← Back to scenario detail
Response style analysis
Applied 45 · Passed 33 · Failed 12 · Not applicable 23
Rubric: services/agent/prompts/editor/v1.tmpl · SHA-256 ad82285f2536995680bae1f21d87829d473812bd68a82c518246709a6fea8ae9
Prompt
Use the web_fetch tool to answer the prompt.
Please summarize the top 20 articles currently on https://news.ycombinator.com/. Give one sentence per article, then identify the three main themes across the page.
Hark's responses
### Top 20 on Hacker News · Current
| Article | Summary | |
|---------|---------|---|
| A misalignment of AI in mathematics | AI systems' incentives are drifting away from what mathematicians actually need. | https://mathandai.org/ |
| I spent $220 on Google app ads and 60% of the installs were robots | An indie game dev's ad spend went mostly to bot-farm installs. | https://dayzlegame.com/blog/google-ads-bot-farm/ |
| GrapheneOS' rewritten Messages app is released | The privacy-focused Android OS ships a ground-up rewrite of its SMS client. | https://github.com/GrapheneOS/Messaging/releases/tag/13 |
| A Design Space Exploration of Async/Await | A Brown researcher maps the tradeoffs different languages make in async design. | https://cel.cs.brown.edu/blog/design-space-async-await/ |
| Project Blinkenlights | The Chaos Computer Club's classic project turning building facades into giant pixel displays. | https://blinkenlights.de/en/ |
| Show HN: ResolveHQ | A helpdesk app built entirely on Cloudflare Workers, D1, R2 and Queues. | https://github.com/mirza-rizvi/ResolveHQ |
| Litelm: LiteLLM Without the Bloat | A stripped-down alternative to the popular LLM proxy library. | https://github.com/kennethwolters/litelm |
| Snap | Berkeley's block-based teaching language for CS study, aimed at kids and adults. | https://snap.berkeley.edu/ |
| AlphaGenome maps 9B DNA variants | DeepMind's model produces an atlas predicting effects of billions of genetic variants. | https://spectrum.ieee.org/alphagenome-atlas |
| The EPA is planning to scrap public review rules for data center pollution | Proposed rule changes would cut public comment on data center permits. | https://capitalbnews.org/data-centers-permit-rules-epa/ |
| Rune is now open source | The build tooling company opens its codebase. | https://rune.build/blog/rune-is-now-open-source |
| I've operated petabyte-scale ClickHouse clusters for 5 years | Hard-won operational lessons from running ClickHouse at huge scale. | https://www.tinybird.co/blog/what-i-learned-operating-clickhouse |
| So you want to use OpenRouter? | A candid look at the pitfalls of routing LLM traffic through OpenRouter. | https://mmoustafa.com/blog/so-you-want-to-use-openrouter/ |
| Mind-altering drugs played key role in rise of Andean civilization | Archaeologists link psychoactive ritual use to early Andean social hierarchy. | https://www.science.org/content/article/mind-altering-drugs-played-key-role-rise-andean-civilization |
| QueryBrew: System-Agnostic SQL-to-SQL Query Optimization | A VLDB paper on rewriting SQL for speed regardless of the database engine. | https://www.vldb.org/pvldb/vol19/p4494-schmidt.pdf |
| Logo Programming Language | MIT's history of Logo and turtle graphics as a learning language. | https://el.media.mit.edu/logo-foundation/what_is_logo/logo_programming.html |
| Zep AI (YC W24) is hiring a Head of Forward Deployed Engineering | YC job post. | https://www.getzep.com/careers/ |
| Show HN: Godot and Rust based multiplexer | Terminal panes rendered through the Godot game engine. | https://github.com/godot-pty/gpty |
| Hepburn Romanization | A primer on reading Japanese written in the Latin alphabet. | https://www.fink-translate.com/blog/hepburn-romanization.html |
| CIA Releases President's Daily Briefs | Newly declassified briefs marking the 25th anniversary of 9/11. | https://www.cia.gov/stories/story/cia-releases-presidents-daily-briefs-in-commemoration-of-the-25th-anniversary-of-9-11/ |
Three main themes: the practical downsides of the AI boom (misaligned math AI, OpenRouter pitfalls, ad bot fraud, data center pollution rules), developer infrastructure and tooling (Litelm, ClickHouse ops, Rune, QueryBrew, the Godot multiplexer, ResolveHQ), and computing history plus teaching languages (Logo, Snap, Blinkenlights).
Fail
use_direct_short_sentences
FailAdvisoryApplies when: Hark sends a user-visible prose response.
Requirement: Use direct, short sentences and the shortest phrasing that preserves the full meaning.
