Human-Computer Interaction on AIBussin — AI applications, systems and books

The Interface Between Minds

Thu, 01 Oct 2026 09:00:00 +0100

A registrar finishes a night shift and hands over a ward of twenty patients to the day team. She has perhaps ten minutes. In her head sits a rich model: which patient is stable, which one worried her at 3 a.m. without quite triggering an alarm, which family needs a careful conversation, which blood result is pending and would change everything. What she can transfer is far thinner: a few sentences per patient, some numbers, a gesture toward the man in bed seven: “keep an eye on him”. The day team will reconstruct what they can and get on with it. Mostly this works. Sometimes the thing she could not quite encode is the thing that mattered.

What the Receiver Rebuilds

Thu, 01 Oct 2026 09:00:00 +0100

Two registrars take over bed seven on different mornings. The handover note is the same on both days: keep an eye on him. The first registrar covered the ward last week. She knows that this patient’s observations drift before he deteriorates, that he under-reports pain, and that “keep an eye” from this colleague means check him within the hour. She reads four words and rebuilds a whole plan. The second registrar is new to the ward. She reads the same four words and rebuilds almost nothing: a patient, some mild vigilance, no particular deadline. Both read the sentence correctly. Neither misread it. They recovered different things.

Communication Was Never Just Words

Thu, 01 Oct 2026 09:00:00 +0100

A junior engineer is stuck on a distributed-systems bug: two services deadlock under load, but only on Tuesdays. A senior colleague tries three explanations in sequence. First, a paragraph of prose describing lock ordering. The junior nods without understanding. Second, a hand-drawn diagram on a whiteboard: two timelines, two locks, arrows showing who waits for whom. Something clicks. Third, the senior mimes it with two coffee cups, sliding them across the table, and the junior laughs, because now it is obvious. Same information, three channels, three different outcomes. The prose was not wrong. It gave this person, at this moment, the wrong evidence to build from.

The Fixed Page

Thu, 01 Oct 2026 09:00:00 +0100

Three people open the same document on the same morning. It is a twenty-page national guideline on managing suspected stroke: symptoms, triage thresholds, drug doses, contraindications, referral pathways. A paramedic in an ambulance needs one thing: the three exclusion checks that decide whether to divert to the thrombectomy centre, readable in ninety seconds, in gloves. A junior doctor on the ward needs another: the dosing table with its renal exceptions, placed beside the contraindication list so the two can be checked against each other. A medical student revising in the evening needs a third: the causal story, why each threshold exists and what happens when it is missed, with the numbers present but in the background. The document contains everything all three need. The page, as rendered, serves none of them well. Each does the same labour: hunting through a linear arrangement that was optimised for nobody’s task.

Visual Compression

Thu, 01 Oct 2026 09:00:00 +0100

It is Monday morning and a security engineer faces forty browser tabs: weekend vulnerability disclosures, three vendor advisories, a thread dissecting one of them, two papers someone said she must read. She has an hour before stand-up. She will open perhaps six tabs and skim two. The other thirty-four will be judged, kept or closed, read or abandoned, on the thinnest of evidence: a title, a favicon, a remembered recommendation, the first three lines glimpsed on hover. Every judgement is a bet. Most bets are cheap when wrong. A few are expensive: the advisory she dismisses because its title reads like routine patch noise is the one describing the library her team ships.

Semantic Enhancement

Thu, 01 Oct 2026 09:00:00 +0100

A team inherits a ten-year-old payments service and its forty-page architecture document. One passage describes the retry policy in dense prose: three paragraphs of conditions, backoff intervals, idempotency keys, and two exceptions buried in the middle. A new engineer reads it three times and still cannot say what happens when the third retry fails during a partition. Then someone draws seven boxes and nine arrows on a whiteboard (states, transitions, the two exception paths in red) and the same engineer answers correctly in thirty seconds. Same passage. Same reader. Radically different understanding.

