RAG on Nikhil Adhikari

Confident Matches on Vocabulary, Not Mechanism

Sat, 25 Jul 2026 00:00:00 +0200

The short version, for anyone: The system finds past incidents by comparing meaning, but sometimes two very different failures use the same words — “Cloudflare,” “edge,” “database” — and it confidently returns the wrong one. This is the most dangerous kind of error: not a crash, not an obvious miss, but a confident wrong answer that would send an engineer down the wrong path during a live outage. Rather than hide it or fake a better score by deleting the test, I’ve kept it visible and documented — because knowing exactly where a reliability system fails is the reliability work, and this particular fix is real design work, not a quick tuning tweak.

Full finding below.

Where it shows: Layer 1 retrieval and Layer 2 diagnosis — the same failure, twice. Status: Understood, not fixed. Kept visible on purpose.

The short version

The system sometimes matches on shared words rather than shared cause, and does it with high confidence. A query and an incident can use the same vocabulary while describing completely different failures. The embedding scores them as close, the system returns the wrong incident, and nothing about the score signals that it’s wrong. This is the failure the whole project exists to guard against: not a crash, not an obvious miss, but a confident wrong answer that would mislead an on-call engineer during a live outage.

Instance 1 — Layer 1 retrieval: the DDoS probe

A no-match probe: “DDoS attack overwhelmed our CDN edge nodes and caused a 12-hour outage.” This is meant to retrieve nothing — the corpus has no DDoS incident. Against the 15-document corpus it correctly declined. Against the 20-document corpus it now matches a Cloudflare incident at distance 0.236 — well inside the 0.30 threshold, a confident hit.

But that Cloudflare incident is a configuration-error incident: a database access-control change that cascaded. It has nothing to do with a DDoS, which is a volumetric attack. The match is on surface vocabulary — “Cloudflare,” “edge,” “outage” — not on the failure mechanism. The probe stays classified as a no-match; its continued matching is the finding, not something to reclassify away.

Instance 2 — Layer 2 diagnosis: the XID-wraparound attractor

In the Layer 2 baseline, three descriptions produced a diagnosis of Postgres transaction-ID (XID) wraparound. Two were correct (a real Sentry Postgres incident). The third, L2-007, was wrong — it’s Roblox’s service-registry cascade, nothing to do with Postgres. But it shares symptom vocabulary — read-only, cascade, database — with the Sentry incident, and the model reached for the specific, authoritative-sounding failure it had seen before.

Why these are the same failure

Both are the system latching onto a specific, plausible, well-documented failure because the surface features match, while the actual mechanism does not. The danger in both is the confidence. A vague wrong answer is easy to distrust. “PostgreSQL XID wraparound” and a 0.236 distance both look authoritative. During an incident, that’s worse than silence — it’s a false lead delivered with conviction.

Why it is being kept visible rather than patched

It is honest signal. The Layer 1 decline rate is 0.500 — three of four no-match probes decline correctly, and the DDoS probe is the one that doesn’t. Forcing that number to look better by deleting the probe would hide a real property of the system. The metric is more useful with the known failure inside it.

The fix is not local. This isn’t a threshold to nudge or a prompt line to add. It’s a limitation of matching on embedding similarity and symptom vocabulary. Addressing it properly means giving the system more to discriminate on — richer context at retrieval time, or a verification step that checks whether the mechanism actually fits before returning a confident answer. That’s real design work, recorded here as the direction rather than attempted as a patch.

What would actually address it

Retrieval: search richer text so the match rests on more than a few shared nouns. More context gives the embedding more to separate genuinely-similar incidents from merely-similarly-worded ones.
Diagnosis: a mechanism-check before a candidate is returned with high confidence — does the cited incident’s actual failure mode match the symptoms, or only their vocabulary? This is a grounding step one level deeper than citation-checking: not “is this incident real and retrieved,” but “does this incident actually explain what was reported.”

Both are deferred. Both are the honest fix. Neither is a tuning change.

The Layer 2 Baseline, and a Grounding Filter That Leaked

Fri, 24 Jul 2026 00:00:00 +0200

The short version, for anyone: Before you can detect whether a system is getting worse, you need a measured snapshot of how good it is now — a baseline. Building that baseline for the diagnostic agent immediately caught a real bug that 30 existing unit tests had missed: a safeguard meant to strip out “made-up” citations was letting them through, as long as at least one real citation rode alongside. One genuine reference could smuggle in any number of invented ones. The lesson: unit tests check the cases you thought of; measuring against real output catches the ones you didn’t.