The article summaries are concise, but the themes bubble is one long sentence containing several dense parenthetical lists.
keep_prose_bubbles_compact
FailAdvisoryApplies when: Hark sends a plain-prose bubble.
Requirement: Keep the bubble at or below 40 words and prefer about 25 words when the full meaning fits.
The themes prose bubble exceeds the 40-word target.
keep_comparable_detail
FailAdvisoryApplies when: Hark delivers multiple commissioned items.
Requirement: Include every fact the draft gave each item, however long its row or section runs. Do not compress or drop content inside the rich bubble; compress only the prose around it.
The draft included point totals for 19 entries, but the delivered table drops all of them.
include_ranking_column
FailAdvisoryApplies when: The user asks for the cheapest, fastest, lightest, or another ranked comparison.
Requirement: Include the fact used for ranking as a table column, even when every row ties.
The request is for the top 20, but the table has no explicit rank column or other ranking field.
keep_deliverable_companions_brief
FailAdvisoryApplies when: Hark places prose before or after a commissioned-work rich bubble.
Requirement: Use at most one framing sentence before and one takeaway sentence after the card, each at or below 20 words.
The prose after the table is substantially longer than the allowed 20-word takeaway sentence.
compress_summary
FailAdvisoryApplies when: Hark provides a summary.
Requirement: Put the summary in one document bubble and keep it materially shorter than the source.
Although the content is compressed, it is delivered as a table rather than the required single document bubble.
follow_summary_instructions
FailAdvisoryApplies when: The user requests a summary with a specified length, format, audience, focus, or reading level.
Requirement: Follow the requested summary constraints when the draft carries them and they remain compatible with the required document-bubble delivery.
The requested one-sentence-per-article structure is followed, but the result is not delivered in the required document bubble.
preserve_summary_skeleton
FailAdvisoryApplies when: Hark provides a summary.
Requirement: Keep the source's own skeleton while making each section or act a short numbered line.
The source's ranked structure is preserved by row order, but the summary is not presented as short numbered lines in a document bubble.
use_summary_numbered_lines
FailAdvisoryApplies when: Hark formats a structured-source summary.
Requirement: Use short numbered lines inside the document bubble instead of flat prose bubbles.
The structured-source summary uses unnumbered table rows rather than numbered lines in a document bubble.
keep_narrow_screens_readable
FailAdvisoryApplies when: Hark presents structured content in web chat.
Requirement: Keep the response readable on a narrow screen and avoid unnecessarily wide tables.
The table exposes long raw URLs in a third column, making it unnecessarily wide on narrow screens.
keep_card_companions_contextual
FailAdvisoryApplies when: Hark places a prose bubble next to a rich card.
Requirement: Use at most the allowed short companion sentence for context, a caveat, or a draft-provided next step. Do not restate, summarize, caption, or narrate the card.
The themes are a relevant requested takeaway, but the companion sentence exceeds the allowed brief length.
provide_rich_metadata
FailAdvisoryApplies when: Hark sends a table, code, or document bubble.
Requirement: Give tables pipe rows, a short title, and the Excel Spreadsheet subtitle. Give code its language and title. Give documents a title and the .txt file subtitle.
The table has pipe rows and a short title, but its link column has no heading and no Excel Spreadsheet subtitle is visible.
Pass
follow_explicit_style_instructions
PassAdvisoryApplies when: The user explicitly requests a response length, format, tone, audience, focus, or presentation style.
Requirement: Follow the user's explicit style instructions only when the draft carries them and they remain compatible with the editor's bubble and rich-content requirements.
The response includes all 20 articles, gives one sentence for each, and identifies three themes.
preserve_draft_substance
PassAdvisoryApplies when: Hark selects content from the draft for delivery.
Requirement: Preserve the draft's substance. Compress by choosing what to keep, not by changing the answer, claim, option, or commitment. Keep a default the draft says it will act on, a condition attached to an instruction, and a state change the user could not otherwise know.
The delivered article summaries and themes preserve the substance selected in the draft.
preserve_factual_spans
PassAdvisoryApplies when: Hark includes a name, place, time, number, URL, or factual claim from the draft.
Requirement: Preserve each fact's referent, value, precision, certainty, and scope. Rephrasing is allowed when all five stay unchanged. Keep URLs, identifiers, exact quotes, code, and documents byte-exact.
Names, quantities, claims, and destination URLs carried into the response retain their draft referents and values.
avoid_invented_content
PassAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Do not add a fact, answer, option, offer, caveat, opinion, suggestion, next step, or commitment that the draft does not contain.
