Toutes les curations

6 curations · 1314 membres · fenêtre de 12 h, demi-vie 6 h, seuil 2 relayeurs

Fenêtre 6 h 12 h 24 h 2 j 3 j 7 j
Montrer Les deux Liens 4 Tweets 12
Seuil 2 relayeurs 3 relayeurs 4 relayeurs 5 relayeurs 6 relayeurs Tout remettre
4liens
12tweets
88740posts lus
953auteurs
9198liens en base
1470 hde recul

Les liens 4

Classés par auteurs distincts, jamais par audience.

1

A Theoretical Framework for Self-Play Theorem Proving Algorithms

Self-play, a type of training algorithm that enables a model to self-improve, has recently shown promising empirical results in the context of formal theorem proving using Large Language Models (LLMs). (Dong & Ma, 2025) instantiate self-play with two cooperating agents: a prover, which proves theorems, and a conjecturer, which generates new theorems as a curriculum to the prover. In this paper, we provide a theoretical framework for understanding the self-improvement capabilities of self-play algorithms for theorem proving. First, we formalize the set of theorems as a graph, with nodes as theo

2 relayeurs à 2 · il y a 6 h arXiv.org ai-iahigh-signal
Qui l'a relayé
Stanford NLP Group @stanfordnlp · 08/11 21:43 Natural Language Processing/Machine Learning @chrmanning @jurafsky @percyliang @ChrisGPotts @tatsu_hashimoto @MonicaSLam @Diyi_Yang @YejinChoinka @StanfordAILab
How can an LLM self-improve at theorem proving? Inspired by STP (Dong & Ma, 2025), we propose a theoretical framework for understanding prover-conjecturer self-play algorithms. NeurIPS 2026, Sydney Poster Session 2, Tue 5-8pm @ Hall 1-4. 1/8
Stanford AI Lab @StanfordAILab · 08/11 20:21 The Stanford Artificial Intelligence Laboratory (SAIL), a leading #AI lab since 1963. ⛵️🤖 Emmy-winning video: https://t.co/lV9smZTC1m
How can an LLM self-improve at theorem proving? Inspired by STP (Dong & Ma, 2025), we propose a theoretical framework for understanding prover-conjecturer self-play algorithms. NeurIPS 2026, Sydney Poster Session 2, Tue 5-8pm @ Hall 1-4. 1/8
2

How ShipStation Global built an AI IT help desk on Amazon Bedrock AgentCore | Amazon Web Services

ShipStation Global's engineering team built Deckhand, an AI IT help desk agent for Slack on Amazon Bedrock AgentCore. It answers routine IT questions from a curated knowledge base, reads error-message screenshots, and files Jira tickets. In its first three months it resolved 97.5% of channel queries with a 96% positive feedback rating.

2 relayeurs à 2 · il y a 6 h Amazon Web Services high-signal
Qui l'a relayé
Omar Khattab @lateinteraction · 08/11 19:28 prof @MIT CSAIL | ColBERT, https://t.co/ZZaSzaRaZ7 (@DSPyOSS), GEPA, RLMs, Pedagogical RL
Nice section in this AWS post on ShipStation Global’s AI IT help desk. A dspy.RLM module holds their entire Slack history as a variable, and mines it into a knowledge base of resolved issues.
Stanford NLP Group @stanfordnlp · 08/11 21:43 Natural Language Processing/Machine Learning @chrmanning @jurafsky @percyliang @ChrisGPotts @tatsu_hashimoto @MonicaSLam @Diyi_Yang @YejinChoinka @StanfordAILab
Nice section in this AWS post on ShipStation Global’s AI IT help desk. A dspy.RLM module holds their entire Slack history as a variable, and mines it into a knowledge base of resolved issues.
3

GitHub - scottleimroth/signal-dog: Hermes Agent plugin: listens through the microphone for door knocks, appliance beeps and alarms and tells you in chat. Built by a deaf developer. Not a certified smoke alarm.

Hermes Agent plugin: listens through the microphone for door knocks, appliance beeps and alarms and tells you in chat. Built by a deaf developer. Not a certified smoke alarm. - scottleimroth/signal...

2 relayeurs à 2 · il y a 8 h GitHub ai-iahigh-signal
Qui l'a relayé
Teknium 🪽 @Teknium · 08/11 19:05 Cofounder and Lead Engineer - Hermes Agent @NousResearch, prev @StabilityAI Github: https://t.co/LZwHTUFwPq HuggingFace: https://t.co/sN2FFU8PVE
I'm deaf, so I never hear the fridge alarm, an oven timer or a knock at the door. I built Signal Dog for @NousResearch's Hermes Agent Plugin Hackathon: a plugin that listens through the microphone and tells you in chat. No audio kept.
Robert Scoble @Scobleizer · 08/11 19:15 The automated life | San Francisco/Silicon Valley AI, robotics, BCIs | Ex-Microsoft, Rackspace, Fast Company | Wrote eight books about the future.
I'm deaf, so I never hear the fridge alarm, an oven timer or a knock at the door. I built Signal Dog for @NousResearch's Hermes Agent Plugin Hackathon: a plugin that listens through the microphone and tells you in chat. No audio kept.

