria, no published rules - a de facto license, applied to the labs that cooperate and useless against the open weights shipping freely out of China.
Read more →
Karpathy's four CLAUDE.md rules went viral: ask don't assume, simplest solution first, don't touch unrelated code, flag uncertainty. The most-upvoted reply added a fifth that quietly reverses the whole point: don't hesitate to suggest a better way. The four rules tame a model that wanders. The fifth one trusts a model that thinks. Which set you want depends entirely on which model you're running, and most people copy the file without checking.
Read more →
Anthropic studied 400,000 Claude Code sessions and found the best users weren't the best programmers. Managers, lawyers, and salespeople land within a few points of software engineers, and management scored highest of all. The skill that transfers isn't syntax. It's knowing what the right thing to build is, which is the one thing a bootcamp never taught.
Read more →
For 19 days the best model on earth was illegal to show a foreign national, including Anthropic's own staff. Then Fable 5 came back with a new classifier, a silent reroute to Opus 4.8, and no proof the weights were the same. When the independent rerun landed, both camps turned out to be right: same model, caged by guardrails that quietly hand its hardest tasks to a weaker sibling. Access used to be gated by price. Now it's gated by permission.
Read more →
One LLM on the long tail is a coin flip. How I designed a product-enrichment pipeline around consensus voting, abstention, and content-hashed freshness gates.
Read more →
Sonnet 5 lands within a few points of Opus 4.8 on most work and looks 2.5x cheaper, but that discount inverts on real tasks: at high effort Sonnet is so token-hungry it often bills more per task than Opus. The usage squeeze, meanwhile, is self-inflicted: agentic work now fans out dozens of subagents across parallel workstreams. Opus 4.8 became the expensive middle, though its real problem was never the price. It's the position.
Read more →
There's a myth, loudest from senior engineers and architects, that before AI the codebase was a cathedral and now it's slop. It was never a cathedral. 'Technical debt' was coined in 1992, the world runs on 220 billion lines of COBOL, and the thing that actually mattered was never how the code looked. It was whether you could prove it works.
Read more →
WebFetch dies at the first Cloudflare challenge. I built a research agent that escalates through an unlocker ladder, cites its sources, and refuses to burn money on auth walls.
Read more →
Headroom went from zero to 40k GitHub stars by attacking agentic token bloat. The durable idea isn't the tool - it's treating context compression as a retrieval problem.
Read more →
Rewards built on likes are unverifiable and gameable. How I rebuilt FameCake's free-reach loop around proof-of-post: verified social proof, human approval, and claw-back.
Read more →
In one week of June 2026, the bash-loop hack got a respectable name - loop engineering - and a C-suite endorsement. Then Uber and Microsoft showed what the invoice looks like.
Read more →
The open model that engages with authorized security work also has a default route that ships your client's data through Chinese infrastructure. Here's how to run GLM-5.2 from the cloud for real engagements - minimal false refusals, data kept in the US, no Beijing tax.
Read more →
Eleven days ago I flagged GLM-5.2's launch claims as unverified. The receipts arrived: independent benchmarks above Fable 5, a security eval beating Claude Code at a sixth of the cost, a 2-bit quant running on a Mac Studio, and a model trained without a single NVIDIA chip.
Read more →Showing 15 of 210 posts
View All Posts →
