Практика Shadowing: Context Engineering for AI Agents: 4 Failure Modes to Avoid - Изучайте разговорный английский по видео

Выберите режим практики

Каждый режим открывает полноэкранную комнату практики.

116 предложений
Если предложения слишком короткие или длинные, нажмите Edit, чтобы их изменить.
1
context windows have grown from well a few thousand tokens to well a lot bigger like a million
2
or more and that's room for more stuff more instructions tool results docs you name it
3
so if we think about ai agents
4
and we give them access to this big old context window well
5
they should probably be getting better at long -running tasks shouldn't they?
6
I mean the more context the better job they can do.
7
Well a recent study looked at 18 frontier models
8
and it turned out that they all got less reliable as the context window got bigger.
9
Researchers have taken to giving this thing a name and that is context rot.
10
The more tokens in the window the less reliably the model uses any of them.
11
And this is the problem that context engineering is there to solve.
12
Context engineering is deciding what actually goes into this context window at each step of an agent's run.
13
Now there are many ways an agent's context can go wrong and I'm going to cover four of them.
14
The four failure modes that you can encounter when working with these big context windows.
15
And because I'm feeling nice I'll also suggest how to fix each one.
16
And the funny thing about those fixes is they involve deliberately throwing away information.
17
So how does an agent get better by holding less context?
18
Well to answer that we should first take a look at what's actually filling up these giant context windows.
19
So let's say an AI agent was given the job to migrate an aging code base over to a new database driver.
20
So I'm talking about here we are building a migration AI agent.
21
Now at the beginning of the context window the first thing most likely in here is the system prompt.
22
That's the standing instructions for how the agent operates in general.
23
Now the agent task itself
24
that will also be stored in here as well just as a prompt on its own
25
and it might not be very big it might only be a couple of lines.
26
Then many agent harnesses also pull in a bunch of project instructions.
27
Now these are things like an agents .md file explaining how this particular project is built.
28
Then after that we might have some tool definitions, a description of every tool the agent can call.
29
And from here on in the context window turns into a bit of a running log
30
so we're going to have a message history here this is every step the the agent has taken
31
and after let's say an hour of running well
32
this could get pretty big that's going to be a lot of steps
33
and then the biggest band is probably the tool results
34
that we store here which is things like file contents
35
and test output and error logs and schema dumps
36
so the job description the prompt is a few lines near the front
37
and pretty much everything else is the stuff
38
that the agent kind of piles up along the way oh
39
and buried in this as well there happens to be a note
40
this is a note the agent wrote itself it says
41
that the new driver retries failed connections automatically
42
so the old retry code can be deleted
43
so the note just basically says hey don't bother with writing any retry code why do i mention
44
that we'll come back to
45
that anyway why is a full context window a problem well
46
a model doesn't look things up in its context the way
47
a database looks up a row every token in the window
48
is competing for a finite amount of attention essentially an attention budget.
49
And to me, this is kind of the crux of it.
50
The window might hold a million tokens, but the attention spread across those tokens is finite.
51
Now, what about those failure modes?
52
Let's start with the first one.
53
Number one, that is context poisoning.
54
So I cryptically mentioned the agent wrote itself a note about the new driver retrying failed connections automatically.
55
Well it turns out that that note is completely wrong.
56
The agent shouldn't have done this.
57
It basically skim the driver's documentation, it misread it, and then it's written down a false conclusion.