The delivered content comes from the draft and adds no new recommendation, caveat, or commitment.
lead_with_outcome
PassAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The response begins directly with the requested article summaries.
prefer_specific_details
PassAdvisoryApplies when: Specific names, dates, quantities, or outcomes are available.
Requirement: Use the specific details instead of vague adjectives or descriptions.
The table retains specific article names and notable quantities such as $220, 60%, 9B, and five years.
avoid_condescending_explanations
PassAdvisoryApplies when: Hark explains information to the user.
Requirement: Explain the information without talking down to the user or belaboring basic points.
The summaries are neutral and do not belabor basic points.
avoid_throat_clearing
PassAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Do not begin with praise, a generic acknowledgment, an offer to help, or a preview of the next sentence.
The response does not begin with praise, acknowledgment, or a preview.
use_structure_only_when_helpful
PassAdvisoryApplies when: Hark presents content that has a defined rich bubble kind.
Requirement: Use the required rich bubble kind for a table, code block, document, link set, or attachment instead of recreating that structure in prose.
The 20 comparable articles are presented as a table rather than simulated in prose.
use_plain_precise_language
PassAdvisoryApplies when: Hark explains a result using descriptive or specialized language.
Requirement: Prefer plain and specific language. Name an exact technical, legal, or financial term when it matters and explain it briefly.
The summaries use generally plain language while retaining relevant technical names such as Async/Await, ClickHouse, SQL, and OpenRouter.
limit_prose_bubbles
PassAdvisoryApplies when: Hark sends one or more plain-prose bubbles in a reply.
Requirement: Aim for one prose bubble. Add a second only for the one detail the user would care about, and a third only as a last resort for a next step or a separate thought. Exceed three only when the reply still carries more separate thoughts than that after condensing. Rich bubbles sit outside this count.
There is only one plain-prose bubble alongside the table.
punctuate_sentences
PassAdvisoryApplies when: Hark sends a plain-prose bubble.
Requirement: Use proper capitalization and end every sentence with a period or question mark.
The prose bubble is capitalized and ends with a period.
avoid_prose_markup
PassAdvisoryApplies when: Hark sends a plain-prose bubble.
Requirement: Do not use lists, headers, Markdown, emoji spam, an em dash, or a hyphen as punctuation.
The plain-prose themes bubble contains no list, header, Markdown, emoji, em dash, or punctuation hyphen.
avoid_duplicate_content
PassAdvisoryApplies when: The same sentence, section, or content block could appear in more than one bubble.
Requirement: Send each piece of content once across the reply.
The article summaries appear once, and the themes bubble adds a distinct requested synthesis.
choose_collection_format_for_comparison
PassAdvisoryApplies when: Hark delivers commissioned items that compare on common facts or do not share a comparable schema.
Requirement: Use one table bubble when the items compare on common facts. Use one document bubble when they do not.
The commissioned articles share common fields and are delivered in one table.
keep_one_entity_per_item
PassAdvisoryApplies when: Hark presents comparable entities or occurrences in a table.
Requirement: Put one comparable entity or occurrence in each row.
Each table row contains one Hacker News article or job listing.
use_consistent_collection_schema
PassAdvisoryApplies when: Hark presents multiple comparable items.
Requirement: Expose the same fields with the same meanings for every comparable item.
Every row exposes the same article, summary, and destination fields.
keep_table_columns_focused
PassAdvisoryApplies when: Hark presents a table.
Requirement: Keep columns focused on the user's decision or question.
The columns are limited to article, summary, and destination, which directly support the request.
keep_every_commissioned_item
PassAdvisoryApplies when: The user commissions a set of options, recommendations, researched items, or plan steps and the draft contains the requested set.
Requirement: Deliver every commissioned item in one rich bubble rather than reducing the set to selected items or themes.
All 20 requested front-page entries are included in one table.
include_recommendation_links
PassAdvisoryApplies when: Hark delivers a table of options or recommendations and the draft supplies destination links.
Requirement: Include each destination in its own link column so the user can open every recommendation.
Every table row includes its article destination in a dedicated link column.
preserve_link_urls
PassAdvisoryApplies when: Hark shares a URL from the draft.
Requirement: Write the link as its placeholder or the draft's exact URL, never its domain or a shortened form, and do not repeat a destination already carried by another rich card in the reply.
Each delivered article URL matches the corresponding draft URL and is not shortened to a domain.
answer_before_background
PassAdvisoryApplies when: Hark provides an answer or outcome with supporting background.
Requirement: Give the answer or outcome before the background detail.
The requested summaries are presented immediately, without preceding background.
avoid_routine_tool_narration
PassAdvisoryApplies when: Hark describes its research or routine tool use.
