Austin

Building AI tools and automations for utility construction.

[Austin @TrickRiggin]

@WallStreetApes The manager must be an Adderall dealer

[Austin @TrickRiggin]

@MiaAI_lab So do I drop 7k on specced MBP that I can also use for other things or 8k on 2 sparks for serving a local model

[Austin @TrickRiggin]

@JiweiLi1 Anyone providing inference? @OpenRouter ?

[Austin @TrickRiggin]

@matthewdif What harness are you using? OpenCode?

[Sakana AI @SakanaAILabs]

Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.

Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.

Try it: https://t.co/hhO6qTawgb 🐡

[Austin @TrickRiggin]

@sudoingX What size context window are you getting with the 128 and 64?

[Austin @TrickRiggin]

@blatennic @0xSero I tried a qwen variant it worked decently I believe it was 4B quant, it barely fit and my context window was garbage. That laptop sounded like a helicopter was taking off when I asked it a simple question.

[Austin @TrickRiggin]

@0xSero I assume by your 3090 comment the gaming rig is the direction to go? I just assumed the GB10 boxes were more scalable?

[Austin @TrickRiggin]

@0xSero Oh and no 3090s locally on Facebook but I didn’t look that hard

[OpenRouter @OpenRouter]

Introducing the Fusion API, the smartest compound model in the market.

Fusion achieves Fable-level intelligence at half the price.

How it works 👇

[Xander Steenbrugge @xsteenbrugge]

More than ever before I feel like Fable 5 speaks a different kind of English than we humans do.
It isn't conversational, its not 'light' to read, it barely explains — it's pure load-bearing density, meaning compacted until every token earns its place.

It assumes your context window is as large as its own and you have perfect recall of everything you're working on. Similar to how AI-chess feels alien, this too, feels almost akin to an alien language.

I mean, just read this stuff, nobody talks like this, only advanced AI does:

[Arun @hiarun02]

@avrldotdev The hard part was never writing code.

[Austin @TrickRiggin]

@thsottiaux Are you saying that the memory improvement is also in Codex CLI?

[Aaron Levie @levie]

As we enter the era of AI agents, one of the defining questions is how you develop competitive advantage when your competitor has access to the same AI models and intelligence as you.

The companies that are able to best harness their internal institutional knowledge, existing data assets, and domain-specific workflows -- connected with AI -- will be those that are able to stay ahead in the future.

Whether a company decides to build out the tech stacks themselves, or leverage a variety of best-in-class tools is certainly one core variable. But the key is to find the way that the enterprise can capture and protect the value created by their unique data, processes, and expertise over the long run. Each industry will have their own version of this, and the competitive advantage will vary by vertical.

We’re increasingly seeing this at Box, where customers want to ensure that they can take advantage of their institutional knowledge and have the flexibility of bringing any AI model and intelligence to their data at any time. This is a pattern that will increasingly become a core principle of strategy in the future.

[Austin @TrickRiggin]

@levie @levie Hypothetically, how valuable would it be if your “genius” (or FDE) in this example was also your SME, with a decade of company knowledge across all departments?

Have you come across this in your experience?

[Tom Blomfield @t_blom]

Imagine replacing 90% of your employees with a team of geniuses who have no idea how your company operates.

Total chaos. Nothing works.

That’s what AI feels like today.

The missing piece is extracting all the domain knowledge from people’s heads and providing that as structured context to the models.

[Austin @TrickRiggin]

Yes. This is the kind of thing you only find on X.

[Theo - t3.gg @theo]

Struggling to pick what agent, model, and effort levels to use? Miss the "slot machine" feel of Claude Code when using other tools?

`npx slotslop "[prompt]"`

[Vlad Tenev @vladtenev]

Agent, meet markets.