58
And that's all poisoning is.
59
A mistake gets into this context window somewhere and then gets treated as fact because to the AI model,
60
its own notes, they look like the ground truth.
61
So file after file, our agent has been deleting perfectly good retry code.
62
Next, number two, that is context distraction.
63
This is where the sheer size of the history starts steering the agent.
64
Now a language model at its heart is just a pattern continuation machine
65
and when the context holds at say an hour of an agent's own past actions, that history becomes pretty much the strongest pattern around,
66
stronger than the reasoning it picked up in training.
67
So instead of asking what the job needs next the model
68
might drift into doing more of what it has already done
69
in this message history agents in this state can get stuck just kind of going over old ground
70
what about number three that is context confusion
71
and this one comes from the tools our agent here is wired into quite a lot of stuff
72
there's probably some amount of version control here
73
it might be access to a database console maybe it also is logging tickets into a ticketing system
74
and each of these tool definitions is in the window whether it actually gets used
75
or not and having more of them makes choosing the right tool a bit harder
76
and in one benchmark a model failed a task
77
when it was offered 46 tools but it then passed the very same task
78
when it was only offered 19 tools
79
that is tool sprawl work okay number four that is context clash
80
which is when the window contains information that disagrees with itself
81
so take that note with the bad information at some point our agent is going to see
82
that no retries are happening and it's going to figure out
83
that that note was wrong and it will probably make a note of
84
that into its message history as well
85
but the problem then is we now have both versions sitting in the window
86
that are presenting conflicting information so these are four different ways a context window can go bad
87
all right so what about some potential fixes well for poisoning one of the fixes is to validate.
88
Before a conclusion gets written down into this context window, check it against something real.
89
So one quick connection test and our agent would never have written this no retry code note.
90
What about distraction?
91
Well, the fix there is really too compact.
92
When the history gets really, really long, the agent can summarize it,
93
which is to say it throws the full log away and starts again from the summary,
94
a shortened version of what was in this message history in the window.
95
Now compaction is lossy.
96
A summary of a summary can start to drift like a photocopy of a photocopy.
97
So consider moving as much out of the context window as possible and put them into permanent files instead.
98
Detailed information can be retained in those files, and then it can be pulled into the context window only when it's actually needed.
99
All right, what about context confusion?
100
Well, that is a curation problem, so the fix is to curate.
101
The agent doesn't need 46 tools for database migration, so just give it the handful that the job calls for,
102
and then it can always go and fetch others
103
if it actually needs them then finally context clash well the fix there can be to prune so
104
when information gets superseded just delete the old version rather than leaving both in the window
105
we could have deleted this guy entirely or go further
106
and start a fresh window just restating the current corrected state of the job
107
and leave the poison stuff behind so
108
if a false conclusion gets saved that's poisoning so you can validate
109
if the history has taken over that's distraction so compact
110
if the agent has more tools than the task needs that's confusion
111
so curate and if the context disagrees with itself that's a clash and the fix is prune.
112
And all four fixes work by throwing something away.
113
An agent can get better at long tasks by holding less.
114
Now I'd love to know how you keep an agent's context lean.
115
Do you have your own context engineering fixes?
116
Let me know in the comments.

