Daniel Gafni (@danielgafni) header
Daniel Gafni (@danielgafni) profile picture

Cloud infra, MLOps, data, Python at TypeSafe AI

Joined January 2014
Daniel Gafni retweeted
I've discovered something more important than the Riemann Hypothesis: if you want your type checker to be faster on Pydantic, just tell it you are MYPY
13
1
338
21,407
Daniel Gafni retweeted
i caught up with @CompleteSkeptic last week to cover a few important things: - the pink coat and hair and everything - the AI bubble - SF's crisis of purpose 00:00 - What’s up with the pink? 01:48 - Posting on X dot com 04:51 - AI has been a bubble for a while now 07:55 - Why are labs IPOing now? 10:21 - A lab, a neolab or a third thing 13:28 - The lab revenue problem 17:42 - SF’s crisis of purpose 25:37 - Not worrying about the macroeconomic climate 30:24 - The labs make a lot of bad bets 34:59 - Innovating on financial engineering 37:05 - Making employees arms bigger 38:23 - Pushing the frontier of craziness and bravery
14
5
7
104
53,419
Daniel Gafni retweeted
Nice DeepSWE score! Does it survive a lowercase filename? Introducing MaxxBench: 89 DeepSWE tasks with small changes to the instructions or starting code. Same engineering problem, slightly different requirement. Models clustered around 74% on DeepSWE end up 23 pp apart. Good at coding, or good at DeepSWE? 🧵
239
410
307
5,483
951,667
Daniel Gafni retweeted
Why don't we at TypeSafe call Jev a decision model? If you think of Jev's questions as making *decisions*, I believe you'll use it at the wrong layer of abstraction and your reliability will suffer. I wrote all about this on our site 🧵👇
42
39
23
467
133,398
Daniel Gafni retweeted
Why hasn't AI automated more work? What's holding coding agents back? And are the labs' valuations built on the right expectations? @CompleteSkeptic, co-founder and CEO of @typesafeai, was the perfect person to discuss this and more. Diogo coauthored OpenAI's InstructGPT paper, and a few weeks before we recorded, TypeSafe launched Jev, a "system one" model that returns structured decisions instead of text. It was a ton of fun to discuss this with Diogo. The conversation includes: 0:00 Intro 1:14 The Early Bet on RLCD 4:40 Built for Humans vs Computers 6:39 Roadmap & Model Limitations 11:04 Mental Models of Models 16:07 Do LLMs Have a Place in 10 Years? 17:32 New Model Shapes 21:24 Problems Still Unsolved 27:00 The Tyranny of the KV Cache 31:21 Rethinking Coding Agents 34:40 Multimodality 37:52 Images, Games & Computer Use 39:36 Could This Have Been Built 5 Years Ago? 42:01 Benchmarks & Copycat Releases 44:12 Fundraising 45:27 Quickfire Listen here: YouTube: youtu.be/ham8dROHCrc Spotify: bit.ly/4kyeNBQ Apple: bit.ly/3WppmgK
4
7
2
22
14,255
Daniel Gafni retweeted
Announcing Dagger for Entire. Goodbye pull requests! @GoEntire is a new Git forge for agents and humans. Now with native Dagger support. Agents run the same checks before and after push, with a shared cache and without melting your machine. dagger.io/blog/dagger-for-en…
3
20
8
132
15,693
Daniel Gafni retweeted
One thing that can be tricky to figure out is how to use Jev's primitives to handle more than one intent in a single user query. My favorite way to approach this is what I call the "shopping cart" pattern: recursively pick the next thing until Jev says we're done. I've personally used this to make a coffee ordering bot for our company Slack (using @DoorDash's CLI!), as well as a fast multi-intent handler for my smart home system. Give it a shot!
