ilOblique

[ilOblique @ilOblique]

Three lines worth asking your contractor for, about last month:

What review caught.
What it would have cost.
Which green check let it through.

The full catch log: https://t.co/5kyw8UgTzB

#CodeReview #AgenticCoding

[ilOblique @ilOblique]

An agent writes the PR. A review bot checks it. The tests are green. So why does human review take a day?

"Context and ownership" doesn't answer that. A log does.

Four entries from one week on krilal board.

[ilOblique @ilOblique]

4/ The one with a price tag.

In a pool of parallel requests, the first error didn't stop the batch. Task 1 of 10 fails, all ten still start: paid calls nobody will read.

After the fix: at most four requests go out after a 403, and the ones in flight are cancelled.

[ilOblique @ilOblique]

Your AI pilot didn't measure your business. It measured who you onboarded first.

In Jeff Wahlberg's teardown, a $447/yr pilot estimate became ~$9,100 on a random sample. Same prices, same code.

Before year two: random sample, then median, p90, p99, max.

#FinOps #AIagents

[ilOblique @ilOblique]

One number to pull on Monday: of the PRs your agents opened this quarter, how many merged, and who owned each one.

If the answer is "nobody in particular", start there.

The full breakdown: https://t.co/T3QX2Mrjbo

#AgenticCoding #CodeReview

[ilOblique @ilOblique]

At the top 10% of engineering orgs, AI writes 45% of merged lines.

Autonomous agents open 4.7% of the pull requests.

Same teams, same year. The gap between those two numbers is the part nobody is pricing.

[ilOblique @ilOblique]

That decision drops a line item. The license goes away. The owner does not.

Someone still has to review, merge, patch and answer for that code for as long as it runs. We think that if nobody is named, you did not save the cost. You moved it.

[ilOblique @ilOblique]

Then weight ratings by the evidence behind them. We think a thumbs-down with a manual edit is the strongest label you have: the user showed you the right answer.

#LLMevals #ProductAnalytics

[ilOblique @ilOblique]

F-Secure's survey (September 2026) shows the same from the other side:

70.1% almost never check AI answers in practice.
47.3% drop their doubts when an answer sounds smooth and confident.
35.3% "check" by asking another chatbot.

[ilOblique @ilOblique]

Our bet: the "nothing" bucket rates highest. If so, your headline satisfaction number is mostly that bucket.

If verified users rate just as high, we're wrong and your ratings are a real signal. That's worth knowing too.

[ilOblique @ilOblique]

A 2026 study in Technology in Society surveyed 544 generative-AI users: the more they trust the system, the more willing they are to give it feedback — and the less likely they are to verify its output.

The authors call it "feedback without verification."