Joseph Miller's Shortform

This is an attempt to compile all publicly available primary evidence relating to the recent death of Suchir Balaji, an OpenAI whistleblower.

This is a tragic loss and I feel very sorry for the parents. The rest of this piece will be unemotive as it is important to establish the nature of this death as objectively as possible.

I was prompted to look at this by a surprising conversation I had IRL suggesting credible evidence that it was not suicide. The undisputed facts of the case are that he died of a gunshot wound in his bathroom sometime around November 26 2024. The police say it was a suicide with no evidence of foul play.

Most of the evidence we have comes from the parents and George Webb. Webb describes himself as an investigative journalist, but I would classify him as more of a conspiracy theorist, based on a quick scan of some of his older videos. I think many of the specific factual claims he has made about this case are true, though I generally doubt his interpretations.

Webb seems to have made contact with the parents early on and went with them when they first visited Balaji's apartment. He has since published videos from the scene of the death, against the wishes of the parents^[1] and as a result the parents have now unendorsed Webb.^[2]

List of evidence:

• He didn't leave a suicide note.^[3]
• The cause of death was decided by the authorities in 14 (or 40, unclear) minutes.^[4]
• The parents arranged a private autopsy which "made their suspicions stronger".^[5]
• The parents say "there are a lot of facts that are very disturbing for us and we cannot share at the moment but when we do a PR all of that will come out."^[6]
• The parents say "his computer has been deleted, his desktop has been messed up".^[7]
  • Although the parents also said that their son's phone and laptop are not lost and are in escrow.^[8][9] I think the claim of the computer being deleted is more up-to-date, but I'm not sure as that video was posted earlier.
• It was his birthday and he bought a bike on the week of his death.^[10]
• He said he didn't want to work and he was going to take a gap year, "leaving the AI industry and getting into machine learning and neuroscience" but also he was planning to start his own company and was reaching out to VCs for seed funding.^[11]
• He had just interviewed with the New York Times and he was supposed to do further interviews in the days after his death.^[12]
• According to the parents and Webb, there are signs of foul play at the scene of death:
  • There are several areas with blood, [Confirmed from pictures] suggesting to Webb and the parents he was trying to crawl out of the bathroom.^[13][14]
  • Webb says the body had bleeding from the genitals.^[15] I'm not aware of a better source for this claim, so right now I think it is probably false.
  • The trash can in the bathroom was knocked over.^[13][16] [Confirmed from pictures].
  • A floss pick is on the floor.^[13][17] [Confirmed from pictures]. Webb interprets this as being dropped at the time of death, suggesting that Balaji was caught by surprise.
  • The path of the bullet through the head missed the brain. I'm not sure what the primary source for this is, but I'm not sure why Webb would invent this, so I think it's true. Webb takes this as evidence that it was shot during a struggle rather than at the considered pace of a suicide.^[18]
    • The bullet did not go all the way through the head, suggesting a lower caliber, quiet gun.^[19]
  • According to Webb and the parents, the drawers of the apartment were ransacked, the cupboards were thrown open.^[8][20] From the pictures this looks false, although the apartment is very messy and his hiking backpacks are strewn around with much of their contents on the table (he had recently returned from a hiking trip).
  • The blood on the sink looks different, suggesting to Webb that it came from a different part of the body.^[21] This is not obvious to me from the pictures but not implausible and the main pool of blood looks surprisingly dark.
  • There is a half-eaten meal at the desk in the apartment. [Confirmed from pictures].
  • There is a tuft of Balaji's hair, soaked in blood, under the bathroom door. [Confirmed that's what it looks like in the pictures], again suggesting to Webb a violent struggle.
• According to the parents, he had a USB thumb drive which is now missing, containing important evidence for an upcoming court case about OpenAI's use of copyrighted data.^[8][22]
• People that spoke to him around the time of his death report him to have been in high spirits and making plans for the near future.^[23]
• George Webb claims there were security cameras working all on floors except the floor which he lived on.^[24] This appears to conflict with the parents' claim that the police said no one came in or out (see below), but may be referring to different cameras, as the parents also mention that the murderer could have come through a different entrance to the main one.^[25]
• The parents say "OpenAI has deleted the copyright data that was evidence that was given to the discovery for the [New York Times] lawsuit. They deleted the data and now my son is also gone, so now they're all set for winning the lawsuit... It's also said that my son had the documentation to prove the copyright violation. His statement, his testimony would have turned the AI industry upside down..."^[26]
  • Looking into the details of this, OpenAI did delete some data but this wasn't a permanent deletion of any of the primary sources and I think it was probably an accident and not significant to the outcome of the case.
  • I don't see any strong reason to believe Balaji had secret evidence that would have been critical to the outcome of the case.
• Ilya Sutskever had two armed bodyguards with him at NeurIPS.

Evidence against:

• One reason the authorities gave for declaring it a suicide was that CCTV footage showed that no one else came in or out of the apartment.^[27]
• In high school Balaji won a $100,000 prize for a computer science competition. His parents didn't find out until they saw the news online, suggesting he may not have been very open with them.^[28]

My interpretations:

• If we interpret the apartment as simply messy (as it looks to me), rather than ransacked, then we can probably discount the knocked-over trash can, the floss pick on the floor and the half-eaten meal. We can also probably discard the hypothesis of someone trying to locate a USB drive with secret information, which raises more questions than it answers (why didn't he reveal this information before? why didn't he back up this crucial data anywhere?).
• In my uninformed view, it doesn't look like the pictures of the scene of death strongly suggest a struggle between murderer and victim, although I don't know how to explain the tuft of hair.
• The motivations of OpenAI or some other actor to murder a whistleblower are unlikely. The most plausible to me is that they want to send a warning to other potential whistleblowers, but this isn't very compelling.
• There's no smoking gun and the parents (understandably) do not look like they are thinking very systematically to establish a case for foul-play. This is notable because their claim of foul-play is the main factor that privileged this hypothesis to credible people.
• Balaji appeared from the outside to be a happy and highly successful person with important plans in the next few days. It is surprising that someone like that would commit suicide.

