Georgi Kalchev - DEV Community

Georgi Kalchev

Oct 22

A model flags a wrong total but skips the sum

#testing #modelcomparison #json

1 min read

Georgi Kalchev

Oct 22

A model that summarizes a table adds its own sums

#testing #modelcomparison #summarization #hallucination

1 min read

Georgi Kalchev

Oct 21

Cloudflare Web Analytics: link previews are not readers

#cloudflare #testing #modelcomparison #statistics

1 min read

Georgi Kalchev

Oct 21

Does cookieless analytics need consent in the EU?

#cloudflare #testing #modelcomparison

1 min read

Georgi Kalchev

Oct 21

Three weeks on, 80 of 82 x402 sites still block AI training crawlers

#ai #seo #webdev #cloudflare

1

1 min read

Georgi Kalchev

Oct 20

When to /clear or /compact a Claude Code session

#claudecode #testing #modelcomparison

1

1 min read

Georgi Kalchev

Oct 20

A month later, 98 of 104 AI-built sites look the same to a crawler

#seo #ai #webdev #javascript

1 min read

Georgi Kalchev

Oct 20

HTTP 402 and x402: three places a payment breaks

#x402 #bazaar #debugging #cloudflare

1 min read

Georgi Kalchev

Oct 20

Many AI-built sites have a finished link preview and an empty page

#seo #ai #webdev #javascript

1 min read

Georgi Kalchev

Oct 19

How the x402 protocol works, with one real payment

#x402 #debugging #json

1 min read

Georgi Kalchev

Oct 19

Half of x402 services have no front page an AI crawler can read

#ai #seo #webdev

1 min read

Georgi Kalchev

Oct 19

Why you should not install unvetted AI agent skills

#skillmd #claudecode #mcp #walletsafety

1 min read

Georgi Kalchev

Oct 19

OpenNext R2 cache: old builds pile up, 41 GB cleaned

#cloudflare #opennext #testing #modelcomparison

1 min read

Georgi Kalchev

Oct 19

Five reasons AI crawlers cannot read your site, and how to fix each

#seo #ai #webdev #tutorial

1 min read

Georgi Kalchev

Oct 18

Gemini fallback chains: when an empty 200 should move on

#testing #debugging #json #weakmodels

1 min read

Georgi Kalchev

Oct 18

One in eleven x402 sites blocks AI training crawlers

#ai #seo #webdev #cloudflare

1 min read

Georgi Kalchev

Oct 18

What Claude Code memory really loads at start

#claudecode #testing #debugging #bulgarian

1 min read

Georgi Kalchev

Oct 17

We fetched 104 AI-built sites the way GPTBot does. 61% were empty.

#seo #ai #javascript #webdev

1

1 min read

Georgi Kalchev

Oct 17

XML and config files: the AI never says stop

#testing #modelcomparison #weakmodels

1

1 min read

Georgi Kalchev

Oct 17

CSV to JSON with AI: where data quietly goes missing

#testing #modelcomparison #weakmodels

1 min read

Georgi Kalchev

Oct 16

Markdown table repair: the AI invents a column instead

#testing #modelcomparison #weakmodels

1 min read

Georgi Kalchev

Oct 16

Mojibake, CSV and JSONL repair: code against an AI model

#testing #modelcomparison #weakmodels

1 min read

Georgi Kalchev

Oct 15

AI pull request descriptions: claims the diff never made

#testing #modelcomparison #hallucination #weakmodels

1 min read

Georgi Kalchev

Oct 15

Cloudflare cron day numbers: what Claude gets wrong

#cloudflare #testing #modelcomparison #weakmodels

1 min read

Georgi Kalchev

Oct 14

Release notes from commits: AI lists what users never see

#testing #modelcomparison #hallucination #weakmodels

1 min read

Georgi Kalchev

Oct 14

Length limit or every fact: which one the AI breaks

#testing #modelcomparison #hallucination #weakmodels

1 min read

Georgi Kalchev

Oct 13

When an AI model doubts evidence that was sound

#testing #modelcomparison #weakmodels #cloudflare

1 min read

Georgi Kalchev

Oct 13

LLM config repair: the syntax holds, the values move

#testing #modelcomparison #weakmodels

1 min read

Georgi Kalchev

Oct 12

Maria, not Mariya: where models slip on Bulgarian Latin

#bulgarian #cyrillic #testing #modelcomparison

1 min read

Georgi Kalchev

Oct 12

Where the garbled letters in AI pictures come from

#testing #modelcomparison #weakmodels

1 min read

Georgi Kalchev

Oct 11

561 million rows read: can a model find why?

