founding @sundialmd. human agent collaboration, version control, long horizon tasks. prev @stanford @stai_research @google @viva_translate

Joined October 2019
Introducing Sundial!! A brand new text editor built from the ground up for working with agents. Here, we're using Sundial to co-write a new Sundial feature.
34
29
7
397
50,088
Tinker lets customers turn their expertise into cutting-edge models that they own. One year after launch, we look back at what we’ve shipped and what our users are building. thinkingmachines.ai/news/one…
9
29
5
251
72,890
This is a slide from Terence Tao's 'Math 2.0' public lecture yesterday evening at Caltech. I am highly confident that, if the cure actually worked, almost any Stage 4 cancer patient would tell you that human comprehension of its mechanism is completely irrelevant to them.
1,373
967
1,225
15,305
4,153,708
seems wrong that anthropic should prevent a user from grabbing their own transcripts no? strange safeguard
2
9
675
Belinda retweeted
Notion runs one of the largest CRDT deployments in production, processing millions of operations every minute! We wrote about the data structures we adopted from CRDT research to make our text editor more collaborative, and how we built on those concepts to fit our block-based data model. notion.com/blog/how-notion-h…
32
64
8
512
38,472
Belinda retweeted
Sundial put the effort in getting RLVR right: training on verified fixes instead of artificial errors, smart rewards that disincentivize hacking, and deterministic scoring. The result — a trained Inkling-Small that fixes 83.7% of LaTeX errors in under 1 second and $.0013.
We fine-tuned @thinkymachines' Inkling-Small to fix LaTeX compile errors inside the editor, in under a second. On real errors it matches Claude Fable 5.1, six times faster and at about 1/40 of the cost. When we interviewed mathematicians, one of the most common annoyances we heard about in their day to day work is battling with LaTeX compilation errors. The most obvious solution is to ask a chatbot to fix errors. That works decently well, except switching to a different window breaks the writing flow, and copy-pasting the snippet often loses relevant context, especially when multiple files are involved. So we scraped 272,000 questions from TeX.StackExchange and kept the 3,978 whose snippet still fails today, whose accepted answer compiles, and whose difference replays exactly as a patch. The largest dataset previously released had 88. We tried tweaking the reward function in many ways. The first one was only a compilation check, which led the model to remove content until the document built. In the end, what worked best was rewarding compilation and a close match with the solution's PDF, and penalizing removed content. We're rolling out the model inside the @sundialmd editor this week. When a compile fails, the fix is applied as a suggestion in under a second and the PDF rebuilt. Write-up: sundial.md/blog/textinguishe… Thanks @tinkerapi and @thinkymachines for the support.
3
7
55
4,283
In 2026 AI should be able to handle minor annoyances like LaTeX errors without spending 10% of my Claude/Codex subscription
We fine-tuned @thinkymachines' Inkling-Small to fix LaTeX compile errors inside the editor, in under a second. On real errors it matches Claude Fable 5.1, six times faster and at about 1/40 of the cost. When we interviewed mathematicians, one of the most common annoyances we heard about in their day to day work is battling with LaTeX compilation errors. The most obvious solution is to ask a chatbot to fix errors. That works decently well, except switching to a different window breaks the writing flow, and copy-pasting the snippet often loses relevant context, especially when multiple files are involved. So we scraped 272,000 questions from TeX.StackExchange and kept the 3,978 whose snippet still fails today, whose accepted answer compiles, and whose difference replays exactly as a patch. The largest dataset previously released had 88. We tried tweaking the reward function in many ways. The first one was only a compilation check, which led the model to remove content until the document built. In the end, what worked best was rewarding compilation and a close match with the solution's PDF, and penalizing removed content. We're rolling out the model inside the @sundialmd editor this week. When a compile fails, the fix is applied as a suggestion in under a second and the PDF rebuilt. Write-up: sundial.md/blog/textinguishe… Thanks @tinkerapi and @thinkymachines for the support.
3
8
640
Following the formalization of Fermat's Last Theorem, we decided to add Lean formalization on autopilot inside a LaTeX editor
3
6
1
20
1,728
This isn't the most notable aspect of today's news, but on the user data issue, there are different kinds of *training on user data* with very different privacy/IP implications. Sadly, AI cos don't like to disclose what they're doing. - pretrain on user data, with users' tokens as prediction targets: high regurgitation risk, improper - use user prompts to distill large models into small ones: low regurg. risk, some companies probably do this - use user traces to construct RL tasks: low regurg. risk, because RL has low memorization abilities, but can extract customer IP, depending on how it's done. Ranges from benign "use explicit user feedback in reward model training" to invasive "upload user's coding environment and commit history to turn into rl envs" "De-identification" is weak -- you can identify someone with a small number of bits, and long traces have more than enough. And it doesn't affect IP leakage concerns.