Overall my conclusion is that this was a suicide with roughly 96% confidence. This is a slight update downwards from 98% when I first heard about it [LW(p) · GW(p)] and overall quite concerning.

I encourage people to trade on this related prediction market and report further evidence.

Useful sources:

• https://x.com/RealGeorgeWebb1/status/1874166318053941567
• https://www.youtube.com/watch?v=zu1whk7XdCo
• https://rumble.com/v6411hm-forensics-say-the-open-ai-whistleblower-was-executed.html?e9s=src_v1_upp
• https://www.youtube.com/watch?v=4LkteX3o1Co

1. ^{^}

   I'm not linking to this evidence here, in the spirit of respecting the wishes of the parents, but this is an important source that informed my understanding of the situation.

2. ^{^}

   https://x.com/RaoPoornima/status/1876101052065558998 

3. ^{^}

   Source: Poornima Ramarao (11:22)

4. ^{^}

   Source: Poornima Ramarao (12:38)

5. ^{^}

   Source: Poornima Ramarao (13:02)

6. ^{^}

   Source: Poornima Ramarao (15:47)

7. ^{^}

   Source: Poornima Ramarao (16:36)

8. ^{^}

   Source: George Webb + Poornima Ramarao (1:45)

9. ^{^}

   Source: George Webb (9:56)

10. ^{^}

    Source: (23:27)

11. ^{^}

    Source: (8:02)

12. ^{^}

    Source: (26:00)

13. ^{^}

    Source: George Webb + Poornima Ramarao (0:35)

14. ^{^}

    Source: George Webb (6:53)

15. ^{^}

    Source: George Webb (3:38)

16. ^{^}

    Source: George Webb (5:44)

17. ^{^}

    Source: George Webb (5:46)

18. ^{^}

    Source: George Webb (0:05)

19. ^{^}

    Source: George Webb (6:23)

20. ^{^}

    Source: George Webb (9:12)

21. ^{^}

    Source: Poornima Ramarao (1:18)

22. ^{^}

    Source: George Webb (9:45)

23. ^{^}

    Source: Poornima Ramarao (4:30)

24. ^{^}

    Source: George Webb (9:30)

25. ^{^}

    Source: Poornima Ramarao (2:40)

26. ^{^}

    Source: Poornima Ramarao (4:14)

27. ^{^}

    Source: Poornima Ramarao (12:42)

28. ^{^}

    Source: Ramamurthy (17:37)

29. ^{^}

    Source: George Webb (13:29)

30. ^{^}

    Source: George Webb (5:43)

Crossposted from https://x.com/JosephMiller_/status/1839085556245950552

1/ Sparse autoencoders trained on the embedding weights of a language model have very interpretable features! We can decompose a token into its top activating features to understand how the model represents the meaning of the token.🧵

2/ To visualize each feature, we project the output direction of the feature onto the token embeddings to find the most similar tokens. We also show the bottom and median tokens by similarity, but they are not very interpretable.

3/ The token "deaf" decomposes into features for audio and disability! None of the examples in this thread are cherry-picked – they were all (really) randomly chosen.

4/ Usually SAEs are trained on the internal activations of a component for billions of different input strings. But here we just train on the rows of the embedding weight matrix (where each row is the embedding for one token).

5/ Most SAEs have many thousands of features. But for our embedding SAE, we only use 2000 features because of our limited dataset. We are essentially compressing the embedding matrix into a smaller, sparser representation.

6/ The reconstructions are not highly accurate – on average we have ~60% variance unexplained (~0.7 cosine similarity) with ~6 features active per token. So more work is needed to see how useful they are.

7/ Note that for this experiment we used the subset of the token embeddings that correspond to English words, so the task is easier - but the results are qualitatively similar when you train on all embeddings.

8/ We also compare to PCA directions and find that the SAE directions are in fact much more interpretable (as we would expect)!

9/ I worked on embedding SAEs at an @apartresearch hackathon in April, with Sajjan Sivia and Chenxing (June) He.
Embedding SAEs were also invented independently by @Michael Pearce [LW · GW].

BBC Tech News as far as I can tell has not covered any of the recent OpenAI drama about NDAs or employees leaving.

But Scarlett Johansson 'shocked' by AI chatbot imitation is now the main headline.

LessWrong LLM feature idea: Typo checker

It's becoming a habit for me to run anything I write through an LLM to check for mistakes before I send it off.

I think the hardest part of implementing this feature well would be to get it to only comment on things that are definitely mistakes / typos. I don't want a general LLM writing feedback tool built-in to LessWrong.

There are two types of people in this world.

There are people who treat the lock on a public bathroom as a tool for communicating occupancy and a safeguard against accidental attempts to enter when the room is unavailable. For these people the standard protocol is to discern the likely state of engagement of the inner room and then tentatively proceed inside if they detect no signs of human activity.

And there are people who view the lock on a public bathroom as a physical barricade with which to temporarily defend possessed territory. They start by giving the door a hearty push to test the tensile strength of the barrier. On meeting resistance they engage with full force, wringing the handle up and down and slamming into the door with their full body weight. Only once their attempts are thwarted do they reluctantly retreat to find another stall.