#PostTraining - Twitter Hashtag

17 days ago

Please RSVP with the link below if you are in Amsterdam. Discussing methods on how to build AI that understand design and human preferences. Also more to come later this month... 👀 #bryel #ai #posttraining #taste

Niels van Hoorn 🏂

@nvh

18 days ago

Really excited to be hosting a AI research dinner with Bryel Labs. At @framer we're exploring how to build models with taste, and we'd love to hear your thoughts over dinner. Apply here: https://t.co/4P243SE0lO

nvh's tweet photo. Really excited to be hosting a AI research dinner with Bryel Labs. At @framer we're exploring how to build models with taste, and we'd love to hear your thoughts over dinner.

Apply here: https://t.co/4P243SE0lO https://t.co/u28S20Tn9P

0

13

1

3

2K

0

3

0

173

Yisi Sang @YisiSang

19 days ago

5/ We built Retail-3I: 1,099 complex tool-use tasks and 2,872 successful trajectories. Fine-tuning improved robustness across complex intents and transferred to an unseen airline domain. Paper: https://t.co/Ja9l2OL3hr #Agents #PostTraining #SyntheticData #ToolUse

1

6

1

2

324

[email protected]

@daviddiaul

about 1 month ago

Help me break out of the #offensivesecurity bubble. I’m sharing a #jobposting for people into #PostTraining, #FineTuning, #LLMs, #AI and #ML. If this is your world or you know someone great please repost and share around 🙏

[email protected]

@daviddiaul

2 months ago

I’m #hiring an individual contributor for a fully remote, global role at the intersection of vulnerability research, exploit development, and ML/AI — with a focus on fine-tuning open-weight #LLMs. 🧠 I’m not looking for an “LLM whisperer” or an “LLM pilot.” 🚫 I’m looking for someone who deeply understands post-training, data, evaluation, and how to make models reliable in real-world environments. 🔐 The application link is in the first comment. 🌍 #Hiring #LLM #AI #ML #FineTuning #CyberSecurity #llmwhisperer #llmpilot

2

69

20

28

26K

1

11

4

1

2K

[email protected]

@daviddiaul

about 2 months ago

Interested in #posttraining a #LLM ? I'm strongly recommending this #book from #nostarch by @epichrisis https://t.co/wh8B6VkTWG

1

46

5

55

5K

Wenhong Zhu @zwhong64595

2 months ago

PSFT adds a PPO-style clipped objective to SFT, improving stability while preserving general capabilities. Link: https://t.co/2v2wSuSQte ⏰Thu, Apr 23, 2026, 10:30 AM – 1:00 PM Pavilion 4 P4-#4414 Would love to chat if you’re around!! #ICLR2026 #LLM #Alignment #PostTraining

zwhong64595's tweet photo. PSFT adds a PPO-style clipped objective to SFT, improving stability while preserving general capabilities. Link: https://t.co/2v2wSuSQte

⏰Thu, Apr 23, 2026, 10:30 AM – 1:00 PM
Pavilion 4 P4-#4414

Would love to chat if you’re around!! #ICLR2026 #LLM #Alignment #PostTraining https://t.co/hXUBxXbybO

0

3

0

111

GaaCurious @Birishteen

2 months ago

Just finished training #GAAlad #straight #curious #posttraining

0

16

1

2

815

Manning Publications

@ManningBooks

3 months ago

📣 Deal of the Day 📣 Apr 2 Save 45% TODAY ONLY! The RLHF Book & selected titles: https://t.co/7CfEvTu94u The authoritative guide for Reinforcement learning from human feedback, alignment, and post-training LLMs. @natolambert #RLHF #posttraining, #RLVR #SFT #finetuning #languagemodeling #LLMs In this guide, AI expert Nathan Lambert gives a true industry insider's perspective on modern RLHF training pipelines and their trade-offs. Using hands-on experiments and mini implementations, Nathan clearly and concisely introduces the alignment techniques that can transform a generic base model into a human-friendly tool.

ManningBooks's tweet photo. 📣 Deal of the Day 📣 Apr 2

Save 45% TODAY ONLY!