Les tweets 12

Axe indépendant : repris sans regarder les liens.

1
J
Justin Lo @loresjpg · 01:37
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
6 relayeurs à 14 · il y a 2 h Voir sur X
Qui l'a repris
J Julian Schrittwieser” Hamel Husain” Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)” Ofir Press” Ethan Mollick” Kosta Derpanis
Ce qu'ils en ont dit
J
Julian Schrittwieser @Mononofu a cité · 01:37
Making novel variations of evals is very useful, public evals tend to get memorized!
Hamel Husain @HamelHusain a cité · 01:16
I see some are drawing the wrong inference from this study: they are focusing on this meta benchmark as yet another benchmark for model picking, i.e. open vs closed models, model families etc. That’s too narrow of an interpretation! You need to do your own private evals on
Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞) @teortaxesTex a cité · 08/11 22:00
holy shit, an art form of scientific grift next METR/Epoch/AA employee right here you all need to work on your epistemic hygiene
Ofir Press @OfirPress a cité · 08/11 21:26
GPT-5.6 Sol and Luna were built by roughly the same people using roughly the same infra, I don't think we can blame the 20 point difference in Luna just on memorization. There's something else being tracked here in addition to memorization. Maybe MaxxBench questions are slightly
Ethan Mollick @emollick a cité · 08/11 18:33
2
Pushmeet Kohli @pushmeet · 08/11 20:37
Across our projects @GoogleDeepMind, we are witnessing a genuine phase transition in the pace of scientific discovery. You will see a glimpse of this in our releases in the next few weeks.
5 relayeurs à 7 · il y a 7 h Voir sur X
Qui l'a repris
Lucas Beyer (bl16)” E echo.hive Dr Singularity” elvis” Chubby♨️”
Ce qu'ils en ont dit
Lucas Beyer (bl16) @giffmana a cité · 08/11 20:37
Pre-announcing the pre-announcement
Dr Singularity @Dr_Singularity a cité · 08/11 18:30
1000 scientific breakthroughs drop from Google incoming?
elvis @omarsar0 a cité · 08/11 17:08
Been working for this moment for over a decade. What I've witnessed behind the scenes, together with what we have been building, tells me we are about to enter a truly incredible era of AI-powered scientific discovery. It's an incredible time to be doing research. I will be
Chubby♨️ @kimmonismus a cité · 08/11 15:36
2026 is the turning point for humanity. Google DeepMind’s Pushmeet Kohli says AI is accelerating scientific discovery and that upcoming releases will offer a glimpse of the progress. He says the team also aims to help the wider scientific community use these tools responsibly.
3
R
Ryo Lu @ryolu_ · 02:14
when we can do anything, do we still know what we want? the full talk from @aiDotEngineer shanghai. every slide handmade in keynote, subs in 中文 and english
2 relayeurs à 2 · il y a 59 min Voir sur X
Qui l'a repris
AI.Engineer 🔜 CODE swyx 🔜 aie.codes
4
The New York Times @nytimes · 08/11 22:30
Breaking News: Nvidia opened an investigation into Jensen Huang, its CEO, after he acknowledged to the company’s board that he had been intimate with a business executive who U.S. intelligence determined to be a Chinese spy.
nytimes.com Nvidia Opens Investigation Into Jensen Huang’s Relationship With Chinese Spy Mr. Huang, the company’s chief executive, acknowledged on Sunday that he was intimate with a business executive who U.S. officials had determined was working for Chinese intelligence.
3 relayeurs à 3 · il y a 5 h Voir sur X
Qui l'a repris
A Alex Volkov” john allard” Ethan Perez
Ce qu'ils en ont dit
A
Alex Volkov @altryne a cité · 08/11 22:30
Nvidia's board opened an independent investigation into allegations against CEO Jensen Huang! Jensen had published an email to the company acknowledging being unfaithful to his wife of 41 years, and didn't mention the allegations beyond the investigation mention. Full message
john allard @john__allard a cité · 08/11 22:18
having an affair with a suspected chinese spy is bad obvi, but it doesn’t materially update my opinion of jensen. i already thought he was a pos when he started groveling at trump’s feet for permission to sell h200s to china
5
S
Shaun Maguire @shaunmmaguire · 01:17
