I Tried to Make AI Writing Sound Human by Banning AI Words Through logit_bias
I tried to make AI writing sound more human with logit_bias, an API setting that changes how likely a model is to select specific…
Read postBlog
Technical notes from real projects
Laravel, AI-assisted development, SaaS, SEO, tooling, and the parts that only show up once software is used by real people. Mostly technical, but not trapped in one narrow lane.
73k readers last year
280+ published posts
Laravel, AI, SaaS, SEO
Latest post
Older posts
Continue browsing the archive.
Anthropic Is Hitting a Wall
Anthropic had the developer story every AI lab craved. Claude Code worked. Opus was expensive but worth the splurge. Sonnet was known as the…
Read postClaude Code Quietly Got 5x More Expensive
I started with an easy quota question. Should I get another Claude account or have I been using the ones I have poorly? Then…
Read postClaude Code Is Quietly Fingerprinting China-Linked API Routers
Claude Code has a hidden test for where your requests are going. The trigger is ANTHROPIC_BASE_URL, the environment variable people use when they want…
Read postSmall Teams Will Ship More Software Than They Can Maintain
Using Cursor and Claude, a 5-person engineering team can now build a billing webhook handler, a customer import tool, a Slack alert bot, an…
Read postAI Makes Bad Product Decisions Look Like Finished Software
AI tools make one software failure mode much easier to miss: a bad product decision can now arrive wrapped in a working interface. In…
Read postThe AI Productivity Trap Is More Output
AI makes it dirt cheap to generate code, draft tickets, summarize meetings, and write proposals. But cheaper generation doesn't mean the work actually gets…
Read postIf Software Gets 90 Percent Cheaper, Who Captures the Savings?
Imagine AI can code at a much higher rate. It’s easy to think development is going to get a lot cheaper. But if writing…
Read postThe AI Coding Era Makes Boring Tests More Valuable
Agents can now produce cheap, plausible diffs. A developer can describe a bug, give it to an agent, and get a patch with tests…
Read postOpen Source Maintainers Need a Spam Filter for AI Labor
AI makes bug reports, pull requests, and security disclosures cheap to create, but expensive to review. Still need to reproduce issues, check compatibility, judge…
Read postThe Junior Developer Problem Is Becoming a Senior Developer Problem
AI is fundamentally changing how junior developers learn, but it’s also making senior developers a whole lot less valuable if all they’re doing is…
Read postVibe Code Is Legacy Code Before It Ships
Vibe coding is useful and fast. Nearly a quarter of the YC W25 batch apparently has codebases that are almost entirely AI-generated. This is…
Read postAI Code That Passes Tests Can Still Fail Review
CI green does not mean the patch is mergeable. When a coding agent has produced a change that compiles, passes the target tests, and…
Read post