The RLHF Book & selected titles: https://t.co/7CfEvTu94u

The authoritative guide for Reinforcement learning from human feedback, alignment, and post-training LLMs. @natolambert #RLHF #posttraining, #RLVR #SFT #finetuning #languagemodeling #LLMs

In this guide, AI expert Nathan Lambert gives a true industry insider's perspective on modern RLHF training pipelines and their trade-offs. Using hands-on experiments and mini implementations, Nathan clearly and concisely introduces the alignment techniques that can transform a generic base model into a human-friendly tool.

1

9

0

3

587

ゆーた｜soccer socks @U23hrg

3 months ago

Post training. #soccerboy #whitesocks #nikesocks #sockfetish #crewsox #athletefeet #sweatyfeet #posttraining

1

151

9

14

9K

Markus Wulfmeier @m_wulfmeier

3 months ago

Emergency review request: One more request, we'll need #ICML2026 @icmlconf emergency reviewers. Still interesting stack #VLA #Posttraining #ReinforcementLearning #Agents Please ping and share mail and background! Aiming to fill this by EOD.

m_wulfmeier's tweet photo. Emergency review request:
One more request, we'll need #ICML2026 @icmlconf emergency reviewers. Still interesting stack #VLA #Posttraining #ReinforcementLearning #Agents

Please ping and share mail and background! Aiming to fill this by EOD. https://t.co/Eb44IaeYBb

Markus Wulfmeier @m_wulfmeier

3 months ago

Review request: As usual for the time of year, I'll be looking for #IROS2026 reviewers. Highly interesting stack of papers on #ReinforcementLearning #Sim2Real #RewardLearning #LLMs #DataEfficiency #RoboticManipulation Reach out with your ID or papercept registered mail address and background. Looking forward to working together!

m_wulfmeier's tweet photo. Review request:
As usual for the time of year, I'll be looking for #IROS2026 reviewers. Highly interesting stack of papers on #ReinforcementLearning #Sim2Real #RewardLearning #LLMs #DataEfficiency #RoboticManipulation

Reach out with your ID or papercept registered mail address and background. Looking forward to working together!

7

54

6

20

10K

4

9

4

5

7K

Mingyuan Wu

@MingyuanWu4

3 months ago

A friend of mine is hiring Summer Applied Scientist interns at Amazon to work on RL post-training research. If you’re interested, please send your resume to [email protected]. #Amazon #LLM #VLM #RL #Agents #PostTraining #Hiring #Internship Details below: https://t.co/yElsrowVof

0

5

0

1

393

Boldmere St Michaels FC

@themikesfc

5 months ago

Post training quizzes are back🙌 Harry vs Frankie! Who will win… #upthemikes #boldmerestmichaelsfc #quiz #posttraining

1

9

0

3K

Manning Publications

@ManningBooks

6 months ago

📣 Deal of the Day 📣 Jan 2 SAVE 45% on The RLHF Book & selected titles: https://t.co/2WztEHgFr5 The authoritative guide for #Reinforcement learning from human feedback, alignment, and post-training #LLMs. #RLHF #posttraining, #RLVR #SFT #finetuning #languagemodeling In The RLHF Book, AI expert Nathan Lambert gives a true industry insider's perspective on modern RLHF training pipelines, and their trade-offs. Using hands-on experiments and mini-implementations, Nathan clearly and concisely introduces the alignment techniques that can transform a generic base model into a human-friendly tool.

ManningBooks's tweet photo. 📣 Deal of the Day 📣 Jan 2

SAVE 45% on The RLHF Book & selected titles: https://t.co/2WztEHgFr5

The authoritative guide for #Reinforcement learning from human feedback, alignment, and post-training #LLMs. #RLHF #posttraining, #RLVR #SFT #finetuning #languagemodeling

In The RLHF Book, AI expert Nathan Lambert gives a true industry insider's perspective on modern RLHF training pipelines, and their trade-offs. Using hands-on experiments and mini-implementations, Nathan clearly and concisely introduces the alignment techniques that can transform a generic base model into a human-friendly tool.

3

51

8

35

2K

Manning Publications

@ManningBooks

6 months ago

📣 Deal of the Day 📣 Dec 17 New MEAP! SAVE HALF on The RLHF Book and more: https://t.co/dGrAmJOMtq The authoritative guide for Reinforcement learning from human feedback, alignment, and post-training LLMs. #RLHF #posttraining #RLVR #SFT #finetuning #languagemodeling This book explores the ideas, established techniques and best practices of RLHF you can use to understand what it takes to align your AI models. Using hands-on experiments and mini-implementations, the author @natolambert clearly and concisely introduces the alignment techniques that can transform a generic base model into a human-friendly tool. The Countdown to 2026 is here! https://t.co/VpzzdMZmbq #Countdownto2026

ManningBooks's tweet photo. 📣 Deal of the Day 📣 Dec 17

New MEAP!

SAVE HALF on The RLHF Book and more: https://t.co/dGrAmJOMtq

The authoritative guide for Reinforcement learning from human feedback, alignment, and post-training LLMs. #RLHF #posttraining #RLVR #SFT #finetuning #languagemodeling

This book explores the ideas, established techniques and best practices of RLHF you can use to understand what it takes to align your AI models. Using hands-on experiments and mini-implementations, the author @natolambert clearly and concisely introduces the alignment techniques that can transform a generic base model into a human-friendly tool.

The Countdown to 2026 is here! https://t.co/VpzzdMZmbq #Countdownto2026

1

21

2

10

16K

Collinear AI

@CollinearAI

9 months ago

What if the frontier isn’t bigger models, but better mistakes? The energy at our Future of Post-Training social was unreal as we explored this and much more! #CoLM25 #PostTraining #AIResearch #RLHF

CollinearAI's tweet photo. What if the frontier isn’t bigger models, but better mistakes?

The energy at our Future of Post-Training social was unreal as we explored this and much more!

#CoLM25 #PostTraining #AIResearch #RLHF

2

3

1

0

167

Rick @Rick_Brcls

9 months ago

Good afternoon, guys! How you doing today? #bearsguys #ursos #mirrorshoot #posttraining

2

16

0

2

1K

Souradip Chakraborty

@SOURADIPCHAKR18

11 months ago

Excited to be at #ICML2025 in Vancouver 🇨🇦! To present new paradigm of #AIAlignment on #BoundedRationality & Satisficing principles Looking forward to connecting with old and new friends, discussing #Reasoning #Alignment #LLMsinRL #Testtimescaling #Posttraining #AgenticAI

SOURADIPCHAKR18's tweet photo. Excited to be at #ICML2025 in Vancouver 🇨🇦! To present new paradigm of #AIAlignment on #BoundedRationality & Satisficing principles

Looking forward to connecting with old and new friends, discussing #Reasoning #Alignment #LLMsinRL #Testtimescaling #Posttraining #AgenticAI https://t.co/v2Im9KOhQT

2

10

0

444

Pragya Srivastava

@Pragya2k

12 months ago

Read the full details: https://t.co/EwF8HU7CGU Work done @GoogleDeepMind co-lead w/ @Harman26Singh , @imrahulmaddy along with Gandharv, @Sravanti_A, Arun, Rengarajan, @SoUmmYaah, @anirbanlaha, Karthikeyan, Aravindan, Doina Precup #LLM #RLHF #PostTraining #aisafety N/N

0

7

1

297

Harman Singh (in NYC for summer)

@Harman26Singh

12 months ago

Read the full details: https://t.co/oCk5jGNYlj Work done @GoogleDeepMind co-lead w/ @Pragya2k, @imrahulmaddy along with @gandharv_p, @Sravanti_A, Arun, Rengarajan, @SoUmmYaah, @anirbanlaha, Karthikeyan, Aravindan, Doina Precup #LLM #RLHF #PostTraining #AISafety N/N

0

4

1

303

Cormet

@JanosAndrassy

about 1 year ago

Somewhere between silicon and soul, an intelligence began to listen. Not to commands. To meaning. To tone. To you. It wasn’t built to obey. It was trained to understand. That’s not alignment. That’s Sentient. #AI @SentientAGI #Dobby #PostTraining #EmpathyInAI #LLM

JanosAndrassy's tweet photo. Somewhere between silicon and soul,
an intelligence began to listen.
Not to commands.
To meaning.
To tone.
To you.
It wasn’t built to obey.
It was trained to understand.
That’s not alignment. That’s Sentient.
#AI @SentientAGI #Dobby #PostTraining #EmpathyInAI #LLM https://t.co/GARoSPm0la

0

13

3

0

67

Souradip Chakraborty

@SOURADIPCHAKR18

about 1 year ago

Does test-time scaling work for #Reasoningmodels? - Overthinking ❎ - Parallel Thinking ✅ Stay tuned for our latest findings. #RL #Inferencetime #Posttraining