HackerTrans
TopNewTrendsCommentsPastAskShowJobs

rjakob

no profile record

Submissions

OpenTSLM: Language models that understand time series

opentslm.com
280 points·by rjakob·hace 10 meses·80 comments

Show HN: AI Peer Reviewer – Multiagent system for scientific manuscript analysis

github.com
108 points·by rjakob·el año pasado·95 comments

comments

rjakob
·hace 10 meses·discuss
It’s less about proof and more about demonstrating a new capability that TSLMs enable. To be fair, the paper did test standard LLMs, which consistently underperformed. @iLoveOncall, can you point to examples where out of the box models achieved good results on multiple time-series? Also, what kind of time-series data did you analyze with Claude 3.5? What exactly did you predict, and how did you assess reasoning capabilities?
rjakob
·hace 10 meses·discuss
Thanks for the note. Ironically, the post is about models built to understand time.
rjakob
·el año pasado·discuss
If you know the trick to getting reviewed in a day, do tell. Asking for an entire field.
rjakob
·el año pasado·discuss
inspired by friends at Browser-Use
rjakob
·el año pasado·discuss
whenever you would like to have comprehensive feedback on your manuscript (more likely during pre-submission or after publishing a preprint).
rjakob
·el año pasado·discuss
noted.
rjakob
·el año pasado·discuss
We also provide feedback on rigor across 7 different categories: https://github.com/robertjakob/rigorous/tree/main/Agent1_Pee...
rjakob
·el año pasado·discuss
System prompts / review criteria cannot be "leaked" because they are open-source (full transparency). Focusing heavily on monetization at this stage seems shortsighted...this tool is a small (but longterm important) step of a larger plan.
rjakob
·el año pasado·discuss
As mentioned above, there is an open-source version for those who want full control. The free cloud version is mainly for convenience and faster iteration. We don’t store manuscript files longer than necessary to generate feedback (https://www.rigorous.company/privacy), and we have no intention of using manuscripts for anything beyond testing the AI reviewer.
rjakob
·el año pasado·discuss
Then let's try to be the least biased and fully transparent (which should also help with bias)
rjakob
·el año pasado·discuss
Here is a description of how it works: https://github.com/robertjakob/rigorous/tree/main/Agent1_Pee...
rjakob
·el año pasado·discuss
Best feedback so far!

You're right: In the current version each "agent" essentially loads the whole paper, applies a specialized prompt, and calls the OpenAI API. The specialization lies in how each prompt targets a specific dimension of peer review (e.g., methodological soundness, novelty, citation quality). While it’s not specialization via architecture yet (i.e., different models), it’s prompt-driven specialization, essentially simulating a review committee, where each member is focused on a distinct concern. We’re currently using a long-context, cost-efficient model (GPT-4.1-nano style) for these specialized agents to keep it viable for now. Think of it as an army of reviewers flagging areas for potential improvement.

To synthesize and refine feedback, we also run Quality Control agents (acting like an associate editor), which reviews all prior outputs from the individual agents to reduce redundancy and surface the most constructive insights (and filter out less relevant feedback).

On your point about nitpicking: we’ve tested the system on several well-regarded, peer-reviewed papers. While the output is generally reasonable and we did not discover "made up" issues yet, there are occasional instances where feedback is misaligned. We're convinced, however, we can almost fully reduce such noise in future iterations (Community Feedback is super important to achieve this).

On the code side: 100% agree. This is very much an MVP focused on testing potential value to researchers, and the repeated agent classes were helpful for fast iteration. However, your suggestion of switching to template-based prompt loading and dynamic agent registration is great and would improve maintainability and scalability. We'll 100% consider it in the next version.

The _determine_research_type method is indeed a stub. Good catch. Also, lol @ the JS comment hashes, touché.

If you're open to contributing or reviewing, we’d love to collaborate!
rjakob
·el año pasado·discuss
We are already looking into that: https://github.com/robertjakob/rigorous/tree/main/Agent2_Out...

Would be great to see contributions from the community!
rjakob
·el año pasado·discuss
...or run it themselves. The code is open source: https://github.com/robertjakob/rigorous

Note: The current version uses the OpenAI API, but it should be adaptable to run on local models instead.
rjakob
·el año pasado·discuss
https://www.rigorous.company/privacy
rjakob
·el año pasado·discuss
Cool! We'll get back asap.

We'd be happy to hear what kind of feedback you find useful, what is useless, and what you would want in an ideal review report. (https://docs.google.com/forms/d/1EhQvw-HdGRqfL01jZaayoaiTWLS)
rjakob
·el año pasado·discuss
Wouldn't that just require a robust, predefined ruleset we could all agree on? Let's make the dream come true!
rjakob
·el año pasado·discuss
We honestly didn’t think much about the term “AI peer reviewer” and didn’t mean to imply it’s equivalent to human peer review. We’ll stick to using “AI reviewer” going forward.
rjakob
·el año pasado·discuss
I wish my own manuscripts would be that important...

Regarding security concerns: there is an open-source version for those who want full control. The free cloud version is mainly for convenience and faster iteration. We don’t store manuscript files longer than necessary to generate feedback (https://www.rigorous.company/privacy), and we have no intention of using manuscripts for anything beyond testing the AI reviewer.
rjakob
·el año pasado·discuss
Thanks for the thoughtful feedback. That’s very helpful.

We didn’t think too deeply about the term “AI peer reviewer” and didn’t mean to imply it’s equivalent to human peer review. Based on your comments, we’ll stick to using “AI reviewer” going forward.

Regarding security: there is an open-source version for those who want full control. The free cloud version is mainly for convenience and faster iteration. We don’t store manuscript files longer than necessary to generate feedback (https://www.rigorous.company/privacy), and we have no intention of using manuscripts for anything beyond testing the AI reviewer.

On novelty. totally agree it’s a core part of good peer review. The current version actually includes agents evaluating originality, contribution, impact, and significance. It’s still v1 of course but we want to improve it. We'd actually love for critical thinkers like you to help shape it. If you're open to testing it with a preprint and sharing your thoughts on the feedback, that would be extremely valuable to us.

Thanks again for engaging, we really appreciate it.