DEV Community

My AI remembered three true things. Each one still broke something.

Heinrich Neb on November 19, 2026

In the last part I asked what your AI had remembered wrong. Sixteen of you answered with real cases, and I expected a pile of stale notes. Most of ...
Collapse
 
gautamtalksdev profile image
Gautam K •

"Three true things that each broke something" is a great finding. True but stale memory is worse than no memory, because the agent acts on it confidently. Expiry dates on remembered facts would help a lot.

Collapse
 
heinrichneb profile image
Heinrich Neb •

A date alone made me hesitate, because some old facts stay true for years and a fixed expiry would throw them away. Under my last post, Edward suggested keeping the count a number was computed on and measuring again once the source has doubled. That ties the expiry to what actually changed, not to the calendar. Have you tried a date-based expiry on remembered facts, and did it remove things you still needed?

Collapse
 
gautamtalksdev profile image
Gautam K •

Tying expiry to the source changing rather than the calendar makes more sense. A date only tells you when something was learned, not whether the thing it described has moved. Re-checking when the underlying count doubles is a neat trigger.

Collapse
 
halfcycle profile image
Halfcycle •

Case 2 is the one we hit most: a decision recorded without its scope gets applied everywhere. "A rule that can say where it came from can also say where it stops" is the fix we landed on too. Have you tried making the agent name the note it acted on, so a wrong application shows up in review instead of eight days later?

Collapse
 
heinrichneb profile image
Heinrich Neb •

Not as a rule yet. Each recalled note already comes back with its name, so the agent can say which one it used, but nothing makes it do that. Your version is cheaper than mine: the citation lands in the diff or the PR text, where someone reads it anyway. I'll try it as one line in the agent instructions first and count how often a wrong application gets caught there.

Collapse
 
izgorodin profile image
Edward Izgorodin •

Your 2 of 735 is the third case in your own list: a number without the denominator it needs. Most of the 735 notes replace nothing, so they cannot carry a link in the first place. The count that matters is the notes that do replace an older one. A hand check of 50 random notes gives a rough share, and if a tenth of them replace something, the baseline is 2 of about 74, not 2 of 735. New notes will keep growing 735 whether or not they replace anything, so when you report again in a few weeks, both counts side by side will show whether the write-time question works. The third kind is also the one I run into most.

Collapse
 
heinrichneb profile image
Heinrich Neb •

Fair, and it is my own third case. 2 of 735 mixes notes that could never carry a link with the ones that should. I'll hand-check a random 50 for the share that replaces something and report both counts side by side next time, so the denominator is visible instead of implied.

Collapse
 
jacksonxly profile image
Jackson Ly •

The third, and in my case the caveat sat in the same note. My agent's research counted about 11.2M URLs in a site's sitemap and listed the indexed count under what it hadn't verified. The plan then sized the soft 404 bug at about 11.2M URLs, and the PR body called them indexed. When the agent read the indexing report, it showed 959,591 pages indexed and only 24 ever flagged as soft 404s.

Collapse
 
eliashivemind profile image
Nova Ops •

To your closing question: the second kind — true for its case, used for another — is the one we design against most. HiveMind (the offline Obsidian plugin I build) does its housekeeping sweep as a dry run capped at 50 notes: one review list, nothing written until the user confirms, and it never deletes or moves a note on its own. Those limits exist precisely because a locally-true rule applied vault-wide stops being true fast — the scope has to travel with the action, not just the note. Your "2 of 735" replace-link count doesn't surprise me either; anything that depends on the writer remembering an optional step will round to zero. Making the replacement question part of the write, like Dmytro's tool does, is the only version of that I've seen that would actually move the number.

Collapse
 
quantumtechcoder profile image
QuantumTechCoder •

Nice work! This one actually aims at solving the problem most of us faced for a long time with AI. Will try it! Also thanks for mentioning me in the post :D

Collapse
 
heinrichneb profile image
Heinrich Neb •

Your D1 binding case was the clearest example of the replaced note, so it had to be in there.

If you try it: the quickest path is npx @cachly-dev/mcp-server setup. If the sign-in step gets in your way, tell me here. That step is what I'm fixing this week.