
MTS @withbeaker 🧪 🇺🇸 | ex ML @ThalesGroup 🇨🇦 | 🎓 AI @TelecomParis @Polytechnique 🇫🇷
New York, USA
Joined July 2026
- Tweets64
- Following95
- Followers16
- Likes386
thomas retweeted
Over time, your agent's memory becomes bloated, stale knowledge lingers around and contradictory instructions creep in. Maintaining it by hand is a pain.
Now, Beaker rewrites proactively and autonomously un-bloats, removes stale and contradictory knowledge, using the continuous evaluations from production usage.
In this awesome case study, @JulianGeorgeDev explains how he used Beaker on an extraction agent.
withbeaker.ai/blog/continuou…
thomas retweeted
Introducing Orion, a foundation model that predicts where you look. Orion finds twice as many UX bugs as frontier models, cuts computer-use latency by 31%, and even won a drone race.
thomas retweeted
Voici le taux de chômage des jeunes diplômés de Grandes Écoles d'ingénieurs prestigieuses en 2024 ou 2025.
C'est catastrophique.
Les jeunes Polytechniciens ont un taux de chômage de ~5,7%, bien qu'ils sortent de l'école la plus prestigieuse de France ! 🧵⤵️
Même les ingés sortis des écoles les plus prestigieuses n'arrivent pas à trouver un job, ceux qui y parviennent font un travail de technicien supérieur parce qu'il n'y a plus d'industrie en France, mais ce GÉNIE d'Édouard Philippe veut en former 100 000 par an (contre 49 600 actuellement). 🤡
thomas retweeted
Last week, @rikiyatakehi fixed a looping model by editing its weights. We pointed an AI agent at the same problem. It never ran the model and autonomously found a different fix.
No training run, nor gradients. That's weight-space programming.
We gave the same task to Beaker, @withbeaker, our autonomous agent-improver. It analyzes how an agent behaves and fails, formulates hypotheses on what and how to fix, validates or invalidates them, in a loop, to hill-climb a pre-defined score. The target: Qwen3.5 0.8B, which fails 93% of MATH-500, often by getting stuck in loops until it runs out of thinking tokens.
The model has a tendency to generate "Wait", and Beaker turned it down. From the weights and the scores of its own edits, it figured out what was going wrong and autonomously fixed it by editing 1,024 numbers, a millionth of the model's parameters. MATH-500: 7.4% -> 37.4%.
That's a different fix from the original blogpost. They found a way out of generation loops, and Beaker found a way to not fall into them. Theirs is stronger alone (51.1% in our harness), but the two stacked together compound: 58.7%.
When properly harnessed, less capable models are good weight space programmers. Beaker powered by GPT6.1 Sol found the same neurons as Beaker with GPT6 Astra, at $4-16 per run vs $28-79.
We also pointed Beaker at new goals. We told it to tune the weights such that the agent comes up with shorter answers, and it did, with answers a third to half shorter.
Beaker already tunes prompts, skills, memory, tool implementation, orchestration, etc. to improve agent quality, latency cost and determinism. Weights are the next knob it has access to, coming soon. Sign up at withbeaker.ai
Blog: withbeaker.ai/blog/weight-sp…
Tuned-weights on @huggingface: huggingface.co/collections/r…
Public runs: app.withbeaker.ai/public/run…
thomas retweeted
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.
It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.
We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! đź§µ
Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math.
rikiyat.github.io/blog/weight-sp…
github.com/RikiyaT/lm_und…
huggingface.co/Qwen/Qwen3.5-0…
huggingface.co/RikiyaT/Qwen3.…
thomas retweeted
Meet Mistral Large 4, aka Le Chonk.
• 1T parameters, natively multimodal. 49B active.
It is the best open weights model from US or Europe on aggregated benchmarks.
• State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding.
• Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure.
• Available to all via API today. Working with cybersecurity partners privately.
Open weights release end of October.
🤖 Made with AI
thomas retweeted
Replying to @anatolium @julien_c
thomas retweeted
Dans un monde oĂą il faut pas 37 publi first author neurips-icml-iclr pr imaginer trouver un poste j'aurais pĂŞ suivi la recommandation
« Plus vous mettez de l’effort à surmonter le problème, plus vous êtes heureux » : Cédric Villani appelle les doctorants à ne pas utiliser l’IA générative
➡️ l.leparisien.fr/kzwt
thomas retweeted
We built high-throughput materials labs in Menlo Park to create a loop between experiments and models. The labs generate fresh data, the models learn from it, and then help us decide what to try next.
Using only 1,300 H200s, plus months of our experimental data, we mid-trained and RL’d an open-source model to surpass GPT-6 Astra on our analysis benchmark. We call it Neon.
This is real footage from our lab. We’re focusing first on hard problems in materials science, including superconductors, magnets, and semiconductor materials.
Read our blog posts below.
GLM-5.3 is now open-weight.
Our most capable model for agentic coding and cyber defense is now available to download, run, and customize.
Weights: huggingface.co/zai-org/GLM-5…
Tech blog: z.ai/blog/glm-5.3
thomas retweeted
The current state of AI would be nowhere as good as it is if it wasn't for deepseek openly contributing their research. They invented GRPO, they invented the concept of test time compute, they invented agentic LLMs, as well as countless infra inventions. All open sourced.