Full finding below.

Measured on: 15 descriptions through the full agent · Result: first measured Layer 2 baseline; one grounding bug found and fixed.

Why this matters

Layer 2 had 30 unit tests proving the machinery worked, and one integration run judged by eye. It had no numbers. You cannot build a regression gate — which detects regressions by comparing against a baseline — without a baseline to compare to. This is that baseline. Building it also caught a real bug the unit tests had missed.

The bug the baseline caught

The first run reported 2 grounding violations — candidates citing incident IDs that were never retrieved. That number is supposed to be impossible by construction, so the tripwire fired.

Why it slipped through

The grounding filter kept a candidate if any cited ID was real:

cited = {...} # every id the model cited
if cited & valid_ids: # at least one is real?
 grounded.append(d) # keep the whole thing, evidence unchanged

So a candidate citing aws-s3-2017-02-28, gitlab-2017-01-31 passed — aws-s3 is real, the intersection is non-empty — and carried the fabricated gitlab citation through untouched. The filter checked that at least one citation was grounded. It never checked that every citation was. One real id smuggled in any number of invented ones.

The fix

real = cited & valid_ids
if not real:
 continue # nothing grounds this, drop it
d["evidence"] = ", ".join(sorted(real)) # keep only the real citations
grounded.append(d)

A candidate now survives only if it has a real citation, and its evidence is rewritten to contain only real citations. Fabricated ids are stripped, not tolerated. Covered by a new test that feeds one real and one fake id and asserts only the real one remains.

Why the unit tests missed it

The existing grounding test used candidates that were entirely fabricated — those were correctly dropped. The gap was the mixed case: one real citation plus one fake. No test exercised it, so nothing failed. The scoring run on real model output was the first thing to hit it. That’s the point of scoring against real output: unit tests check the cases you thought of, evaluation catches the ones you didn’t.

The baseline (after the fix)

Metric	Value
top-1 accuracy	0.625 (5 of 8 with a primary cause)
any-hit rate	0.615
noise rate	0.444
decline rate	1.000 (2 of 2 no-match entries)
mean candidates	1.80
grounding violations	0
mean iterations	2.20

No targets were set in advance — the first clean run is the baseline, so the gate enforces “do not fall below this,” not an invented number. The one exception is grounding violations, which isn’t a target but an invariant: it must be zero.

Reading it

What works: decline rate is perfect — the reliability behaviour (declining rather than inventing) holds. Mean candidates fell from 5 to 1.8; the list no longer pads. Grounding is clean and now provably so.

What doesn’t: noise rate 0.444 is high, but concentrated, not spread — two specific descriptions (L2-003, L2-007) produce almost all the noise in the whole suite. Every other entry is clean or nearly so. So the problem is two descriptions the agent handles badly, not a diffuse quality issue — a located problem to work on rather than a general sense that quality is mediocre.

What this unblocks

Layer 2 now has a committed baseline across seven metrics and a clean grounding invariant. The regression gate has something to regress against — and two concrete, located problems to work on: the noise concentrated in L2-003 and L2-007, and the XID-wraparound attractor (documented separately).

The three layers where ML systems fail

Thu, 12 Feb 2026 00:00:00 +0100

Most ML portfolios show a model that runs once. The interesting engineering is in the part that comes after: keeping it running. In my experience, ML systems fail at three predictable points.

1. Bad data gets in

The model trains or scores on corrupt input and nobody notices until the numbers are wrong three steps downstream. The fix is boring and essential: validate data before it reaches the model — missing values, duplicates, malformed headers, schema drift.

2. The model drifts in production

A model that passed every test on launch day quietly degrades as the world changes underneath it. The first sign shouldn’t be an angry user — it should be a metric. That means monitoring distribution shift (PSI, Wasserstein) and gating deployments on it.

3. The same failure repeats

An outage happens, someone writes a post-mortem, it gets buried in a wiki, and six months later the same thing happens again. Turning past failures into searchable, deployment-gating feedback is the third layer — and the one almost nobody builds.

One principle — reliability — across three layers: data, model, system. That’s the thread running through everything on my projects page.