undefined | Better HN

Skip to content

Top New Best Ask Show Jobs

0 pointswhalesalad1mo ago0 comments

I am having a shit experience lately. Opus 4.7, max effort.

> You're right, that was a shit explanation. Let me go look at what V1 MTBL actually is before I try again.

> Got it — I read the V1 code this time instead of guessing. Turns out my first take was wrong in an important way. Let me redo this in English.

:facepalm:

0 comments

5 comments · 5 top-level

tremon1mo ago

> I read the V1 code this time instead of guessing

Does the LLM even keep a (self-accessible) record of previous internal actions to make this assertion believable, or is this yet another confabulation?

al_borland1mo ago

This seems like the experience I've had with every model I've tried over the last several years. It seems like an inherent limitation of the technology, despite the hyperbolic claims of those financially invested in all of this paying off.

ed_elliott_asc1mo ago

If it isn’t working for you why don’t you choose an older model? 4.6

ericol1mo ago

Matches what I am experiencing. Makes incredible stupid mistakes.

The weird stuff is yesterday I asked it to test and report back on a 30+ commit branch for a PR and it did that flawlessly.

alphabettsy1mo ago

The docs suggest not using max effort in most cases to avoid overthinking :shrug:

j / k navigate · click thread line to collapse