AI Education | Developer Advocate @huggingface
EU
- Tweets 1,073
- Following 495
- Followers 3,797
- Likes 3,316
Pinned Tweet
introducing tau τ — an educational agent harness that teaches you how to build agent harnesses
i will be publishing tutorials and demos on how to use it to create your own TUIs, harnesses, extensions, etc.
Happy Tau Day!! 🤓
👉 twotimespi.dev/
74
213
2,278
328,051
Alejandro AO 🤗 retweeted
"we had a wonderful run chiseling that code by hand and it’s over.
On the other side of that is an exciting new career as professional maker of things, steering intelligence that was only available in science fiction up until a moment ago
What a privilege to have been there when we did it all by hand and be there at the exact moment where we switch over."
My god this is such a good speech that every SWE needs to hear. You know what? Every person should hear it
Keep the happy memories, eyes on the reality, be excited about the future. That’s the best that anyone can do
11
27
217
22,990
trying out the stealth model "space-bunny-alpha" on @OpenRouter for my video editing.
it's doing an amazing job at great speed as you can see. and it's free for the next week i think.
link below 👇
3
11
1,499
if you want the harness on the video 🤗
twotimespi.dev/
1
126
THIS. The main reason i don’t use anthropic’s models often is that i can’t use the plan with my harness.
Anthropic's strategy to win back the community:
✅ Support AGENTS.md
✅ Reduce Opus price 40%
✅ Make Opus 5.5 the best agentic coding + writing model
✅ Gave us a banked reset (with no window reset)
❓ Let us use the subscription in any harness? 🤞
1
8
1,258
Tau 0.4.3 adds cross-project session resuming.
Open /resume, choose the project, then pick a saved conversation.
Useful when you switch between repositories: check the full project path before continuing, so you know which work you are picking up.
2
16
947
Tau 0.4.2 is out with bookmarks inside the session tree.
When creating a coding agent, it's good UX to allow the user to label a message.
> Mark a point before a refactor,
> find it again,
> try another conversation branch.
Small feature, but useful. ofc: Inspired by @pidotdev
2
2
29
2,130
Install it here:
`uv tool install tau-ai`
buff.ly/mFfNmUS
2
188
can we get a mosquito brain instead? that’d make me feel much better about this whole thing
1
10
490
mcp apps is the way
modelcontextprotocol.io/exte…
1
10
1,838
great writing.
but this is sci-fi horror meant to scare you.
one interesting takeaway, though.
what's wrong:
> there's no natural selection of disconnected subagents -- there are no inheritable changes, self replication, or any persistence beyond a session.
> nor is there a "global network" of all agents that would somehow "wake up". even agents using the same model in the same datacenter are separate, stateless inference calls.
BUT:
it does make you think that something like consciousness likely won't come from a single model "waking up".
rather, we should pay attention at coordinated networks of thousands or millions of subagents with the same memory (a "country of geniuses" in a datacenter).
that sounds more like the condition where this "emergent" behavior could arise 👀
1
365
Alejandro AO 🤗 retweeted
It's now clear that alignment is critical and won't be solved behind the closed doors of a handful of frontier labs.
So today we're launching the Open Alignment Initiative, led by @Thom_Wolf @huggingface and asking to be part of the "embedded evaluators" program that @DarioAmodei just committed to.
Let's make AI safer by making it more transparent!
We Must Pace the Frontier: I’ve written a new essay on why the AI industry should slow down, with a three-part plan for doing so.
Anthropic is unilaterally committing to the first of these steps. We’ll provide third-party evaluators with permanent, employee-level access to our systems, so that they can verify adherence to our safety measures, report on incidents, and assess models’ alignment during training.
You can read the full post here: darioamodei.com/post/we-must…
291
422
3,873
442,958
tip: ask codex/chatgpt "what books should i read next?"
(or any memory-powered agent you use... hermes, claw, etc.)
2
10
966
coming to tau in next version: browse recent sessions in other projects when opening the /resume modal
2
2
29
2,716
install it with `uv tool install tau-ai`
twotimespi.dev/
4
262
