Fundamental Research Labs

Building machines with fundamental human qualities

Makers of the strongest spreadsheet agent @tryshortcutai

[nico @nicochristie]

I challenged the MSFT Excel World Champion to a battle.

AI beat humans at Chess, then Go. But those are games

We built an agent to surpass humans on the most important app in the history of work

Meet Shortcut: The Excel AI Agent

Comment SATYA and I'll send you free credits

[Robert Yang @GuangyuRobert]

@nicochristie just beat the Excel world champion at financial modeling by using @tryshortcutai

18 months ago, we demoed to investors an agent that's 2x SOTA on OSWorld, and "superhuman" on its Spreadsheet category, scoring ~80% when every other agent was <20%

At the time our agent was able to create pivot tables and that was considered impressive

We have truly gone a long way, super proud of the team🔥

[Adrian Duermael @aduermael]

What a week! The first GPT model worth being served by default in Shortcut.
Let's benchmark Grok 4.5 tomorrow! 😁

[Peter Wang @BrainsAndTennis]

we evaluated GPT 5.6-Sol against Fable and Opus using the Shortcut production harness on our own internal set of benchmarks, results were very surprising

ShortcutBench V1: swiss-army knife spreadsheet tasks

ShortcutBench V2: gnarly, tough, long spreadsheet tasks

Sol costs half as much as opus and had similar if not higher accuracy. It also took way less turns and was much faster.

Historically, we never served GPT models as default because they are significantly worse at formatting (trust-breaking) than Opus class models. This is also no longer true in our taste tests, although fable is still the best at formatting

well done @OpenAI

[Robert Yang @GuangyuRobert]

Tianhang finally on twitter. He was a founding member at Qwen and head of RL at https://t.co/hJWGsSHYX5

There's so much discussions about models from the Chinese labs, but very few people on twitter actually worked there and in the US now

[nico @nicochristie]

Tianhang is finally on twitter

He was formerly a founding team member and head of RL at Qwen, and leads model training here at FRL / shortcut

He will be posting more on twitter now

Probably the most cracked person i've ever met. Excited for you to see his work soon!

[tianhang zhu @TianhangZhuzth]

Hey guys, I'm leading LLM research for fundamental research labs. I'll be posting more.

[nico @nicochristie]

Shortcut can now spin up 1000's of agents to parallel search, but we built the feature entirely around the filesystem - enabling some pretty cool new things

Here I fill out a huge table of VCs we tracked for a fundraise and another table that has subtables, merged cells, etc.

[Peter Wang @BrainsAndTennis]

https://t.co/DVyPORQgPe

[Fundamental Research Labs @Fundamental]

@BrainsAndTennis @GuangyuRobert 👀

[Peter Wang @BrainsAndTennis]

https://t.co/MVcIdCly31

[nico @nicochristie]

/Autonomous is now default on in Shortcut.

@BrainsAndTennis built it before Codex released /goal and has gotten pretty awesome reviews.

You need runtime observability and verifiable goals for long term autonomy, and our solution to compacting is to never ever do it at all

[Robert Yang @GuangyuRobert]

Fable 5 is the best model today, but for everyday spreadsheet task, you won't see a huge difference

You'll get much more gain with the right harness &amp; environment

Codex + Mog is dramatically better than Codex's default spreadsheet skill, and almost as good as the best agents

[nico @nicochristie]

I think it's safe to say Excel is solved.

The sign of an Excel rookie used to be manually using your mouse... now it's doing ANYTHING at all without AI.

If you use Excel do yourself a favor and watch all 3 mins.

It's a new world. Solving tasks in 20 mins that take teams days.

[Robert Yang @GuangyuRobert]

I'm rebuilding Excel

Excel was designed for floppy disks and fax machines, we deserve something better now

Run xlsx headless, API for agents + UX for humans, colab, embeddable

Mog is the new way to Excel

Free, Open source, Building in public: https://t.co/5KXgG1XQZG

[nico @nicochristie]

@tryshortcutai Link to case study:
https://t.co/y96VIweL6r

[nico @nicochristie]

For the second time now, @tryshortcutai was independently ranked as the top Excel AI agent in the world.

We specifically build for the top analysts, and this matches what we see on the ground.

It's firmly us, then Claude, or your firm forces Copilot upon you.

[nico @nicochristie]

GPT 5.5 is now live on @tryshortcutai

GPT-5.5 is genuinely a bit more intelligent than Opus 4.6/7 on the very hardest end-to-end tasks, but it's less verbal and still less tasteful on formatting.

Try it, it will come down to personal preferences now for Excel.

[nico @nicochristie]

We have been testing GPT 5.5 on the hardest spreadsheet tasks in the world (100k-1M+ cell complex models).

It is the Pareto frontier for spreadsheets -- SOTA accuracy, the fastest and the most efficient public model across effort levels.

OAI really cooked here