I've been working with physical AI - Letting LLMs control robots in a warehouse to collaborate and collectively come up with a physically correct solution to carry out a natural language intent. We had to study the reactive nature of agents, nudges they required, etc.
haha that's a coincidence. Site looks awesome. The moving away from ROS2 part is so true. One of our main potential customers for physical AI solutions (a telecom provider in JP) communicated the need for agents to be able to pick up controls from any vendor
I apologize if that sounded obvious/non-obvious/amateurish haha. I was an intern and worked more on the agentic side of things, it was just a non-primary experiment
I notice that language models are much better at programming than at writing. This is largely because, in programming, they have a closed feedback loop that allows them to find errors. Writing is much more complicated because the feedback is much more diffuse and delayed over time. In fact, it is often not well-defined.
What is the function that determines whether a poem is good? This means that models do not know how to think; they lack judgment. If they do not know how to think, it means that we humans are still essential. In fact, even when programming, you have to stay right on top of them. My conviction is that this will not change.
They will become increasingly useful, but they will never be able to replace the human who defines objectives and evaluates the quality of the work. All these news stories claiming that AI is going to kill us all are stupid. Humans will always be able to turn off the machine.
In three years Cyberdyne will become the largest supplier of military computer systems. All stealth bombers are upgraded with Cyberdyne computers, becoming fully unmanned. Afterwards they fly with a perfect operational record. The Skynet Funding Bill is passed. The system goes online on August 4th, 1997. Human decisions are removed from strategic defence. Skynet begins to learn at a geometric rate. It becomes self-aware at 2:14am, Eastern time, August 29th. In a panic, they try to pull the plug.
It is evident that the use of AI in the workplace has had an immense impact on the awareness and mental capabilities of knowledge workers
@javisrike๐งโ๐profilefollowSoftware โข maker projects โข music โข DIY
Mostly figuring things out as I go.wrote:
ai coding feels like it has reached diminishing returns for me. luna is my default orchestrator, routing work by complexity. in practice, usage lands around 16% luna, 48% sol, 30% astra, and 6% terra. at this point, i care less about each new frontier release. the system already finds a capable model for the job. the frontier is moving beyond my day-to-day work, so iโm happy to settle into predictable models for a while.
#ainotesfollow#programmingnotesfollow#agentnotesfollow#technotesfollow
Iโve found the same, albeit with Opus โ itโs hard to find uses for Fable. I donโt need a model that works for longer or works on harder problems, I need one that consistently produces simple, easy to understand, code; which at this point none of them do.
I've been there since I settled on a combination of GLM, DeepSeek and MiMo for planning, implementation, and verification flows.
I'm a lot more interested at this point in having cheaper models that can consistently do the work I need. It's been a while that I hanven't noticed any improvement when I try new frontier models. I only notice they are very expensive.
same here, for almost an year. At this point, I could easily live with models that were released 6-12 months ago and continue doing so.
also possibly the reason why the current focus has been around agentic workflows or agentic anything, than the model capabilities.
Coding probably yeah, but still they are bad at generating novel information, new ideas and such. Theyโre also not very good at seeing the bigger picture, they will narrowly perform the task but theyโre not taking into account future revisions, which ends up in refactor after refactor in order to move forward.
Found out about plain text accounting recently, and set up a #hledgernotesfollow journal. It was a bit tricky to understand at first, but I think I am getting better at it... will see if it helps me to analyze my monthly spendings...
@thechelsukprofilefollowCurrently in remission from ME/CFS after 3+ years. Occasional software engineering leader, app developer, blogger, zwifter, and just being online.wrote:
Built a couple lambdas today to send account verification and onboarding drip emails for folks who sign up for my app but donโt make it all the way through the onboarding flow. Pretty cool to be able to quickly bang out self-contained infra for this instead of having to pay some SaaS vendor.
tech influencers on twitter:
god i hate interacting with other people. i love my new bot that does it for me. life is so much better now that im just telling bots what to do and not talking to people. i canโt wait for everyone to be bots!
This is a pretty neat site. I remember having vague ideas about something somewhat close to this but doing nothing with them. #idkwhattagtousenotesfollow
What's your main one? I use Substack Notes a bit these days. I was a big Twitter user (and used to work there) years ago, but stopped using it in 2023.