monkeydust

Would love to see a load/unload dishwasher benchmark.

I recently created a video and didn't want to use my voice on it.

Rather than TTS I did STS (speech to speech) through Eleven Labs (you upload the video it alters the audio track to voice of choosing with some parameters you can control).

I showed it to a bunch of people and they could not believe it was non-human. The bit that got most was all the pausing, broken sentences ...essentially elements you don't put into text if your doing T2S.

An LLM over the original text could perhaps inject these elements though if prompted correctly.

Where is a good place to start with training SLM these days if you don't have the compute locally?

'Intelligence is what you do when you don't know, -> came up somewhere, I think on LinkedIn but stuck in my head.

Don’t Win the Argument, Profit From the Difference

Best section for me. Many times I have taken the contrarian view. It doesn't always work, I do get it wrong (fail fast) but when it goes right you earn virtual credit against the person whom you took the opposing view. Its not something tangible but its there and the next time you lock horns they remember.

Very cool. Recommend walking through the curated story here first then exploring the menu visualization

https://pudding.cool/2026/06/menu-story/

Whats peoples thoughts on Tenstorrent - they were looking for funding on Hiive recently but that deal got pulled when Qualcomm rumours surface a week or so ago.

I only use this for high value problems/challenges. A lot related to life decisions including work, where to live, finances etc. It gives me a small army that can break down and slice, dice the problem in different ways then someone to reconcile it all and present it back to me. The variance in their opinions is the most interesting part of this project so f ar.

the tax exemptions make it very attractive place to hold cash versus bank accounts - if your a UK citizen google (or AI) - low coupon gilt investing.

I think ...or hope...he ends more right than left and manages to do what Starmer failed to do a year ago which is to make major reforms to the Welfare system. Its just not sustainable.

yea for sure :)

Signup link here

-> https://ets-connect.co.uk/users/prod-onboarding/

Commercials here:

-> https://ets-connect.co.uk/annual-fees-2026-2027/

Imho there are two dimensions here: Firstly different LLMs and secondly the strategy in which you break down the problem in an agentic fashion (e.g. break up to separate agents with own persona and then judge evaluates across all agents). You can of course mix-up the dimensions as well and that's what I have been tinkering* with for a good few months with some success. This was all done using home-brew setup running on openrouter.

Personally I prefer understanding the dimensions and the interplay and controlling it though can see why openrouter and others are now offering this a solved solution.

Just be careful when you start outsourcing too much of your intelligence needs to a blackbox.

* https://github.com/monkeydust/rightmind

I wouldn't underestimate the community effect of software. There are plenty of features that get shipped because a small but important minority requested them, only to benefit the long tail of users who never knew to ask for such a feature but now find it indispensable. If everyone is building their own isolated solutions, how does this positive externality manifest itself?

If you ask people to rank say 5 things from top to bottom where the first thing at the top is what they are least cost conscious about and the one at bottom is what they are most - I would bet health would at the top slot for most of us. So relatively we would spend (whatever we have) on our health versus other things if we had conviction on the outcome.

I have been experimenting with multi-agent llms for last month, as I put in the writeup for my repo and in the video the biggest value I have found is when you run a bunch of different agentic strategies in parallel then have a judge review the variance of them. So far that has uncovered interesting insights. The rest of it is so-so. Been fun but also expensive!

Repo with video: https://github.com/monkeydust/rightmind

Multi Agent setup to tackle complex problems using the diversity of multiple LLMs. All for personal use but finding it very useful especially what I call the 'all angles' where it runs multiple strategies parallel then a judge agent presents summary including a view on how the strategies agreed and diverge from one another.

Repo with video: https://github.com/monkeydust/rightmind

Don't know but could BOINC setup which has been around for ages and mature plus has some incentive mechanism (Gridcoin) be used for this?

AI has collapsed the cost of producing content while leaving the cost of reviewing, verifying higher imho. This has inverted the economics of collaboration. Reviewer attention, not output volume, is now the scarce resource, this happened with my engineering teams (PR reviews) and is now happening in my world in Product.

Details and repo post on ShowHN here - https://github.com/monkeydust/rightmind

Right here is the video demo of what I built - https://streamable.com/e49cgt

Sure let me do that. Can I post this as a ShowHN if its just video? The rules say people need to try out but that will cost me a small fortune :) ...could perhaps post on Github and people can setup the repo themselves with their own Openrouter key if that works. Have never done a ShowHN but would be fun to try it.

Homebrew harness and all frontier ones plus deepseek. All via Openrouter at the moment. Works well enough but can get expensive so use for real high value challenges. Interestingly the refine feature has been most useful to me and people I have shown, essentially people are lazy when expressing the initial problem (me included!), refine asks relevant questions to initial problem then refines the initial statement, user can accept/reject/edit before submitting.

I have a MA system setup for personal use.

You give it a problem, you then refine that problem where a fast, cheaper model asks you questions which you answer to get a better input prompt. You then choose a MA strategy for example take problem break up to sections then final judge concludes or you do multi turn where agents debate then judge summarises debate.

The best approach is what I call 'all angles' where all these strategies run in parallel the final meta-judge synthesise the response - the most useful part of this which I recently added is a view to see the variance in each strategy.

Been using this for life stuff - housing search, schools, family challenges!

Perhaps I should make a video of it in action if people in HN community interested let me know.

Same, you can instruct it specifically to look non-standard and give it examples of website styles I want. After some wrangling it feels a bit more creative but takes prompting.

Does it matter though.

So if I have a problem with my telecom provider and I want to get it solved asap, I'd the AI can do this just as effectively as a human operator isnt that OK?

The article pretty much plays out whats happening in our place, heavy use of AI in software development but we dont see us shipping faster, about same or perhaps slower (for other reasons). Its a weird feeling as were waiting for this utopia to kick-in but its not and were cant fully put our fingers on it.

These guys have been around for a while, anyone have practical experience/exposure to using their technology for heavy enterprise workloads?

This does feel like where things should be going for more natural human-AI interaction patterns. Nice write up and demos.

If people were incentivized to solve problems with least amount of token spend that would help.

Somewhat ironic is that people are using them to create generic web apps like they are going out of fashion.