ianpurton

True.

If this is even 50% functional its going to have an impact on adobe revenue.

Would be amazing to this these tools in Linux distros.

Off Topic - The Mistral website - Really nice design. My guess, built by a human.

On Prem. Thats a bid deal for some enterprises.

also the benchmarks are not necessarily indicative of how well the model will perform in its own harness with its own skills.

I wouldn't say execeptional.

There are many times I tried to charge and got asked to indstall apps or the charger wasn't working. Blocked by a petrol car.

Charging in europe comes with a learning curve.

For my commute I'd have to charge every 2-3 days in winter. Not a show stopper, but an extra 10k for more convenience is a bit much.

You can find a new sub 25K EUR car in Europe but the range will suck.

For example the VW Polo starts at 25K but if you want the bigger battery, its 35k.

Bionic has Sqlite and office tools. So you could ask "store this csv in sqlite" then you can get it to query that.

They don't really say why they built their own rather than using one of the open source solutions like https://github.com/bionic-gpt/bionic-gpt

Chat GPT work is running a full bash environment with python.

You can get it to run scripts direct from the prompt.

Try...

Run the script below in your sandbox

message="I'm running in a bash sandbox"

printf '< %s >\n' "$message" printf ' \ ^__^\n' printf ' \ (oo)\_______\n' printf ' (__)\ )\/\\\n' printf ' ||----w |\n\n'

printf 'User: '; whoami printf 'Host: '; hostname printf 'System: '; uname printf 'Folder: '; pwd printf '\nWorkspace:\n' tree

I have some more examples here -> https://bionic-gpt.com/architect-course/ai-computer/sandboxe...

The main benefit here seems to be smaller and lighter for the same power output.

For context this is the authors website. https://axonlore.com/

So where its fair to say enterprise users buy safety, if he's referring to his own product I would offer the following.

He's in the AI tool space i.e. a better rag. So you're selling to AI developers and developers nearly always go open source first.

If they can't find an open source solution or if they don't even look, they prefer to build it themselves.

For this kind of product most enterprise buyers won't understand its benefits, you have to get the developers interested first.

And finally, in this market, you are 1 prompt away from someone cloning your whole business and calling it openaxon or something like that.

It's a tough time to be a software startup.

I don't get it, what is this, how is it different?

That site is everything that's wrong with the internet at the moment.

A dizzying array of adverts and popups.

Because the model that generated that list was trained before the M5 came out.

> if you face a problem in development, db, storage or anything

Developers won't pay for it. I'll pay for hosting begrudgingly and I pay for AI tokens and domain names and that's it.

And every Saas idea can now be copied with this prompt.

Build me an open source clone of -> https://your-saas.com

You need a moat these days more than ever.

Thats true. The reason I like k8s is once you've gone up the learning curve you can apply that knowledge to cloud deployments, on prem, or in this case VPS.

The authors stack left me thinking about how will he re-start the app if it crashes, versioning, containers, infra as code.

I've seen these articles before... the Ruby on Rails guys had the same idea and built https://kamal-deploy.org/

Which starts to look more and more like K3s as time goes on.

Dynamic scaling is not really even available on a single node kubernetes.

I was thinking more of

Running multiple websites. i.e. 1 application per namespace. Tooling i.e. k9s for looking at logs etc. Upgrading applications etc.

When he switches from Kubernetes in the cloud to Nginx -> App Binary -> Sqlite he trades operations functionality for cost.

But, actually you can run Kubernetes and Postgres etc on a VPS.

See https://stack-cli.com/ where you can specify a Supabase style infra on a low cost VPS on top of K3s.

> I bet we will move from CLIs to something else in about 3-6 months.

My bet would be OpenAPI specs. The model will think its calling a cli but we intercept the tool call and proxy it with the oauth credentials.

There are some implementations already out there in open web ui and bionic gpt.

If you look for jobs on linkedin you'll see a lot are posted by recruiters.

Its usually pretty easy to get one to call you and they can give you an idea about the market.

This is a really good idea.

Taking something that is basically a lonely depressing activity and putting a social aspect around it.

Well done.

I don't work at Open AI but I use Codex as I imagine most people there do to.

I actually use it from the web app not the cli. So far I've run over 100 codex sessions a great percentage of which I turned in to pull requests.

I kick off codex for 1 or more tasks and then review the code later. So they run in the background while I do other things. Occasionally I need to re-prompt if I don't like the results.

If I like the code I create a PR and test it locally. I would say 90% of my PR's are AI generated (with human in the loop).

Since using codex, I very rarely create hand written PR's.

I imagine they mean a remote KVM. So you remote into a PC sitting in a basement in someones house in the US. You then make all your outgoing internet from thta setup and your IP address would look legit.

I've never worked on a mono repo that has the whole organizations code in it.

What are the advantages vs having a mono repo per team?

Some context.

1. Some LLMs support function calling. That means they are given a list of tools with descriptions of those tools.

2. Rather than answering your question in one go, the LLM can say it wants to call a function.

3. Your client (developer tool etc) will call that function and pass the results to the LLM.

4. The LLM will continue and either complete the conversation or call more tools (functions)

5. MCP is gaining traction as a standard way of adding tools/functions to LLMs.

GitMCP

I haven't looked too deeply but I can guess.

1. Will have a bunch of API endpoints that the LLM can call to look at your code. probably stuff like, get_file, get_folder etc.

2. When you ask the LLM for example "Tell me how to add observability to the code", the LLM can make calls to get the code and start to look at it.

3. The LLM can keep on making calls to GitMCP until it has enough context to answer the question.

Hope this helps.

It may reduce consumerism in the US and therefore be beneficial to the environment.

Tesla in Berlin employs 12,000 workers and can produce 5000 cars a week.

The US will need a lot of factories to employ 10s of millions of workers.I also imagine new factories will employ less workers due to increased automation.

I'm interested to see how this plays out.

In your scenario white collar jobs will be destroyed globally.

So effectively you would be paying people to work in manufacturing even though it's no longer necessary.

You may as well pay a basic income instead.

You need to take a Defence in depth strategy.

There are various ways to validate libraries but it's best to assume an exploit gets through.

So then, you should be looking at your deployment, i.e. locking down containers, network policies, least privileges etc etc.

Try to reduce the blast radius to zero.