Proved, Certified, Swept, Sampled
A claim in a paper can be backed by very different things. It can have a written proof. It can have a theorem the Lean kernel has checked. It can ha…
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
The Visible Test Suite Is the Ceiling on What the Next Agent Can Deliver
Originally published at tddbuddy.com . Related reading: Coverage Was a Proxy. The Proxy Just Failed. names mutation score as one metric under the ce…
AI agents designed the chip that runs their inference
openTPU is an AI inference accelerator whose SystemVerilog, instruction set, compiler, bit-exact simulator and host stack were written by AI agents.…
Your Verifier Is a Confident Liar
The official judge said the agent succeeded 74% of the time. A better verifier said 38%. That gap — almost double the reported success rate — is not…
Finding Duplicate Functions by Executing Them, Not Reading Them
Code: Megapixel99/assay-checks assay asks two questions about work that already passes its tests: could those tests have failed, and does the tree a…
A Check With a Zero Denominator Reports Clean
Code: Megapixel99/zerocase A suite whose every test was skipped, a lint whose glob matched nothing, and a coverage run over no statements can all ex…
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…
Customer Domain Verification: Scheduled Polling and Triggered Rechecks for Tenant Onboarding
Give each fintech tenant a platform-owned subdomain first, and activate it from the platform's own DNS change. For a customer-owned hostname, run sc…
Who Verifies the Verifier?
The premise of this series is that you should not take an agent's word that it is done. So I built a gate that makes Claude Code prove each task in…
Proving the Tree Came Back After Breaking It on Purpose
Code: Megapixel99/restore-verified Any tool that breaks a file on purpose and puts it back (a mutation harness, a codemod, a benchmark swapping a co…
Domain Verification vs Email Confirmation for Workspace Joining — Control in 2026
Short answer: use DNS domain verification to establish organisational control, use email confirmation to establish a person's current mailbox access…
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…
KYB + KYC : Architecting 'Know Your Business', 'Entity Graph Traversal' & 'PII Orchestration'
KYB and KYC get bundled into the same dashboard and the same sentence, but they verify different things for different customer types. Here's what Kn…
7 Rules for Email and Phone Verification Delivery Risk and Account Continuity
The page fires at 02:13. A student cannot sign in, support is asleep, and the dashboard shows a healthy login endpoint. The missing signal was earli…
Coding Agents Invent Facts When Denied Them. All 4 of My Probes Returned a False Zero.
A new arXiv paper watched coding agents get denied the facts they needed. They did not stop. They invented. On August 17th, a group of researchers p…
The Verification Ladder: A Field Guide
Claude has, at various points in our working relationship, warmly endorsed: an efficiency statistic fabricated over one too many turns of a massive…
Green Is a Timestamp
A test failed in my Medicare reimbursement engine on a day nobody touched the code. No commit, no deploy, no new data. I read the diff twice looking…
The Agent Can Own the Loop. It Cannot Own the Receipt That Ends It.
Peter Steinberger put it plainly: you shouldn't be prompting coding agents anymore, you should be designing loops that prompt your agents. Boris Che…
Introducing correctover-patronus: 6-Dimensional Verification for Patronus AI
The Problem LLM evaluation tools like Patronus AI excel at hallucination detection, toxicity checks, and semantic relevance. But they don't catch th…
Can You Tell When an LLM API Swaps in a Cheaper Model?
If you call an open-weight model behind an API, whether that is your own box, a hosted endpoint, or a router, you are trusting that the thing answer…
Design Verification at 3nm: What's Actually Hard and How Teams Are Solving It
If you've been following semiconductor news, you know the industry is deep into the 3nm era. But while fab announcements grab headlines, the verific…