Meaning Becomes the Source

Thu, 01 Oct 2026 09:00:00 +0100

Consider what happens to the payments retry policy across a single week. On Monday a system reads the passage, decides it describes a process with topology, and draws a state diagram. On Wednesday it reads the same passage for a different reader and produces a timeline of the retries. On Friday it renders the passage as a table of backoff intervals. Three renderings, three fresh readings of the same prose, and nothing carried over between them except the prose itself, which sat unchanged while the system worked out, each time, what it had already worked out before.

Enhanced Interaction

Thu, 01 Oct 2026 09:00:00 +0100

A doctoral student reads a systems paper that cites, in passing, “the well-known impossibility result”: no proof, no reference, just the assertion. She opens a new tab and searches the phrase. She skims three PDFs, finds the actual theorem in the second, checks its assumptions against the citing paper’s setting, and discovers they do not hold here. Forty minutes gone. The paper is still open where she left it, her mental stack of its argument half-evaporated. She will spend ten more minutes working out where she was.

Similarity Is Not Discovery

Thu, 01 Oct 2026 09:00:00 +0100

The sidecar has a regular guest, and it is an embarrassing one. A researcher is reading a paper on retrieval evaluation and opens the side panel. Ranked first is a paper with nearly the same vocabulary: the same benchmarks, the same metrics, the same dataset family. She opens it. It contributes nothing. Same conclusions, weaker experiments, no new evidence, no disagreement, no extension. In the corpus it is the closest thing to what she is reading. As information it is empty. The system did its retrieval job perfectly and its discovery job not at all.

What Survived the Transformation?

Thu, 01 Oct 2026 09:00:00 +0100

Someone asks a system for a one-line version of the payments retry policy. It answers: “Failed payments are retried up to three times.” The sentence is fluent, plausible and professionally phrased. It is also not what the policy says. The policy had an exception for idempotent requests. It was explicitly uncertain about how a third-party timeout is handled. And it had a source, a design decision made two years ago for a stated reason. The one-liner keeps the headline and loses the rest. Nothing on the screen announces the loss. The sentence looks exactly as good as a faithful one would.

The Language Between Languages

Thu, 01 Oct 2026 09:00:00 +0100

A product owner asks for a job queue with two properties. A job must never be executed twice. And a job that fails for a transient reason should be retried up to three times. Both sentences are clear. Together they are not, and the problem lives in one word. If a job’s first attempt fails and is retried, has the job been executed twice? It depends what “executed” means. It could mean an attempt: any time the code runs. It could mean a completed job: a run that finished and counted. Or it could mean an externally committed effect: an email sent, a card charged. Under the first reading the two requirements contradict each other. Under the second or third they sit together comfortably.

The Semantic Browser

Thu, 01 Oct 2026 09:00:00 +0100

Take the twenty-page incident report from the first chapter. A database went down on a Tuesday. The report holds a timeline, excerpts of logs, five candidate causes, and a conclusion that two engineers dispute. It is the kind of document that has to be read by several people for quite different reasons, and the chapters of this part have been building, one piece at a time, toward handling it differently. This chapter puts the pieces together and follows that one report through them, to see what the system looks like when it works as a whole.

Too Much Information

Thu, 01 Oct 2026 09:00:00 +0100

Return to the incident manager from the last chapter, now with a Semantic Browser that works. She opens the report on Tuesday’s outage, and the system has found a good deal more than the report. There are forty earlier incidents that look similar. There is service telemetry for the hour in question. There is documentation for three dependencies, and a runbook that has not been updated since the migration. The record has turned up three possible contradictions between the report and other sources. The system has drafted seven diagrams of the causal story, each from a slightly different angle. There are fourteen relevant excerpts from the team’s chat, the change history for the week, and a handful of external write-ups of the same failure mode.

A Video Is Not an Hour

Thu, 01 Oct 2026 09:00:00 +0100

A person has one hour of video and ten minutes to decide whether it contains the answer she needs. (She, her colleagues and the talk are invented for this book, as are the examples that follow in this part.) It is a conference talk about a new consensus protocol, recorded last spring. She cannot watch it. She could scrub through, catching a few seconds here and there, or read the auto-generated transcript, fourteen thousand words of speech. The honest options the interface gives her are two: watch, or don’t. That is too coarse. The question she has is not “is this video worth an hour?” but “does it say whether this protocol survives the kind of failure we have?”