1) Jensen is one of the greatest entrepreneurs of this generation 2) he did something incredibly dumb 3) it was bad for America 4) but my guess is there was no bad intention 5) two mistakes don’t make a right, and I believe Jensen is irreplaceable for America’s AI leadership
2 relayeurs à 2 · il y a 2 h Voir sur X
Qui l'a repris
Bing Xu” Robert Scoble
Ce qu'ils en ont dit
Bing Xu @bingxu_ a cité · 01:17
+1 Jensen is the irreplaceable leader of 🇺🇸 AI. I'm proud of having worked directly or indirectly with him for the past 15 years. He's a true patriot who made a dumb mistake every man may make. We should continue to trust him.
6
H
Hey, It's Erin! @TheTruestErin · 02:41
Watch Jesse’s smile fade micrometer by micrometer as he realizes that yes actually, that is indeed the plan. Watch him slowly realize that his party will never receive votes again. You can literally see his mouth straighten out if you watch the video
2 relayeurs à 2 · il y a 45 min Voir sur X
Qui l'a repris
Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)” Ben (no treats)
Ce qu'ils en ont dit
Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞) @teortaxesTex a cité · 02:41
I didn’t realize that libs genuinely want One Billion Americans
7
J
Jameson Hodge @jamesonhodge · 01:01
I only make serious software
2 relayeurs à 2 · il y a 2 h Voir sur X
Qui l'a repris
A Alex Volkov” Mat Velloso”
Ce qu'ils en ont dit
A
Alex Volkov @altryne a cité · 01:01
Be very very careful, if you watch this video your whole timeline is going to be this thing doing different songs.
Mat Velloso @matvelloso a cité · 08/11 22:41
This might be the best piece of software ever built
8
B
Bill Ackman @BillAckman · 01:06
An alert: @JensenHuang is human. And he is an incredible human. Even incredible humans make mistakes. He takes full responsibility as he should. We should all support him and his family. Onward.
2 relayeurs à 2 · il y a 2 h Voir sur X
Qui l'a repris
Denny Zhou Rohan Paul”
Ce qu'ils en ont dit
Rohan Paul @rohanpaul_ai a cité · 08/11 22:30
🎯🎯
9
will brown @willcb · 03:00
2027 is gonna be about engines
2 relayeurs à 3 · il y a 28 min Voir sur X
Qui l'a repris
swyx 🔜 aie.codes” Joanne Jang”
Ce qu'ils en ont dit
swyx 🔜 aie.codes @swyx a cité · 03:00
are you listening anon?
Joanne Jang @joannejang a cité · 08/11 18:18
vroomberg terminals
10
T
tae kim @firstadopter · 00:11
Nvidia CEO Jensen Huang's email to Nvidia employees: To my colleagues at NVIDIA, I owe my family and all of you an apology. I was unfaithful to my wife. My actions hurt her and our children. There is no excuse for what I did. I am deeply sorry. Throughout my life, my family
2 relayeurs à 2 · il y a 3 h Voir sur X
Qui l'a repris
Sam Bhagwat” Mike Bradley
Ce qu'ils en ont dit
Sam Bhagwat @calcsam a cité · 00:11
This reminds me of a story a mentor of mine told me 15 years ago, that his dad (Robert) told him. Robert grew up in northwest Washington. He and his high school sweetheart both had horrible family situations. They decided to elope the day after their graduation. This was
11
B
Ben South @bnj · 08/11 23:13
Sunday afternoon, 2026. I unfold my pocket supercomputer and give the day’s orders to a few hundred thinking machines. Then I summon a robot cab. It arrives in four minutes. I find this slow.
2 relayeurs à 2 · il y a 4 h Voir sur X
Qui l'a repris
Grace Li Jenny
12
W
Watcher.Guru @WatcherGuru · 08/11 22:29
JUST IN: 🇺🇸🇨🇳 Nvidia $NVDA CEO Jensen Huang sends letter to employees after being targeted by female Chinese spy: "I was unfaithful to my wife. My actions hurt her and our children. There is no excuse for what I did." "I am fully committed to NVIDIA and will work to earn back
2 relayeurs à 2 · il y a 5 h Voir sur X
Qui l'a repris
Krish Gupta” Rahul”
Ce qu'ils en ont dit
Krish Gupta @krishgupta72 a cité · 08/11 22:29
Bro is more committed to his company than to his wife and family. Bullish for Nvidia bearish for the kids☠️
Rahul @sairahul1 a cité · 08/11 21:29
holy shit: jensen huang just told nvidia employees "I was unfaithful to my wife." US officials reportedly suspect the woman was a chinese spy. rubio had warned trump officials. now nvidia's board has opened an independent investigation. the company powering all of AI opens