Measure AI recommendations with saved answers, stable prompts and explicit counting rules
Schema, entity markup, llms.txt and crawler access are implementation questions. Whether an assistant recommends your business is an observation que…
Latest News
⚑ Report a ProblemTech news from the best sources
All topics
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
database
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
security
showdev
testing
tutorial
typescript
webdev
When a Query Returns 1,225,564 for an Appliance That Ships in Thousands: Reading Fuzzy Matching Honestly
When a Query Returns 1,225,564 for an Appliance That Ships in Thousands One result from a recent measurement round deserves more attention than the…
Penpot returned a true zero: 3,617 title matches and no fingerprint in any field
Penpot returned a true zero: 3,617 title matches and no fingerprint in any field Zero is a result worth reporting precisely, and it is also easy to…
How much of the public internet runs on Caddy? A ZoomEye measurement of 1.7 million assets
How much of the public internet runs on Caddy? A ZoomEye measurement of 1.7 million assets What the number is for Caddy is a web server written in G…
Measuring How Cost Scales by Counting Instead of Timing
Code: Megapixel99/countfn Every empirical complexity tool I could find on either registry measures elapsed time. PyPI's big-O estimates the class fr…
A Curve Fitter That Refuses to Answer
Code: Megapixel99/undetermined Plenty of libraries fit a curve to measurements and hand you back a number. undetermined hands back a number with the…
Breaking CI Guards on Purpose to Prove They Can Fail
Code: Megapixel99/canfail A CI guard that has never failed may be incapable of failing. A lint rule disabled by a config merge, a type check whose g…
Ten Packages, One Rule: A Check Must Be Able to Fail
Between 20 August and 31 August I published ten small packages, eight of them on the last day. The first of the eight repositories was created at 06…
What Mutation Testing Frameworks Do When a Timeout Kills Them
Code: Megapixel99/assay-checks assay audits mutation harnesses: the scripts that deliberately break your code and check that a test notices. It look…
My Extraction Score Was 0.08 and the Model Was Innocent: Rebuilding the Ruler
Update — v0.3.1 released. CauterRule is now live on GitHub and PyPI . It turns repeated agent failures into permanent standing rules — extract, repl…
Predicting the Speed of a 276B Model Streamed From an SSD
A mixture-of-experts model only activates a few of its experts per token, which means (unlike a dense model, where every forward pass touches every…
Why a Small Transformer Can't Copy a Word It Hasn't Seen
I have a small transformer that turns a one-line spec into a working web app. It is 11.9M parameters, 6 layers, d=384, trained on 4,176 generated pr…
How a Dedup Pass Deleted My Training Curriculum
Code: Megapixel99/capture-the-flag I built a capture-the-flag arena where language models attack and defend each other's containers. The replays the…
Comparing INT4 and NVFP4 Palettes on Real Gradient Tensors
Four-bit training quantizes every number to one of 16 values. NVFP4's menu is {0, ±0.5, ±1, ±1.5, ±2, ±3, ±4, ±6} , with one scale factor per block…
Don't trust model quotes; use anchors instead
I asked models to extract facts with provenance two different ways. Naive: return {answer, quote} , insist the quote is verbatim, then string-match…
An AI Capture-the-Flag Tournament: What the Scoreboard Counted
Code: Megapixel99/capture-the-flag In April I ran five games of an AI capture-the-flag tournament between five small open-weight models (1.0B to 2.5…