Important to Whom?

Thu, 01 Oct 2026 09:00:00 +0100

The talk on the consensus protocol has been broken into units, with the definition at minute 4 and the qualification at minute 53 joined where they belong. Three colleagues now ask the same system about it, each for a different reason. Priya has to decide whether the protocol is safe when network delays are unbounded. Tom is writing the history of consensus algorithms for a literature review. Mina wants to reproduce the demonstration.

Don't Tell Me What I Already Know

Thu, 01 Oct 2026 09:00:00 +0100

Priya asks about the consensus protocol, and the system knows something about her. She has worked on consensus systems for two years. She has given talks on the subject. So when it prepares her digest it leaves out the speaker’s definition of partial synchrony as something she plainly knows, and shows her the parts that look new. It is a considerate thing to do. It is also a mistake, because the speaker uses the term in a narrower sense than the one Priya works with. Her usual definition allows delays whose bound is unknown. In this talk the bound is known to the protocol, and everything the speaker later says about safety rests on that. Priya reads the digest, meets the claim about bounded delays, and concludes the talk contradicts what she knows. The system had removed the one piece of information she needed in order to read the rest.

From Channels to Semantic Channels

Thu, 01 Oct 2026 09:00:00 +0100

Priya follows fourteen conferences, nine labs, thirty authors and four preprint feeds on distributed consensus. In March, a result appears that undermines the assumption her team’s design rests on, the one about bounded network delay. It is in none of her feeds. It is a paper on distributed databases, from authors she has never heard of, and it never uses the word “consensus”. It shows a mechanism that works without the delay bound she has been treating as essential. She finds it in June, by accident, cited in a thread about something else. Three months of work stood on the old assumption.

Compression Has Levels

Thu, 01 Oct 2026 09:00:00 +0100

At three in the morning Priya’s semantic subscription fires. A new paper from a database group has appeared, and the system judges that it qualifies: it may weaken the assumption her protocol’s safety result rests on. The item is relevant to her purpose, new to her, and matches a relation she asked to be told about. All of that has been settled. What has not is how much of it she should see first.

When Should the AI Speak?

Thu, 01 Oct 2026 09:00:00 +0100

At 14:40 a candidate arrives: a new paper that may contradict an assumption in the code Priya has open in her editor. The system’s account of it is solid. The match is plausible, the evidence is attached, a brief is the right resolution, and the item is new to her. It also knows something else. She is presenting in a design review until 15:30, and the deployment the paper might affect is not until 18:00.

The Personal Information Radar

Thu, 01 Oct 2026 09:00:00 +0100

Priya’s afternoon, as seen from inside the system, begins at 14:40. She is in a design review that runs until 15:30. The Radar, which is what this chapter will call the system that has been assembled over the last seven chapters, the same layer as before now attending to a stream and not a single document, has four candidates waiting to reach her.

A  a new paper that possibly weakens the bounded-delay assumption
B  a major update to a library she uses often
C  an interesting new survey of consensus protocols, mostly material she knows
D  an incident report affecting tonight's deployment

Part I ended with a Semantic Browser, a renderer that treats a source as something to interpret and present. This chapter is the equivalent for attention. It asks: what does the whole attention architecture look like when information is continuously competing to reach one person? The metaphor is chosen with care. A radar watches continuously, signals enter and leave range, some are uncertain, they differ in significance, and not everything becomes an alarm. What the metaphor must not become is surveillance, and the chapter will say what prevents that.

