HNHacker News
TopNewBestAskShowJobs

carsoon

120 karma · joined February 3, 2024

submissionscomments
carsoon··on Vintage Large Language Models
We need a library of Alexandria for primary sources. If we had source transparency then referencing back to original sources would be more clear. We could do cool things like these vintage models to reduce bias from current events. Also books in every language and books for teaching each language would help with multimodality. Copyright makes it difficult to achieve the best results for LLM creation and usage though.
carsoon··on Vintage Large Language Models
Using old models is a good way to received less biased information about an active event. Once a major event occurs information wars happen that try and change narratives and erase old information. But because models were trained before this the bias that the event causes is not yet present.
carsoon··on Three kinds of AI products work
Recent articles seem only to mean LLMs when they reference AI. There are tons of commercial usecases for other models. Image Classification models, Image Generation models (traditionally difusion models, although some do use llm for image now), TTS models, Speach Transcription, translation models, AI driving models(autopilot), AI risk assessment for fraud, 3D structural engineering enhancement models.

With many of the good usecases of AI the end user doesn't know that ai exists and so it doesn't feel like there is AI present.

carsoon··on Three kinds of AI products work
Legal seems to be a big usecase for AI. I think more for simplification and classification versus generation though.
carsoon··on Three kinds of AI products work
You spot bad ai content. Since there is no button that will tell you if something was Ai generated you never know if what you read was/wasn't.
carsoon··on Go is a good fit for agents
I wrote the start to an agent library in Go. Its quite rough as most of it was implemented through using AI but I had a lot of ideas through planning/building it.

1. If you make your agents/workflows serializable you can run/load them from a config file or add/remove them from a decoupled frontend. You can also hash them to make versioning easy to track/immutable.

2. If you decouple the stateful object from the agent/workflow object you can just store that through sufficient logging then you can rebuild any flow at any state and have branching by allowing traces to build on one another. You can also restart/rerun a flow starting at any location.

3. You can allow for serializable tools by having a standard HttpRequestTool then setup cloudflare workers/any external endpoints for the actual toolcall logic. Removing primary server load and making it possible to add/remove tools without rebuilding/restarting.

Given this system in golang you can have a single server which supports tens of thousands of concurrent agent workflows.

The biggest problem is there isn't that many people who are working on it. So even if you can make agents 100x more efficient by running in Go it doesn't really matter if cost isn't the biggest factor for the final implementations.

The actual compute/server/running costs for big AI Agent implementation contracts is <1%, so making it 100x more efficient doesn't really matter.

carsoon··on Go is a good fit for agents
I actually working on an agent library in golang and this is exactly the thought process I've come up with. If we have comprehensive logging we can actual reconstruct the agents state at any position. Allowing for replays etc. You just need the timestamp(endpoint) and the parent run and you can build children/branched runs after that.

Through the use of both a map that holds a context tree and a database we can purge old sessions and then reconstruct them from the database when needed (for instance an async agent session with user input required).

We also don't have to hold individual objects for the agents/workflows/tools we just make them stateless in a map and can refernce the pointers through an id as needed. Then we have a stateful object that holds the previous actions/steps/"context".

To make sure the agents/workflows are consistent we can hash the output agent/workflow (as these are serializable in my system)

I have only implemented basic Agent/tools though and the logging/reconstruction/cancellation logic has not actually been done yet.

carsoon··on Rails is better low code than low code
Same thing I have settled on.

Sqlite for quick and easy postgres for scaling.

For simple frontends I just use the built in go templates.

If I need complex frontends for larger apps I use sveltekit/svelte5 for frontend data I just export a single instance of a class that has state/derived fields for data and an isInitialized field that returns a promise for loading the data. Then methods for reloading data, changing data or any actions I need.

So all i have to do is await classInstance then use the class data in whatever way I need. Everything is reactive and simple due to states. you can use and update the fields directly like regular js but with global reactivity built in.

The data automatically loads the first time the module is imported. due to how esmodule files work. I just have a classInstance.LoadData() after the export.

Svelte5 isn't as good with LLM's but with some small instructions about how states, derived, and effects work it works pretty well.

carsoon··on US Forest Service proposes protections for old-growth trees, without logging ban
Why would you be skeptical of tree farming leading to less carbon sequestering?

The whole point of farming timber is to harvest wood which is lignin and cellulose aka CARBON.

The green leaves on the tree are not what will store carbon. The green will fall off and become forest duff which gets digested by fungi and bugs and the carbon released back to the atmosphere.

Goal of timber companies == make more timber timber == captured carbon

carsoon··on US Forest Service proposes protections for old-growth trees, without logging ban
There is plenty of timber in northern California and southern Oregon, these regions are actually temperate rain forests, that are harvested sustainably and aren't old growth forests. Every 30-50 years, (depending on species: redwood or doug fir) the same tracts of forest can be logged again and again.

Once you get further north the taigas are colder and slower growing and may take 200 years or longer to grow back.

The best thing for the USA is to use the resources which supports jobs in logging, wood processing, transportation, and have lower costs associated with transportation and fees from importation. I'm not against importing timber into very northern parts of the US but there is no reason to ONLY use canadian timber.

carsoon··on Summary: The daily number game that thinks it's a word game
I made a solver for it using svelte 5 https://www.carsonshort.com/summarysolver
← PreviousPage 2 of 2