Stories

Comment by esamust

Comment

Comment by esamust

Hi HN,

I'm esamust, the creator behind Aisir.

I built Aisir because I often found myself wanting multiple AI perspectives for complex coding/analysis tasks and was kind of frustrated by the blindspots of single models. So then the natural thing to try was, what if rather than just queueing each model in one go they actually talk to each other and work together to solve the problem.

Aisir uses a "council" approach where agents (currently Gemini, Claude Sonnet, o4-mini, WebSearcher (Gemini based)) deliberate on a query over a number of rounds. A moderator agent guides the discussion, chooses what to do next, identifies issues, and pushes for refinement before a final answer is synthesized. This is obviously overkill on simple queries but I would speculate (obviously biased) that it could beat price per token on the some very complicated queries vs like o1-pro as multiple models working together have a quicker way in token terms to find the right answer than a single model. This is based on my anecdotal experiments vs singular models.

So to explain, the difficult (and very limited) benchmarking I've done on it is using the epoch.ai FrontierMath examples to make sure the result would atleast not be worse than just using the best singular model but turns out it's more likely to answer correctly than any single model. This is slightly obvious in the sense that if a model can't answer one specific question, another one might be able to instead even if they don't talk to eachother. The next test would be to see if there are specific problems that none of the best models can answer individually but can be solved using this council method. Let me know if you find any by hand.

You can see the 'thinking' process unfold, showing each agent's contribution and the moderator's comments.

This is very much an experiment and currently free to use. Running these models is expensive over time, so if it gets traction, I might need to add limits/subscriptions later, but for now, I'm focused on seeing if the core idea is useful. I'd love to get your feedback, especially on: a) Does the multi-agent approach yield better results for you? b) What kinds of complex problems would this be most useful for? c) Any suggestions for improving? There's a lot of optimization I see with token spent etc but I want to see if this is interesting or valuable to anyone other than me.

Link to the tool: https://aisirai.com

Replies esamust · 2025-04-30
Open on HN
Loading the discussion…

Domain filters

Stories from these domains are hidden from every list. Subdomains match too: blocking substack.com also hides danluu.substack.com. Type a domain, or paste a link to block its site, and press Enter.

New collection

Delete this collection?

About YAVCHN

YAVCHN is a reader for Hacker News and Lobsters, with articles and discussions in separate windows or Classic pages.

Created by Paul Parks and built with PUDL.

YAVCHN source code on GitHub

Privacy policy · Terms of use

Help

Keyboard

j / k
Move down and up the story list. The arrow keys scroll whatever has focus.
Enter
Read the marked story in the article reader.
[ / ]
Read the story above or below in the list, in the same article reader. Back returns to the story you came from.
p
Pin or unpin the marked story, which keeps it in Pinned.
n / N
Move to the next or previous top-level comment in the window in front.
c
Collapse or expand that comment.
f
Hide or show the story list.
Esc
Close a menu or this help.
Access key m
Go to the menu bar. Most browsers take it with Alt on Windows and Linux, and Safari with Control and Option.
?
Show this help.

Windows

Each story opens in a window holding its article above its discussion; drag the bar between them to share the room differently. A window can be moved by its title bar, resized from any edge, snapped to a half or a corner by dragging it there, maximised, or minimised to the bar at the foot of the page. Use Window > New reader window to open an empty reader, or Story > Open in new reader window to open another reader for the current article. Docked readers keep their articles when you select another story from the sidebar. Minimized readers can be restored and reused for their site. A window's Previous and Next buttons read up and down the list in the same window.

A link in a comment or an article to another Hacker News or Lobsters thread opens that thread in a window too. A link to a single HN comment opens the comment above its replies.

While a story's window is in front, the Story and Discussion menus in the menu bar hold its commands: pinning, Previous and Next story, sorting, collapsing every thread, jumping to the first new comment. Each window also remembers where you were in its article and discussion, so a reload, or Back to a story that Next took you past, finds your place again. Closing a window forgets it.

The whole arrangement lives in the address, so a bookmark or a shared link brings it back, and Back undoes the last change. Moving between Hacker News, Lobsters, their lists, Pinned and Find changes only the list, and leaves the windows open.

The list

The pin at the start of a row keeps the story in Pinned, and the cross at its end hides it. Pinned can be narrowed by words in the title, site or author, by source, and to the stories you haven't opened yet, and ordered by when you pinned them, by points or by comments; the filters are part of the address, so a filtered view can be bookmarked. Scroll past the end of the list to load more. Domain filters, in the View menu, hide every story from a site.

Collections are named lists of stories. Story > Add to collection files the story in front into one or more of them, and the Collections feed shows them all or one at a time; the menu that chooses collections also creates, renames, and deletes them. A note is your own text on a story. Choose Add note in a story's toolbar to write one; it saves as you type. Rows with a note carry the note mark, and the Notes feed lists every noted story and searches the text of your notes.

Browsing view

View > Windowed and View > Classic select the browsing view and save your default in this browser. Window view reuses a reader for each feed. Classic view opens stories and applets as pages. Open as a page is a one-off action that does not change your saved default. Use the Windowed selector to return an article to a window. Direct page links always open as pages.

Applets

The Applets menu in the menu bar holds three tools, each a window of its own. Replies to me takes your Hacker News user name and lists the replies to your last thirty comments and stories, checking again every three minutes while it is open, and marking what is new since you last marked them read. Look up a user opens a profile on Hacker News or Lobsters, with their submissions and recent comments, as a commenter's name in any discussion does; the bar at the top of a profile looks up someone else in the same window, and Back returns to the one before. Who is hiring? filters the posts of HN's monthly hiring threads by the words you type.

They read only what the sites publish to everyone, so none of them asks for a login, and your user name stays in this browser anonymously and is included in retained applet state when signed in.

Find

Find takes any link and lists every time it was submitted to Hacker News and Lobsters, so you can read each discussion of it.

About

YAVCHN never sees your Hacker News or Lobsters login. The discussion is fetched from each site's public API; to vote or reply, follow the link above the discussion, or the arrow beside a comment, to the source's own site. Without a YAVCHN account, your data stays in this browser. When signed in, pins, collections, notes, blocked domains, and retained reading state are stored with your account and synchronized across devices. Hidden stories and layout stay in this browser. The privacy policy has the details.

Open source: github.com/paulmooreparks/yavchn. Built with PUDL.