The Personal Experience

Thu, 01 Oct 2026 09:00:00 +0100

A few weeks into using the Radar, Priya notices that it behaves differently from the first day. Library updates no longer interrupt her. Papers arrive with the conclusion first and the method behind a click. Comparisons come as tables. Contradictions of her protocol arrive with the evidence attached, never as a bare verdict. None of this surprises her entirely, and most of it she likes. (Priya and the sessions in this part are constructed for illustration, as in the last part. Where research is cited it is attributed, and nothing here reports a measurement of the book’s own.) But when she asks why a particular item was shown the way it was, the answer is not clear. Some of it she told the system. Some of it she did, and the system noticed. And some of it the system concluded for itself, from the way she had behaved, in ways she cannot now reconstruct.

There Is No Universal Best Interface

Thu, 01 Oct 2026 09:00:00 +0100

The previous chapter ended with a temptation. Priya’s behaviour is leaving traces. She opens tables more often than prose, expands the mathematical detail, ignores diagrams. A system that remembers could draw the obvious conclusion: this person is a certain kind of reader. Diagram people get diagrams, detail people get detail, and the interface learns her type and stops asking.

This chapter takes that shortcut apart. It does not do so by saying that people are all the same, which they plainly are not. The target is exact:

From Observation to Policy

Thu, 01 Oct 2026 09:00:00 +0100

Memory can be right and still make the present wrong

In March, Priya tells the system something important about a payments service.

The old replication path is gone. Writes now go through a new quorum path. She is explicit because the distinction matters to an incident review they are doing that afternoon.

The system remembers it.

Three months later, the service changes again. The quorum path is replaced during a larger architecture migration. The March statement remains perfectly good evidence about March. Priya really said it. At the time, it was correct.

The Person Changes During the Day

Thu, 01 Oct 2026 09:00:00 +0100

Priya opens the system on her phone before an architecture review and says: I have five minutes before the meeting. Just tell me what can break.

Her standing policy asks for implementation detail and equations when they affect the decision. Yesterday, at her desk, that meant a full account of the recovery path. Today the same account would consume the time she has before the meeting. But a short answer that hides the decisive qualification would also fail her.

Sometimes the Best Interface Adds Friction

Thu, 01 Oct 2026 09:00:00 +0100

At the start of an evening study session, Priya says: For this session, I want to finish this paper first. Remind me before I open another one. Twenty minutes later, a new result arrives through her semantic subscription. She reaches to open it.

The channel shows a line beside the action: You asked for a reminder before opening another paper. She can continue with the paper in front of her or open the new result immediately. The reminder makes the choice visible without taking it away.

Protection That Travels

Thu, 01 Oct 2026 09:00:00 +0100

Priya has asked her reading tool to remind her before she opens another paper. She has separately asked it to keep unrelated recommendations out of the reading view during the study session. Neither instruction governs her news or video services. When she moves to one of those, the recommendations return.

She now gives another instruction: For this evening’s study, keep new consensus-research recommendations out of the recommendation feeds in these two services. Leave search and direct opening available. End the rule when I finish the paper or end study, and by eight this evening in any case. She selects the services and accepts the scope.

What the System Believes About You Must Be Visible

Thu, 01 Oct 2026 09:00:00 +0100

Priya opens a talk about a consensus algorithm she has not used. The channel shows the algorithm’s steps and a diagram. An introductory section is folded away. When she asks why, it answers: Consensus foundations treated as already known, inferred from earlier architecture reviews.

Priya knows the field. But the folded section states which failures this particular algorithm assumes. Familiarity with consensus does not establish that she knows this talk’s assumptions, and even knowing them would not make their role in the argument dispensable. The inference has changed the communication at the point where its scope mattered most.

The Personal AI

Thu, 01 Oct 2026 09:00:00 +0100

At twenty past nine, Priya begins an architecture review. The channel has a standing policy she declared, observations from earlier reviews, an inference about derivations, and the means to apply temporary instructions and carry boundaries to selected services. It could use all of them.

Priya says: I have ten minutes. In this review view, show material that bears on the decision. Keep the decisive equations and assumptions visible; fold the supporting steps, with the full calculation available.

How Much of You Can an AI Reproduce?

Thu, 01 Oct 2026 09:00:00 +0100

Priya opens a new architecture review. The system predicts that she will choose the expanded calculation before the summary. Its record says that she chose the calculation in the previous review. That record may be correct. The prediction has yet to be tested.

