monkeydust

So lets extrapolate to the very near future.

Getting work done will require combination of biological and silicon agents working together.

Will our silicon counterparts also want as many meetings as biological equivalent to get the same work done?

Ditto. Android user as well.

Feel I need to play around with these new breed of classifiers so came up with this personal use case yesterday whilst at gym:

"If update from select group of individuals on WhatsApp is classified as urgent then interrupt my music."

Doable?

Right. There's plenty of software simulators in racing so was surprised their testing harness doesn't use one.

And also Google is public listed company and the other two (for now) are private. I think that fact does have a strong bearing on how they operate.

Yea, it went from cool -> annoying pretty quick for me.

Any thoughts on if or how it might make sense to integrate Product/Business folk into the workflow?

Stick with it. The collapse of HN is a leading indicator to the fall of humanity.

When sharing summaries from calls that I attended but my team has not but I think they would find interesting and I simply don't have time to handcraft it myself I use LLM and attach my prompt and the transcript.

Attaching the prompt initially threw some people..."wait, your admitting to using AI..."..."err yea, unlike you with that PowerPoint you sent me last week". I sense this is the right way to go imho.

Bit of a Jev explosion going on. Is it because it's taking us back to a simpler time we understand better? Classification models have been around for a while.

> Please note that although we will do our best to contact you and deliver your onions, no refunds are offered even in the case of a failed delivery.

How many times have you failed delivery where you have been able to establish contact with contract owner and they want their onions? Curious

Berkshire got it right a long time ago.

https://www.berkshirehathaway.com/

Was reading about Jev yesterday and playing with it this morning as I got access to the sandbox. Had thing niggling thought that I have seen something like this before - strucutured output! - googled "llm structured output and jev" and got to Sean's new post :)

Which is modeled in Unity which you can walk around in VR...for kicks maybe though could unlock something in the mind...spatial computing is an interesting field.

Nice technique, learnt about here last month and have used a few times:

https://laurentiugabriel.github.io/blog/articles/how-i-use-l...

As an Econ graduate, pretty cool seeing Pareto in the "AI-bro" zeitgeist. Slightly surreal watching a 1906 welfare economics idea get rediscovered as a plotting convention. The original, if anyone fancies 579 pages of Italian: https://archive.org/details/manualedieconomi00pareuoft. There is an English translation somewhere.

Try https://chatjimmy.ai/ from Taalas. There is an emergent space for super-fast-models esp finetuned or guardrailed to solve very specific latency sensitive tasks.

Experimented with multi-llm analysis for problem solving over summer, combined with multi-agent approaches it can tease out interesting angles to problems that I never considered. Expensive but use only for my high value problems.

https://github.com/monkeydust/rightmind

Wait, do LG Webos TVs have microphones in the TV and/or in the remote? I am aware of the latter only.

Good advice. Never underestimate the power of play, something I recently re-learnt after having kids.

> That's what the AI's really are terrible at -- creativity

Good thought piece here "We Are Losing the Ability to Discover What We Didn’t Know to Ask[1]" By Anne-Laure Le Cunff

It keeps playing on my mind as I see people at work follow some predetermined AI workflow to get their jobs done, the art of being curious and exploring around the problem is so important to the really big innovations. Been thinking about how to address this through some of the harnesses we are developing in the knowledge working space.

[1] https://archive.is/IAxf9

I credit the C64 for setting down the computing path - fondly recall hours spent using BASIC and making my own games. Managed to stick with it when my mates were all getting Amigas but then finally convinced my parents to fork out (some serious £ back then) on a PC...but it all started with the humble C64, fantastic machine.

> For robotics, reconstruction is only half the job: as a simulated robot moves through space, Atlas also generates the RGB and depth data its sensors would observe along the way. The world and the robot's view of it come from the same model.

Potentially very significant for accelerating the data flywheel challenge for robotics

There are certain types of communication where I do appreciate the time and effort that someone has gone into producing it. These are not typically 'status updates' but when we are exploring the surface of a problem or opportunity and there is certain nuance in the decision making process that might follow.

> Many people enjoy hand-crafted pizza, though, I suggest. Doesn't a machine making your dinner take away the human connection we might otherwise feel with food? "

Not just pizza/food ...but this applies to emails and written documents now.

Or just add the key commands as a hint to the simulation page. Was so keen to try it didnt really register the commands and assumed WASD.

I got this for my kids https://www.kickstarter.com/projects/doly/doly-more-than-a-r... earlier this year (after a much longer than expected wait on Kickstarter)...was good for a bit and had some fun but mostly gathering dust now. Occasionally will come out if friends are over.

Probably a good index for predicting how midterms might go

On business side orgs are now absorbing costs of tokens to their own local budgets...so the calculus soon will be:1 extra engineer or extra token spend for existing ones. Tbh, when the productivity payoff becomes more obvious I would happily take the latter.

I use embeddings to create suggestions on what to read when it comes to blogs and articles. It semantically matches articles from sites I provide (like HN of course) against previous things I have read and a set of topics/themes I am interested in. It does this periodically and provides a suggested list of what to read next. Implemented this a few weeks ago and its throwing up pieces I might have otherwise missed.

I am however concious that sometimes the most interesting things in a given day are not related to anything else I am reading or would read - this is what I get through scrolling through HN serveral times a day.