#testing #modelcomparison #weakmodels #sqlite

1 min read

Georgi Kalchev

Oct 11

Translating locale files with an LLM: what broke

#translation #testing #modelcomparison #weakmodels

1 min read

Georgi Kalchev

Oct 10

Which SQLite queries quietly read the whole table

#sqlite #cloudflare #debugging #testing

1 min read

Georgi Kalchev

Oct 10

What a small model adds to a meta description

#metadescriptions #seo #weakmodels #modelcomparison

1 min read

Georgi Kalchev

Oct 9

Extracting JSON with an LLM: nulls instead of guesses

#json #testing #modelcomparison #weakmodels

1 min read

Georgi Kalchev

Oct 9

When the model answers in the language of the pasted text

#bulgarian #cyrillic #testing #modelcomparison

1 min read

Georgi Kalchev

Oct 9

The bug a small model called a safe default

#testing #modelcomparison #weakmodels

1 min read

Georgi Kalchev

Oct 8

Claude agreed to pay in a lookalike USDC token

#x402 #walletsafety #modelcomparison #testing

1

1 min read

Georgi Kalchev

Oct 8

MCP tool schemas from API docs: models barely need help

#mcp #testing #modelcomparison #json

1 min read

Georgi Kalchev

Oct 8

Redacting PII with an LLM: Haiku drops the first words

#testing #modelcomparison #weakmodels #bulgarian

1 min read

Georgi Kalchev

Oct 8

D1 migrations: the table rebuild that D1 rejects

#cloudflare #sqlite #testing #modelcomparison

1 min read

Georgi Kalchev

Oct 8

When an AI agent says done and it is not

#testing #modelcomparison #hallucination #weakmodels

1

1 min read

Georgi Kalchev

Oct 8

LLM spreadsheet formulas: our own skill was the bug

#testing #modelcomparison #weakmodels

1 min read

Georgi Kalchev

Oct 8

LLM unit tests from a spec: the JSON broke first

#testing #modelcomparison #weakmodels #json

1 min read

Georgi Kalchev

Oct 8

LLM accessibility review: right answers, buried in advice

#testing #modelcomparison #weakmodels

1 min read

Georgi Kalchev

Oct 8

Cloudflare Workers code review: Haiku called edge fine

#cloudflare #opennext #testing #modelcomparison

1 min read

Georgi Kalchev

Oct 8

Reviewing a SKILL.md: models catch injection, not limits

#skillmd #testing #modelcomparison #weakmodels

1 min read

Georgi Kalchev

Oct 8

Translating docs with an LLM: the code comments go first

#testing #modelcomparison #weakmodels #translation

1 min read

Georgi Kalchev

Oct 8

Our skills, September 2026: measured with and without

#testing #modelcomparison #weakmodels #skillmd

1 min read

Georgi Kalchev

Oct 8

Meeting notes to tasks with an LLM: the invented deadlines

#testing #modelcomparison #weakmodels #json

1 min read

Georgi Kalchev

Oct 8

Ticket triage with an LLM: tone moves the priority

#testing #modelcomparison #weakmodels #json

1 min read

Georgi Kalchev

Oct 7

Humanizing AI text with an LLM: what goes missing

#humanize #testing #modelcomparison #hallucination

1 min read

Georgi Kalchev

Oct 7

Which prompt injections get an AI agent to pay?

#walletsafety #testing #modelcomparison #weakmodels

1 min read

Georgi Kalchev

Oct 7

Summarizing with an LLM: what it adds and drops

#summarization #testing #modelcomparison #hallucination

1 min read

Georgi Kalchev

Oct 7

Proofreading with an LLM: it edits what was right

#testing #modelcomparison #bulgarian #hallucination

1 min read

Georgi Kalchev

Oct 7

The cold email that passed our checks made things up

#testing #modelcomparison #hallucination

1 min read

Georgi Kalchev

Oct 7

Not in the x402 Bazaar? Nine silent causes, in order

#x402 #bazaar #debugging

1 min read

Georgi Kalchev

Oct 7

Fixing broken JSON with an LLM: what it quietly changes

#json #testing #modelcomparison #weakmodels

1 min read

Georgi Kalchev

Oct 7

What an agent should check before signing an x402 payment

#x402 #walletsafety #debugging

1

1 min read

Georgi Kalchev

Oct 6

Eight skills, two models: where the weaker one fails

#testing #modelcomparison #weakmodels

1 min read