tony retweeted
I would have paid like $50/mo for this feed, but they won't even sell the API access, let alone the linking and intent capturing and annotation layers I'll have slathered on top before Monday.
But they'd rather build walls than build products.
π€·ββοΈ Old world playbook. ngmi.
tony retweeted
Replying to @jrysana
.pdf is perhaps the most cursed, but .ipa (iOS apps) is evil at a social level: wildly popular format normalizing a level of restriction that's become the default.
There's a now-dead timeline where mobile phones were general purpose computers. Few hands are redder than Apple's.
I have a rigorous e2e suite configured via @superlogical rex and it is a dream for testing TUIs. Satisfying watching all the sessions open and close and pop into them to see what's being tested live. I can imagine a playwright / cypress hosted solution for this in the future
55
tony retweeted
I recently gave my first conference talk at @aiDotEngineer representing @arizeai . It was great getting to meet fellow AI nerds and talk about the things we are building. It genuinely gave me energy being around true innovators.
There's so much hype around self-improving agents and RL environments but I've only recently started to feel this is possible when I started playing with code mode and the harbor framework plugin with @ArizePhoenix. It's been a journey over the last few months and I think it fundamentally has changed how I think we should build agentic systems.
Have you setup code mode and RL / hill-climbing evals that work for you? What should I try next?
youtu.be/dAoOYFx7ZYw?si=6bKOβ¦
tony retweeted
Our Head of Open Source, @mikeldking talks through a problem every agent builder runs into: tool lists start out helpful, then start filling the context window.
Code mode gives the agent a sandbox where it can find the tools it needs, call them in code & return a smaller result.
I recently gave my first conference talk at @aiDotEngineer representing @arizeai . It was great getting to meet fellow AI nerds and talk about the things we are building. It genuinely gave me energy being around true innovators.
There's so much hype around self-improving agents and RL environments but I've only recently started to feel this is possible when I started playing with code mode and the harbor framework plugin with @ArizePhoenix. It's been a journey over the last few months and I think it fundamentally has changed how I think we should build agentic systems.
Have you setup code mode and RL / hill-climbing evals that work for you? What should I try next?
youtu.be/dAoOYFx7ZYw?si=6bKOβ¦
tony retweeted
Abliterated models are having quite the moment right now, especially in cyber security. What is abliteration and how does it work?
I spent a few hours on my plane ride relearning and apply it on Qwen3.5-4B! I wrote up my notes + put the model on HF
it mostly follows @maximelabonne's guide, which still holds up really well!
calebfahlgren.com/how-abliteβ¦
tony retweeted
Honored to receive this award on behalf of our @ArizePhoenix maintainers and community. Excited to keep building in the open for all.
π Meet the winners of the Open Source AI Awards 2026!
Celebrating the people and projects moving open source AI forward:
β’ The Bedrock Award β Best AI Infrastructure:
vLLM (@vllm_project), represented by Richard Bian (@RichSFO).
β’ The Reward Signal Award β Best Reinforcement Learning Project:
Harbor (@harborframework) from Laude Institute, represented by Ryan Marten (@ryan_marten).
β’ The Reality Check Award β Best Benchmark or Evaluation:
ExploitGym from UC Berkeley RDI, represented by Zhun Wang.
β’ The Guardrails Award β Best Security & Alignment Project:
NeMo Guardrails from NVIDIA (@NVIDIAAI), represented by Jean Kossaifi (@JeanKossaifi).
β’ The Community Lifeline Award β Outstanding Community Support:
Daniel Han (@danielhanchen), co-founder of Unsloth AI (@UnslothAI).
β’ The Unsung Maintainer Award β Outstanding Project Stewardship:
Quentin GallouΓ©dec (@QGallouedec), TRL maintainer at Hugging Face (@huggingface).
β’ The Mission Control Award β Best Agentic Harness:
Hermes Agent from Nous Research (@NousResearch), represented by Sam Herring (@yaboilyrical).
β’ The Glass Box Award β Best Observability Tool:
Arize Phoenix from Arize AI (@arizeai), represented by Mikyo King (@mikeldking).
β’ The Open Knowledge Award β Outstanding Educator:
Sebastian Raschka (@rasbt), author of Build a Large Language Model (From Scratch).
β’ The Naming Things Is Hard Award β Most Spectacularly Questionable Project Name:
Alex Newman (@thedotmack), creator of Claude Mem β CMEM.
Congratulations to all our winners, and thank you to everyone who nominated, voted, contributed, and joined us to celebrate! π€
#OpenSourceAIWeek #OpenIntelligence
tony retweeted
Why does everyone seem to think patching source code will solve security?
Once source code is patched, the compiled packages have to be distributed. Thatβs a much harder problem.
Source is the βeasiestβ problem to target because models are very good at it. Dropping a fix on a running application sever, container image, etc and testing that end to end is what a significant amount of IT and security have to deal with.
tony retweeted
building an agent: this is incredible
building an eval for the agent: what even is truth
End of an era, I've been inspired by partykit since day 1 and still have a bunch of random toys deployed on it (until today π
). PartyServer is great too though
I'm finally shutting down the free hosted @partykit_io platform (*.partykit.dev), 2 and a half years after getting acquired(!). I hope and assume that was long enough to move over projects to cloudflare π
blog post with more details: blog.partykit.io/posts/hosteβ¦
I can sense it: 2027 is the year of durable computing by default.
I have been obsessed with the concept of durable computing since the day @threepointone launched partykit all those years ago
Pi Durable is awesome! Asked Opus 5.5 to make a deep technical manual on it.
It's really good and the diagrams work really well to explain things π€
huggingface.co/buckets/cfahlβ¦
7
709
we have the same challenge developing @ArizePhoenix but it leads to innovation and problem solving that we otherwise would not experience. Something something constraints breed creativity π
our main challenge is we can't directly solve a problem
we have to make sure the solution
- can be opensource
- decent experience without cloud service
- everything is pluggable
sometimes i'm jealous of codex where everything is a logged in, cloud powered experience
4
95
I recently built code mode, in the browser, using web workers and proxies and javascript
looking for critical feedback tbh arize.com/blog/code-mode-in-β¦
One of my great regrets is canceling my batch 1 @FrameworkPuter fw 13 pro x9 limited pre-order
1
53
I gotta stop "taking notes" and "having ideas". I gotta start brain dumping into cloud agents who can manifest fleeting thoughts into stuff I can play with by the end of the day
4
307
This is exactly what I had in mind, very cool to see if manifested
Introducing jevgrep - a research agent CLI powered by jev from @typesafeai that reduces your coding agent cost by 40% (verified on SWE-bench)
Make sure to use the built in skill so your coding agent knows to use jg for context collection github.com/dzhng/jevgrep
1
147

