It is a small distinction, easily hidden by a fluent interface. “You chose this last time” becomes “you will choose this now”, and then “I know how you think”. Each sentence makes a different claim. The evidence does not travel between them merely because the system speaks with the same confidence.

A Model of Me Is Not Me

Thu, 01 Oct 2026 09:00:00 +0100

A colleague asks Priya to meet on Tuesday afternoon. The system forecasts that she will accept and prepares a reply. In this constructed case, its forecast is right and its wording matches what she would have written. It has not been authorised to send the message.

That last fact does not become less important because the first two are true. The system could predict this particular choice very well and still have no standing to make it for her. “It knows what I would say” and “it may say it for me” require different evidence.

What Do I Want to Keep?

Thu, 01 Oct 2026 09:00:00 +0100

A colleague’s meeting request arrives. Suppose the system can notice it, interpret the request, check a calendar, suggest a response and send one. Even suppose it can predict which response Priya would choose. Those capabilities leave a question unanswered:

Which parts of this activity does Priya want to keep doing herself, and which does she want the system to do?

She says: “Check when I’m free and prepare a reply. I’ll decide whether this meeting belongs in the week. Show me the draft before sending.”

From Conversation to Delegation

Thu, 01 Oct 2026 09:00:00 +0100

Priya has decided what she wants to do about the Berlin trip. The last chapter ended with her statement of who does what, and she has made up her mind about one part of it: she will hand over the hotel. She does not want to search, compare and click through confirmation pages herself. She is happy for the system to do it, within limits she is clear about.

Until now, every output of the system has been something she could look at before anything happened: a view, a summary, a draft, a reminder. A booking is different. It changes the world. A hotel is reserved, money is committed, a cancellation window starts to run. The move from conversation to action is the first point in the book where a mistake cannot be corrected by editing a screen. So a further question has to be answered with something stricter than a preference:

What May My Proxy Say for Me?

Thu, 01 Oct 2026 09:00:00 +0100

The hotel replies to Priya’s booking request with a counteroffer. A room at €400 a night, with a free upgrade. (The amounts are illustrative.) The system holds a grant to book a refundable room up to €350, and it has just drafted a response. The text of the draft is four words: €400 works for me.

Those four words could be four different things. They could be a draft that Priya has not yet seen. They could be a signal in a negotiation, a way of testing whether the hotel will come down. They could be an acceptance of the offer. Or they could be a binding commitment, with a cancellation window attached. The text is the same in each case. What differs is what has been done: how much authority the act needs, how much it commits her to, and whether anyone can take it back.

Private Discovery Between People

Thu, 01 Oct 2026 09:00:00 +0100

Priya has been chasing a failure in her protocol for three weeks: an intermittent split vote under clock skew that she can reproduce about one run in twenty. She suspects someone else has seen it. She does not know who. The ways of finding out are the usual ones. She can post about it publicly and wait. She can search for people who have written about similar problems. She can lean on a platform that indexes what everyone has published and recommends accordingly. Each of these works because privacy has already been surrendered: her interest is announced, other people’s work is catalogued, and the introduction happens at the price of exposure.

A Society of Proxies

Thu, 01 Oct 2026 09:00:00 +0100

At a conference of five hundred researchers, every one of them has a system working for them, and every one has told it the same kind of thing as Priya did: find people who might collaborate with me. Each system is careful. It matches on a criterion its principal authorised, it asks for introductions through the staged process of the last chapter, and it keeps to every limit in its grant. Each finds twenty relevant people and sends twenty requests. (The numbers are illustrative.)

The Final Extent of Language

Thu, 01 Oct 2026 09:00:00 +0100

The book began with a registrar at the end of a night shift, handing over a ward of twenty patients in ten minutes. A few sentences per patient, some numbers, a gesture toward the man in bed seven. What she held in her head was far richer than what she could say, and the day team rebuilt what they could from what she gave them. It was the oldest picture of communication there is: