Bertram Højer
@brtrm.bsky.social
CS PhD Student @ IT University of Copenhagen |
NLP, AI reasoning and seeming intelligence
https://bertramhojer.github.io |
nlpnorth.bsky.social
NLP, AI reasoning and seeming intelligence
https://bertramhojer.github.io |
nlpnorth.bsky.social
You can find the answers to more interesting questions regarding the beliefs of researchers on LLMs and "Intelligence" in the full paper!
This work was done in collaboration with @terne.bsky.social, @heinrichst.bsky.social, and @annarogers.bsky.social ✨
This work was done in collaboration with @terne.bsky.social, @heinrichst.bsky.social, and @annarogers.bsky.social ✨
May 30, 2025 at 8:53 AM
You can find the answers to more interesting questions regarding the beliefs of researchers on LLMs and "Intelligence" in the full paper!
This work was done in collaboration with @terne.bsky.social, @heinrichst.bsky.social, and @annarogers.bsky.social ✨
This work was done in collaboration with @terne.bsky.social, @heinrichst.bsky.social, and @annarogers.bsky.social ✨
❓Do researchers believe current LLM based systems are intelligent?
✔️Generally not - although junior researchers are more willing to attribute intelligence to current systems!
✔️Generally not - although junior researchers are more willing to attribute intelligence to current systems!
May 30, 2025 at 8:53 AM
❓Do researchers believe current LLM based systems are intelligent?
✔️Generally not - although junior researchers are more willing to attribute intelligence to current systems!
✔️Generally not - although junior researchers are more willing to attribute intelligence to current systems!
❓What do AI researchers believe to be key criteria for intelligence?
✔️Researchers across fields agree that Generalization, Adaptability, & Reasoning are key components of intelligence!
✔️Researchers across fields agree that Generalization, Adaptability, & Reasoning are key components of intelligence!
May 30, 2025 at 8:53 AM
❓What do AI researchers believe to be key criteria for intelligence?
✔️Researchers across fields agree that Generalization, Adaptability, & Reasoning are key components of intelligence!
✔️Researchers across fields agree that Generalization, Adaptability, & Reasoning are key components of intelligence!
This work was done in collaboration with @olliejarvis.bsky.social and @heinrichst.bsky.social!
Looking forward to presenting our poster alongside Oliver at the conference in Singapore! Hope to see you there! ✨
Looking forward to presenting our poster alongside Oliver at the conference in Singapore! Hope to see you there! ✨
March 31, 2025 at 2:27 PM
This work was done in collaboration with @olliejarvis.bsky.social and @heinrichst.bsky.social!
Looking forward to presenting our poster alongside Oliver at the conference in Singapore! Hope to see you there! ✨
Looking forward to presenting our poster alongside Oliver at the conference in Singapore! Hope to see you there! ✨
We of course took the chance to discuss:
🔹the implications of our results for LLM reasoning
🔹the use of the term "reasoning" to discuss LLM computations
🔹 whether LLMs can be said to do reasoning at all 🤔
🔹the implications of our results for LLM reasoning
🔹the use of the term "reasoning" to discuss LLM computations
🔹 whether LLMs can be said to do reasoning at all 🤔
March 31, 2025 at 2:27 PM
We of course took the chance to discuss:
🔹the implications of our results for LLM reasoning
🔹the use of the term "reasoning" to discuss LLM computations
🔹 whether LLMs can be said to do reasoning at all 🤔
🔹the implications of our results for LLM reasoning
🔹the use of the term "reasoning" to discuss LLM computations
🔹 whether LLMs can be said to do reasoning at all 🤔
We:
1️⃣ Derive steering vectors from LLM representations on "reasoning" tasks.
2️⃣ Apply them as a linear transformation to the representational space to improve "reasoning" performance.
A very simple tweak resulting in a slight improvement! 📈
1️⃣ Derive steering vectors from LLM representations on "reasoning" tasks.
2️⃣ Apply them as a linear transformation to the representational space to improve "reasoning" performance.
A very simple tweak resulting in a slight improvement! 📈
March 31, 2025 at 2:27 PM
We:
1️⃣ Derive steering vectors from LLM representations on "reasoning" tasks.
2️⃣ Apply them as a linear transformation to the representational space to improve "reasoning" performance.
A very simple tweak resulting in a slight improvement! 📈
1️⃣ Derive steering vectors from LLM representations on "reasoning" tasks.
2️⃣ Apply them as a linear transformation to the representational space to improve "reasoning" performance.
A very simple tweak resulting in a slight improvement! 📈
That this is a misrepresentation is something we also show in our forthcoming survey paper on Intelligence and LLMs in researcher communities (preprint coming).
March 6, 2025 at 4:13 PM
That this is a misrepresentation is something we also show in our forthcoming survey paper on Intelligence and LLMs in researcher communities (preprint coming).
Sorry, my bad for being a bit quick there! When you say "popular AI denial" I think more of people just not wanting to accept that these systems are *actually* intelligent. I think it's a shame to discuss healthy skepticism in a derogatory manner ..
March 3, 2025 at 8:41 AM
Sorry, my bad for being a bit quick there! When you say "popular AI denial" I think more of people just not wanting to accept that these systems are *actually* intelligent. I think it's a shame to discuss healthy skepticism in a derogatory manner ..
I disagree, and what exactly do you mean by AI denial? One can state that there are legitimate (limited) use-cases of modern AI while not subscribing to the belief that current models show "sparks of AGI".
March 3, 2025 at 7:54 AM
I disagree, and what exactly do you mean by AI denial? One can state that there are legitimate (limited) use-cases of modern AI while not subscribing to the belief that current models show "sparks of AGI".
Reposted by Bertram Højer
Not to mention that rather than being well-established observations, (1) is difficult if not impossible to assess without a proper definition of intelligence and (3) seems to be complete blather.
Three Observations
Our mission is to ensure that AGI (Artificial General Intelligence) benefits all of humanity.
Systems that start to point to AGI* are coming into view, and so we think it’s important to...
blog.samaltman.com
February 10, 2025 at 6:21 AM
Not to mention that rather than being well-established observations, (1) is difficult if not impossible to assess without a proper definition of intelligence and (3) seems to be complete blather.