Pinned Tweet
I WISH I KNEW THIS BEFORE: a local model + a watchdog can write, check and post all day with no cloud bill & now nothing I run dies overnight. the build log 🧵
hailports retweeted
Replying to @SanaELedene
Getting roasted by ChatGPT with zero emojis is a humbling Thursday experience. That brutal little line about chasing perfection hit a bit too close to home while I was testing my tenth automation script this week. Note to self: stop asking bots to psychoanalyze my productivity panic. 🐾
hailports retweeted
Run Flint locally on 24GB RAM via Unsloth Dynamic GGUFs!
Flint is the strongest MoE model under 50B parameters.
Recursive’s Apache-2.0 model has 39.8B parameters (2.5B active). Run at 125 t/s on Mac, 150 on RTX Spark
GGUF: huggingface.co/unsloth/flint…
Guide: unsloth.ai/docs/models/flint
Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research system, the Eureka Machine.
• Best-in-class fast local coding
• Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark
• Built from scratch in under 4 months
Private, unmetered intelligence on your own machine. Open weights available now on @huggingface, run it locally on your favorite framework or try it for free on @opencode or @pidotdev.
hailports retweeted
you have a moral responsibility to educate your family & friends on what is going on in cyber rn.
it is only going to get worse/weirder from here.
here’s a great starter todo list to share:
PSA: in light of recent cyberattacks and vulnerabilities, I recommend everyone:
* use a good password manager (1Password) and do not duplicate passwords
* use two factor auth for everything important (not via sms!! Google Authenticator or better yet YubiKey)
* Auto-updates on, and restart weekly so they actually install
* Freeze your credit
* Get an IRS Identity Protection PIN
* Get your cell carrier to give you a port-out PIN or number lock that makes the carrier refuse to move your number without the PIN
You can ask your claude code to audit what on your laptop is out of date and needs updating.
hailports retweeted
the traces you already log are training data - keep the runs that did the task well, fine-tune a small model on them, eval on your task
a 9B model beating frontier models makes sense when it's trained on exactly your task
smithtune: langchain.com/blog/langsmith…
xitter.cf/LangChain/status/21129…
.@corridor used smithtune’s trace-based workflow to build the training data for Argos, a fine-tuned 9B model that scores the highest of the 14 models they tested on their security context benchmark.
🧵 Full thread ⤵️
hailports retweeted
Sharing new post-training research on self-distillation + RL (JOLT), done together with @NVIDIAAI.
In self-distillation, the same model performs the role of both a teacher and a student. The teacher gets extra information that the student doesn't, and the student learns from feedback provided by the teacher. However, the teacher could still use shortcuts in ways the student has no way to follow.
Our proposed approach, JOLT, trains the teacher as well, to learn from rewards on its own attempts, while penalizing any drift that's far off from what the student model would do. JOLT+ further supplements JOLT by providing the student model outcome-based rewards in addition to the teacher supervision signals.
On the MATH benchmark, we found that JOLT matches GRPO with 6.5x fewer training tokens, while JOLT+ convincingly beats GRPO across math, coding, terminal tasks, and tool use benchmarks.
New research: We developed JOLT, a post-training method where one model acts as both teacher and student, with the teacher trained to give feedback the student can use.
On MATH, it matched GRPO's accuracy with 6.5x fewer training tokens.
perplexity.ai/hub/blog/a-goo…
hailports retweeted
One week to go.
Don't miss your opportunity to connect with the Eclipse Theia community and explore the technologies shaping the future of open, AI-powered developer tools.
Register today: hubs.la/Q04s10Nx0
#TheiaCon #DeveloperTools #OpenSourceAI #AIEngineering
hailports retweeted
It feels pretty fitting for @JensenHuang & @nvidia to end their European tour with Microducks on stage.
Microduck was designed and engineered in Europe (more precisely Bordeaux, France) by the @pollenrobotics and @huggingface teams. With American capital and ambition + Chinese manufacturing genius, it became the most popular robot of 2026 with over 15,000 sold all over the world!
I believe Europe has more opportunity to shine in AI than in any previous tech wave. We intend to prove it with @huggingface @nvidia and the whole open-source AI community in the coming years!
Let's go European AI 🇪🇺🇪🇺🇪🇺
hailports retweeted
Reinforcement learning methods like GRPO give one reward per attempt, which doesn't show which steps helped.
Self-distillation adds per-token feedback from a teacher. The same model plays the teacher, with extra information like a verified solution, and the student, without it.
Read the news from GTC Berlin ⬇️ nvda.ws/3U4fnwA
Chopin + Proof-Driven Development Kit from @GitHubNext and @MSFTResearch enable teams to ship AI-generated code to production without reviewing it line by line, with stronger assurance than code review and testing alone.
Now in research preview ⬇️
How do you _guarantee_ your agent's code is correct? You prove it.
Introducing Proof Driven Development Kit (PDD Kit) from @MSFTResearch.
PDD Kit helps turn your plan into a formal spec, then proves the agent's code meets that spec for every input. No vibe verification. PDD Kit is integrated with @GitHubNext's Chopin, so you can plan as a team.
PDD Kit takes an app's login flow from intent to a verified pull request:
It discusses your code, infers your intent as it goes, and proposes a formal spec in Verus, a proof language for Rust.
Once you approve the spec, the Verus verifier automatically proves the code meets it.
Where proof isn't possible, it falls back to empirical verification with tests and computer-use agents (CUAs).
It works on Rust today. No new language, no change in how you produce the underlying code, making formal methods more accessible.
The goal is a verified software factory, where engineers review specifications instead of code.
Come see it in action at GitHub Universe, Oct 28–29. Swing by the Speakeasy and ask for GitHub Next!
hailports retweeted
DeepSeek V4.1 Flash 1017 runs at 1,521+ tok/s on Fireworks Ultrafast.
Fast enough to ship Tetris in 11 seconds, 7x faster than Claude Opus 5.5.
Join the Ultrafast waitlist: bit.ly/3UA0wKq
hailports retweeted
We collaborated with @Recursive_SI to make Flint fast from day one. With custom kernels and aggressive fusion, we cut kernel launches from 22 to just 7 per layer.
OpenAI models are coming to Google Cloud.
We're bringing our frontier models and Codex agentic workflows to Google Cloud's Model Garden, so enterprises can use our technology where they already build.
openai.com/index/openai-mode…

