Скачать приложение

Всё для свободной речи

ИИ-оценка произношенияОценка каждой фразы
Практика IPAОсвойте каждый звук
СловарьСоберите свой словарный запас
Игра со словамиУчитесь играя

Тот же канал

FOR YOU

Рекомендуемое видео

Лексика и советы по произношению к этому уроку

Этот урок разговорной практики построен на видео «Context Engineering for AI Agents: 4 Failure Modes to Avoid». Чаще всего повторяются слова: context, agent, window, tool, note. В этом видео 100 предложений и 1451 слов для шедоуинга. Речь длится 10:08. Говорящий держит ровный темп — около 143 слов в минуту, удобный для шедоуинга. 86% слов входят в 3000 самых частых слов английского языка; остальные стоит разобрать перед занятием.

Ключевая лексика этого видео

15 слов из видео, которые стоит выучить, с произношением и значением:

СловоПроизношениеЗначение
poison существительное/ˈpɔɪ.zən/яд, отра́ва
token существительное/ˈtoʊkən/знак, си́мвол
database существительное/ˈdeɪtəˌbeɪs/ба́за да́нных
delete глагол/dɪˈliːt/удаля́ть, удали́ть
conclusion существительное/kənˈkluːʒən/оконча́ние, заверше́ние
summary существительное/ˈsʌm.ə.ɹi/резюме́, кра́ткое изложе́ние
confusion существительное/kənˈfjuːʒən/пу́таница, неразбери́ха
instruction существительное/ɪnˈstɹʌkʃən/инстру́кция, инструкта́ж
clash существительное/ˈklæʃ/лязг, громыха́ние
prompt глагол/pɹɑmpt/побужда́ть, внуша́ть
distraction существительное/dɪsˈtɹæk.ʃən/отвлече́ние
log существительное/lɔɡ/бревно́, коло́да
migration существительное/maɪˈɡɹeɪʃ(ə)n/мигра́ция, переселе́ние
disagree глагол/dɪsəˈɡɹi/не соглаша́ться
compact прилагательное/kəmˈpækt/компа́ктный, пло́тный

Фразовые глаголы, которые вы услышите

СловоПроизношениеЗначение
turn out глаголока́зываться, оказа́ться
figure out глаголразбира́ться, разобра́ться
fill up глаголзаполня́ть, запо́лнить
look up глагол/ˌlʊk ˈʌp/улучша́ться
pile up глаголнагроможда́ть, нагромозди́ть
take over глаголбрать на себя́, взять на себя́
throw away глаголвыбра́сывать, вы́бросить
write down глаголзапи́сывать, записа́ть

Грамматика в этом видео

Конструкции, которые говорящий использует чаще всего, с точными словами из видео:

КонструкцияВ видео
Пассивный залог be + причастие прошедшего времени — важно, что происходит, а не кто это делаетwas given · be stored · is built
Present Perfect have/has + причастие прошедшего времени — прошлое действие, важное сейчасhave grown · have taken · has taken

Произношение, на которое стоит обратить внимание

Говорящий использует 12 сокращённых и редуцированных форм, например doesn't, gonna, I'm. Произносите их коротко, так, как слышите.

  • Звуки «sh» и «zh»: conclusion /kənˈkluːʒən/, confusion /kənˈfjuːʒən/, instruction /ɪnˈstɹʌkʃən/, clash /ˈklæʃ/, distraction /dɪsˈtɹæk.ʃən/
  • Длинные слова — следите за ударением: essentially /ɪˈsɛnʃəli/, deliberately /dɪˈlɪb.(ə.)ɹət.li/, documentation /ˌdɑkjəmɛnˈteɪʃən/, continuation /kənˌtɪnjʊˈeɪʃ(ə)n/, photocopy /ˈfəʊtəˌkɒpi/

Звуки, трудные для русскоязычных:

  • /h/ — лёгкий выдох, а не русское «х»: handful /ˈhæn(d)fʊl/, harness /ˈhɑɹ.nəs/
  • Звонкие согласные в конце слова — не оглушайте их: log /lɔɡ/, solve /sɒlv/, involve /ɪnˈvɑlv/, bind /ˈbaɪ̯nd/, misread /mɪsˈɹiːd/

Как заниматься с этим видео

  1. Прослушайте всё видео один раз молча и выпишите незнакомые слова.
  2. Повторяйте предложение за предложением на обычной скорости, пока ваш ритм не совпадёт с ритмом говорящего.
  3. Запишите себя и сравните с оригиналом, обращая внимание на такие слова, как poison, token, database.

Что такое техника Shadowing?

Shadowing — это научно обоснованная техника изучения языка, изначально разработанная для подготовки профессиональных переводчиков и популяризированная полиглотом доктором Александром Аргуэльесом. Метод прост, но эффективен: вы слушаете аудио на английском от носителей языка и немедленно повторяете вслух — как тень, следующая за говорящим с задержкой в 1–2 секунды. В отличие от пассивного прослушивания или грамматических упражнений, Shadowing заставляет мозг и мышцы рта одновременно обрабатывать и воспроизводить реальные речевые паттерны. Исследования показывают, что это значительно улучшает точность произношения, интонацию, ритм, связную речь, понимание на слух и беглость речи — что делает его одним из самых эффективных методов для подготовки к IELTS Speaking и реального общения на английском.

Техника шедоуинга: читать полное пошаговое руководство →