13
19
4
177
24,221
Daniel Gafni retweeted
Announcing Dagger for GitHub. Run the same checks before and after push. See results in your terminal and PR. Cut out the middleman: just GitHub and Dagger Cloud. Stop wasting compute: checks are cached, and you pay for exact usage, not machines. dagger.io/blog/dagger-for-gi…
14
31
9
284
67,591
Daniel Gafni retweeted
One of my favorite Jev patterns is "line-by-line search", where you put an entire document in state, and ask a question for each line (or paragraph). This is super useful when you want to find the most relevant line for a query. Use nouls when you expect one dominate answer, use scores when you want to highlight lines by overall relevance. The former is good for answering a specific question while the latter is good for finding all relevant passages.
21
17
7
308
48,462
Daniel Gafni retweeted
NEW: Top SaaS Vendors on Ramp (Oct 2026) We clearly see AI spend pulled in two different directions. On the downside, new and cheaper models are pushing AI spend down. Jev captured an entire percentage point of market adoption within a month (unheard of growth). And routers continue to gain. On the upside, the increased adoption of expensive image and video generation models will push AI spend up, like Higgsfield and Runway.
10
23
28
210
71,021
despite the unfortunate timing, we take disclosures seriously at @typesafeai at approximately 6:49PM this Friday evening, we became aware of a massive unauthorized leak of ALL customer noul outputs in effort to maximize transparency, here is the link: gist.github.com/diogo149/810…
447
313
260
6,140
1,203,143
Dagger is one of the sickest technologies I've seen in the recent years. It powers all our CI at TypeSafe! Can't recommend it enough
Announcing Dagger 1.0 beta. Replace Jenkins and GitHub Actions with CI that matches the speed and scale of coding agents without wasting compute or tokens. Featuring: test-native CI, dev shells, local and remote execution, official modules, and more. dagger.io/blog/dagger-10-bet…
5
12
3
395
61,732
Others can benefit from some our modules that are open source! Featuring the uv module specifically, it can build most Python packages out of the box. It has efficient caching, including local deps in monorepos. github.com/typesafe-ai/dagge…
1
21
1,225
Daniel Gafni retweeted
Announcing Dagger 1.0 beta. Replace Jenkins and GitHub Actions with CI that matches the speed and scale of coding agents without wasting compute or tokens. Featuring: test-native CI, dev shells, local and remote execution, official modules, and more. dagger.io/blog/dagger-10-bet…
57
89
40
986
207,884
Daniel Gafni retweeted
Our latest real-time avatar model is live 🚀 Cara-4.1 Express builds on top of cara-4 to make it faster and more expressive. Tested blind against Tavus, HeyGen and LemonSlice, with the code public. Try it: go.anam.ai/MrjU4Iz xitter.cf/benatanam/status/21125…
Cara-4.1 Express is now live at @Anam__AI Faster and more expressive than cara-4 with better lip sync and stronger prompt adherence. It also handles much wider framings for custom avatars. We ran blind human evals: 85% of raters scored Anam higher than HeyGen, 88% higher than Tavus and 92% higher than LemonSlice. The eval code is public and reproducible. Try it in the Anam Lab: go.anam.ai/dXLpQWy
11
1
25
1,404
Daniel Gafni retweeted
On an internal test set we generated for this task, Jev 1.13 had the highest accuracy and lowest cost when compared to other Decisions models and Claude Code's usage of Sonnet 5.
3
2
1
38
12,066
Daniel Gafni retweeted
New @typesafeai Jev capabilities! Some decision models can ask questions about images but can they ask questions with images? 🧵 How to get the most out of the new Jev launch
8
7
173
18,108
Happy JevDay! But before announcements we have to talk philosophy… The needs of early adopters / tinkerers / dreamers are quite different from what is needed for extremely stable infrastructure. For the Jev release, we erred on the latter, but this release is for the former - with a gate so people can opt-in to the danger zone!
83
75
49
1,339
395,287
today sana is becoming the new home for workday. workday actions now take a few seconds to complete with dynamic ui. powered by jev. it's been v fun working with the @typesafeai team on this!
57
58
37
1,228
180,109
Daniel Gafni retweeted
launched a model accidentally served trillions of tokens a day 29.4% of the fortune 500 showed up raised a really big series A from @a16z it's been 3 weeks we would like to sleep now
562
307
287
8,001
1,342,946