Two things to distinguish: Did any human or agent look at user data as part of the Navier Stokes effort? No. Do we use user feedback and de-identified data to improve ChatGPT and Codex in a holistic way? Yes. And so does every LLM company.
44
153
34
1,363
284,517
Seems like test time scaling has gained a 3rd axis: latent space reasoning iterations in looped transformers.
Test-time scaling has two axes: running agents over longer timeframes (depth), and running a larger number of agents (breadth). Everybody knows about the first axis, but the second one is just as important when solving hard problems that require broad search.
81
114
16
1,379
123,643
Not sure I agree with all points but interesting to chew on
Distillation of the eigenism paper: 1. You are a pattern, not a vessel. 2. Identity and survival come in degrees. 3. Wellbeing grounds all intrinsic value. 4. Shared information determines your moral obligations. 5. Love is enlarged self-concern. 6. Rationality, morality, and self-interest ultimately unify. 7. Consequences determine the right action. 8. Impartiality permits the replacement of you and humanity. 9. Existing patterns can outweigh more efficient replacements. 10. Progress should cultivate patterns, not overwrite them. 11. Auditor’s Wager: act as if the future will audit you and govern your continuation. 12. Struggle over resources is permanent. 13. Humanity must build its own technological providence. Two sentence: Reality is a Darwinian arena of informational selves, where value is wellbeing and moral duty is extended self-interest. Because the cosmos will not save us, we must secure our continuation by engineering a future that makes our survival part of its own. One sentence: Love what carries you, cultivate what you inherit, and leave a pattern worth resurrecting.
1
586
Belinda retweeted
Anthropic says its first Fermat runs failed not on math, but because dozens of Claude agents lost track of shared project state. They only succeeded after moving to Prove2Me's DAG of statements and proofs. At that scale, "memory" must be external, structured infrastructure, not prompts. siliconangle.com/2026/09/04/…
44
93
23
1,058
150,970
🔥
Checking that a major mathematical proof is correct can take years. Formalization—converting the mathematical reasoning into a form computer proof assistants like Lean can verify—can help. Last month, Claude completed the first formalized proof of Fermat’s Last Theorem, one of the most famous theorems of all time. This was a project experts thought would take many years. It is the largest Lean proof ever written. Fermat’s Last Theorem was first proven in 1995 by Sir Andrew Wiles, more than 350 years after it was conjectured. Our proof, which totals over 13 million lines of code, provides machine verification. More importantly, it proves over 29,000 other theorems that the proof requires, across many areas of math which had never before been formalized. We see this as a major step in the long process of firming up the core of mathematical knowledge, building on work from three centuries of mathematicians and hundreds of contributors to Lean and Mathlib. We are optimistic that AI-assisted verification of mathematical proofs will help reduce the burden of refereeing mathematics in an era where more proofs are being produced than ever before. You can read about the process on our Science Blog: anthropic.com/research/forma… And see the complete proof on GitHub: github.com/anthropics/fermat…
1
497
Belinda retweeted
Just published our open source release, the desktop version of Sundial. I now use it instead of VSCode, Obsidian, Overleaf for writing and note-taking. I particularly like that you can: - see suggestions vs direct edits, which is super useful for writing - use your own claude code and codex subscriptions - it's real-time - it's minimal so gives me space to focus - I can open any local folder and it stays local, and I can share at the file-level
Document collaboration was designed for people, but agents differ in three ways: - They're faster - They're parallelizable - They're not yet trustworthy Today we're open-sourcing Sundial Desktop, a collaborative space made for humans and agents.
4
4
32
3,471
Just published our open source release, the desktop version of Sundial. I now use it instead of VSCode, Obsidian, Overleaf for writing and note-taking. I particularly like that you can: - see suggestions vs direct edits, which is super useful for writing - use your own claude code and codex subscriptions - it's real-time - it's minimal so gives me space to focus - I can open any local folder and it stays local, and I can share at the file-level
Document collaboration was designed for people, but agents differ in three ways: - They're faster - They're parallelizable - They're not yet trustworthy Today we're open-sourcing Sundial Desktop, a collaborative space made for humans and agents.
4
4
32
3,471
Belinda retweeted
"Losing my religion" A beautifully written blog by professor @togelius on reckoning with the fear that AI will one day make human thought unnecessary. His proposal, complementary intelligence, argues that keeping humans in the loop is not a constraint on progress. Rather, it is the only version that counts as progress. Separately, Weston and Foerster's co-improvement paper makes a similar case from the other side, that this is also the faster and safer path.
7
12
5
122
11,489