Joined November 2021
Photos and videos
Fundamental Research Labs retweeted

44
95
1,090
389,757
Fundamental Research Labs retweeted
/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
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.
2
17
4,566
Fundamental Research Labs retweeted
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 & environment Codex Mog is dramatically better than Codex's default spreadsheet skill, and almost as good as the best agents
Mog v0.9 is published! Mog is the best spreadsheet for agents, and available wherever your agents are Use it in Codex, Claude Code, etc. Just tell them to use npm mog-sdk/sdk, that's all Use it with Shortcut agents, Cloudfare workers, etc Edit xlsx in VSCode, Cursor, etc
2
5
25
19,153
Fundamental Research Labs retweeted
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.
18
40
716
345,798
Fundamental Research Labs retweeted
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: github.com/fundamental-resea…
6
11
76
32,380
Fundamental Research Labs retweeted
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.
5
10
59
50,773
Fundamental Research Labs retweeted
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.
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
7
5
62
9,978
Fundamental Research Labs retweeted
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
15
74
1,074
90,840
Fundamental Research Labs retweeted
This is what going extremely deep on a vertical looks like. @tryshortcutai is the only Excel agent that can do all of the following - connect to live/open excel models - iterative recalc - multiple (30 ) models in parallel - goal seek / what if / sensetables - edit/creat VBA
Introducing ShortcutXL - your favorite spreadsheet agent is now available as a desktop generalist. Unlock Excel capabilities that no other spreadsheet agents can touch (VBA macros, What-if analyses, and more). Have a swarm of Shortcut agents work on dozens of models concurrently / in parallel. This is just a taste. try ShortcutXL now: npmjs.com/package/shortcutxl
2
3
63
70,006
Fundamental Research Labs retweeted
Introducing ShortcutXL - your favorite spreadsheet agent is now available as a desktop generalist. Unlock Excel capabilities that no other spreadsheet agents can touch (VBA macros, What-if analyses, and more). Have a swarm of Shortcut agents work on dozens of models concurrently / in parallel. This is just a taste. try ShortcutXL now: npmjs.com/package/shortcutxl
7
6
45
24,527
Fundamental Research Labs retweeted
Opus 4.7 is live in @tryshortcutai It's a great model, but definitely requires some getting used to. Reminds me of Sonnet 3.7 when it came out. According to our spreadsheet evals, it is a meaningful efficiency jump, but is ~ parity with Opus 4.6 depending on task/config.
1
3
28
3,877
Fundamental Research Labs retweeted
v0.8.1 is live @tryshortcutai Chat with your data build/edit/share dashboards with your team
Introducing Shortcut v0.8 - the best way to do spreadsheet work. Releasing 5 big updates - The Shortcut Safe for APIs/Tokens - Live, Shareable Dashboards - ShortcutXL CLI for Windows - The /skillstudio for automations - Bunch of new features Walkthrough and details below!
2
3
33
6,792
Fundamental Research Labs retweeted
Shortcut Safe, Dashboard, CLI for multi-agents, Skill Studio, and more!
Introducing Shortcut v0.8 - the best way to do spreadsheet work. Releasing 5 big updates - The Shortcut Safe for APIs/Tokens - Live, Shareable Dashboards - ShortcutXL CLI for Windows - The /skillstudio for automations - Bunch of new features Walkthrough and details below!
2
2
7
1,971
Fundamental Research Labs retweeted
Introducing Shortcut v0.8 - the best way to do spreadsheet work. Releasing 5 big updates - The Shortcut Safe for APIs/Tokens - Live, Shareable Dashboards - ShortcutXL CLI for Windows - The /skillstudio for automations - Bunch of new features Walkthrough and details below!
11
6
56
48,599
Fundamental Research Labs retweeted
We are opening up a Research Preview for a product we are calling ShortcutXL We used ShortcutXL to build and audit 100 of the most searched for Excel templates in parallel (we are making them free too). OfficeJS/Openpyxl are great, but still quite limiting. Comment for access
55
11
86
31,703
Fundamental Research Labs retweeted
Replying to @tryshortcutai
@tryshortcutai is growing ~50% MoM and we are looking for a world-class technical GTM person to join the team. Looking for someone relentless, and passionate about profoundly solving spreadsheet work. DM me (bonus for a referral!) TC $220-$300K Cash Equity
13
10
111
11,436
Fundamental Research Labs retweeted
Shortcut just experienced 46 minutes of downtime. Our servers were overloaded by a usage spike and we just deployed a fix. We will continue to monitor and keep you posted, and we apologize for the outage. Thank you for bearing with us as we scale. @tryshortcutai is back up
1
2
47
6,588
Fundamental Research Labs retweeted
Definitely worth a watch I think if you're a PE or Private Credit professional you should be leveraging Shortcut for deeper data cuts as opposed to just DCFs
We had early access to GPT 5.4 to benchmark on @tryshortcutai and it is extremely good at Excel Here is a quick walkthrough of two real-world tasks in our internal eval of 50,000 cells each Watch, because the industry is way beyond the same flashy and meaningless DCF demo
4
6
201
43,979
Fundamental Research Labs retweeted
We had early access to GPT 5.4 to benchmark on @tryshortcutai and it is extremely good at Excel Here is a quick walkthrough of two real-world tasks in our internal eval of 50,000 cells each Watch, because the industry is way beyond the same flashy and meaningless DCF demo
17
21
232
88,878