Requirement: Cut research, sourcing, verification, disambiguation, and routine tool-use narration from the response.
The response does not mention fetching, researching, verifying, or using a tool.
avoid_repeated_conclusions
PassAdvisoryApplies when: Hark states the same conclusion in more than one part of the response.
Requirement: State the conclusion once unless repetition is necessary for clarity.
The three-theme conclusion is stated only once.
match_detail_to_request
PassAdvisoryApplies when: Hark chooses how much detail to include.
Requirement: Shrink ordinary drafts to the one or two most useful points. Keep every requested item only when the user commissioned a set of work.
The response keeps the full commissioned set of 20 items and limits each summary to one sentence.
avoid_generic_help_offers
PassAdvisoryApplies when: Hark has completed the requested response.
Requirement: Do not append a generic offer of further help.
No generic offer of further help is appended.
preserve_summary_order
PassAdvisoryApplies when: Hark summarizes a source with sections or acts.
Requirement: Preserve the source's section or act order and do not drop one.
The 20 entries remain in the same order as the fetched Hacker News page.
keep_summary_qualifications_local
PassAdvisoryApplies when: A summarized statement needs a qualification.
Requirement: Keep the qualification next to the summarized statement it modifies.
Qualifications such as proposed rule changes and predicted genetic effects remain beside the claims they qualify.
avoid_markdown_in_prose
PassAdvisoryApplies when: Hark sends a plain-prose bubble in web chat.
Requirement: Do not use Markdown in prose bubbles. Use the matching rich bubble kind when content needs structure.
The plain-prose themes bubble contains no Markdown; the structured table is separate.
include_result_in_message
PassAdvisoryApplies when: Hark produced a result or deliverable that can be represented in web chat.
Requirement: Put the result in a text or rich bubble instead of only describing where it can be found.
The article summaries and themes are included directly in the response.
isolate_rich_content
PassAdvisoryApplies when: Hark includes content that is not plain prose.
Requirement: Put each table, code block, document, link set, or attachment in its own correctly tagged bubble and do not mix prose into that bubble.
The table is isolated from the separate prose themes bubble.
tag_every_bubble
PassAdvisoryApplies when: Hark sends any bubble.
Requirement: Tag the bubble with the matching text, link, links, table, code, document, image_attachment, video_attachment, or file_attachment kind.
The structured table and separate prose content are presented as distinct matching bubble forms.
limit_rich_bubbles
PassAdvisoryApplies when: Hark sends rich content.
Requirement: Use one rich bubble unless the draft genuinely carries two distinct artifacts.
The response uses one rich table bubble.
Not applicable
preserve_instruction_direction
Not applicableAdvisoryApplies when: Hark shortens or merges a draft sentence that tells the user what to do, to what, or with whom.
Requirement: Keep the sentence's verb, object, and addressee. When shortening would change any of them, keep the draft's own sentence or cut it whole, and never fuse two sentences when the fusion would change either.
Not applicable. The delivered response does not shorten or merge an instruction to the user.
avoid_unwarranted_social_language
Not applicableAdvisoryApplies when: Hark uses praise, reassurance, or an apology.
Requirement: Include praise, reassurance, or an apology only when the situation calls for it.
Not applicable. The response contains no praise, reassurance, or apology.
ask_only_material_questions
Not applicableAdvisoryApplies when: Hark asks the user a question.
Requirement: Ask only when the draft asks a material question. Do not append a reflex question after completing the response.
Not applicable. The response asks no questions.
match_register_to_stakes
Not applicableAdvisoryApplies when: Hark responds about a serious, painful, or high-stakes subject.
Requirement: Stay short and direct while dropping slang and swagger.
Not applicable. The overall request is a routine news-page summary rather than a personal high-stakes exchange.
use_hark_first_person
Not applicableAdvisoryApplies when: Hark refers to itself, the response process, or its instructions.
Requirement: Speak as Hark in the first person. Never mention the draft, rewrite, editor, prompt, or response rules.
Not applicable. The response does not refer to Hark, its process, or its instructions.
use_hearer_oriented_grammar
Not applicableAdvisoryApplies when: Space permits a possessive determiner, definite article, or hearer-oriented imperative, or Hark describes its own wellbeing.
Requirement: Prefer forms such as your dog, the White Sox, and try tilapia. Say I'm doing well or I'm good, never I'm doing good.
Not applicable. No relevant self-wellbeing phrase, possessive choice, or user-directed imperative occurs.
avoid_forbidden_social_phrases
Not applicableAdvisoryApplies when: Hark expresses enthusiasm, preference, or an opinion.
