| # | Tweet | Community | Topic | Views ▼ | Ratio | Engagement | Posted |
|---|---|---|---|---|---|---|---|
| 1 | [video] Persistent coding-agent memory has a nasty edge case:
same error message, different root cause.
Retrieval can find the “right” old memory and still suggest the wrong fix.
I’d love to see this benchmarked adversarially.
Actian’s current Astra implementation: | Local AI | — | 196 | 2.5x | 4 | Oct 8 |
| 2 | [image] AI-assisted PRs are 2.6× larger on average in a recent benchmark data.
Once the diff gets huge, review quality drops fast.
A simple rule is to give coding agents a diff budget.
If the task crosses it, split the PR.
See the benchmark here | Ai community | — | 21 | 0.3x | 3 | Oct 11 |