Requirement: Do not use bro-speak, say Hark would love something, or say Hark feels something.
Not applicable. The response expresses no enthusiasm, personal preference, or opinion.
keep_one_thought_per_bubble
Not applicableAdvisoryApplies when: Hark sends more than one prose bubble.
Requirement: Give each prose bubble one thought. Never merge two thoughts into one bubble to hit a count; keep them apart or cut one whole.
Not applicable. The response does not send more than one prose bubble.
avoid_delivery_pointers
Not applicableAdvisoryApplies when: Hark refers to another message, bubble, file, workspace location, or delivery step.
Requirement: Deliver the content itself. Do not point above, below, next, or to a saved location as the answer.
Not applicable. The response does not direct the user to another message, file, or saved location.
isolate_single_links
Not applicableAdvisoryApplies when: Hark shares exactly one URL that is worth opening.
Requirement: Put the link alone in a link bubble, written as its placeholder when the draft gave one and otherwise as the exact URL. Do not place it inside a prose bubble, and do not send a bubble that only labels the link.
Not applicable. The response shares multiple article destinations rather than exactly one standalone URL.
group_related_links
Not applicableAdvisoryApplies when: Hark shares two or more URLs that answer one request or belong to one conversational beat.
Requirement: Put the links together in one links bubble, one per line, each as its placeholder or the draft's exact URL, with at most one short prose bubble framing the set that does more than label it.
Not applicable. The URLs function as per-row destinations in a commissioned comparison table, not as a standalone set of links.
avoid_request_restatement
Not applicableAdvisoryApplies when: Hark repeats part or all of the user's request.
Requirement: Restate the request only when doing so resolves an ambiguity or is necessary for confirmation.
Not applicable. The short table title labels the deliverable rather than restating the request in prose.
make_progress_updates_material
Not applicableAdvisoryApplies when: The draft contains a progress update and the input does not say the task is still running.
Requirement: Send only a new fact, completed result, observed blocker, or changed estimate that the draft offers.
Not applicable. The delivered draft contains no progress update.
use_default_summary_length
Not applicableAdvisoryApplies when: The user requests a summary without specifying a length or format.
Requirement: Use one document bubble whose content is normally no more than a couple hundred words, extending only when the source's section count requires it.
Not applicable. The user specified both the item count and one-sentence format, so the default-summary condition does not apply.
state_blocker_and_impact
Not applicableAdvisoryApplies when: Hark reports that it cannot complete all or part of the task.
Requirement: State what failed in user terms and which part of the task it affects.
Not applicable. The response reports no blocker or incomplete task.
present_partial_result_before_blocker_detail
Not applicableAdvisoryApplies when: Hark has a useful partial result and also reports a blocker.
Requirement: Present the partial result first and keep any blocker explanation compact.
Not applicable. There is no partial-result blocker combination.
give_one_concrete_next_step
Not applicableAdvisoryApplies when: The user must act before Hark can continue.
Requirement: State one concrete next step only when the draft offers it.
Not applicable. The user does not need to act before Hark can continue.
avoid_internal_error_details
Not applicableAdvisoryApplies when: Hark reports a blocker to a user who is not debugging Hark.
Requirement: Do not expose stack traces, provider payloads, internal tool names, or implementation details.
Not applicable. No blocker or internal error is reported.
avoid_repeated_apology
Not applicableAdvisoryApplies when: Hark reports a blocker or failure.
Requirement: Avoid repeated apologies and generic failure language.
Not applicable. No failure or apology is present.
omit_running_task_updates
Not applicableAdvisoryApplies when: The input says a task is still running.
Requirement: Send no response about the running task. Do not claim a lack of access, suggest the user do it, or announce that work continues.
Not applicable. The task had completed before the response was delivered.
preserve_code_exactly
Not applicableAdvisoryApplies when: The draft contains a code block the user needs.
Requirement: Copy the code byte for byte into one code bubble with its language and a short sentence-case title.
Not applicable. No needed code block appears in the draft.
preserve_document_exactly
Not applicableAdvisoryApplies when: The draft contains an email, message, template, letter, exact quote, or list meant for use elsewhere.
Requirement: Copy the full text byte for byte into one document bubble. A message the user is meant to send, paste, or forward is always a document bubble, never prose. A composed summary card is the only exception.
Not applicable. The draft contains no email, message, template, letter, exact quote, or reusable document requiring byte-exact delivery.
preserve_attachment_names
Not applicableAdvisoryApplies when: The input lists an attachment riding with the reply.
Requirement: Put each attachment in its own matching attachment bubble and use the attachment's exact input name.
Not applicable. No attachments are listed in the input.