J Bostock

Karma: 2,796

Maybe Use BioLMs To Mitigate Pre-ASI Biorisk?

J Bostock10 Oct 2025 16:25 UTC

12 points

0 comments4 min readLW link

“Pessimization” is Just Ordinary Failure

J Bostock1 Oct 2025 13:48 UTC

56 points

2 comments6 min readLW link

[Retracted] Guess I Was Wrong About AIxBio Risks

J Bostock29 Sep 2025 11:44 UTC

62 points

7 comments5 min readLW link

Will Any Crap Cause Emergent Misalignment?

J Bostock27 Aug 2025 18:20 UTC

192 points

37 comments3 min readLW link

Steelmanning Conscious AI Default Friendliness

J Bostock25 Aug 2025 16:56 UTC

8 points

0 comments2 min readLW link

Red-Thing-Ism

J Bostock31 Jul 2025 14:09 UTC

101 points

9 comments3 min readLW link

Demons, Simulators and Gremlins

J Bostock9 Jul 2025 20:22 UTC

10 points

1 comment3 min readLW link

You Can’t Objectively Compare Seven Bees to One Human

J Bostock7 Jul 2025 18:11 UTC

58 points

26 comments3 min readLW link

(jbostock.substack.com)

Lurking in the Noise

J Bostock25 Jun 2025 13:36 UTC

37 points

2 comments4 min readLW link

We Need a Baseline for LLM-Aided Experiments

J Bostock24 May 2025 20:52 UTC

11 points

1 comment1 min readLW link

Everything I Know About Semantics I Learned From Music Notation

J Bostock9 Mar 2025 18:09 UTC

34 points

2 comments10 min readLW link

Turning up the Heat on Deceptively-Misaligned AI

J Bostock7 Jan 2025 0:13 UTC

19 points

16 comments4 min readLW link

Intranasal mRNA Vaccines?

J Bostock1 Jan 2025 23:46 UTC

26 points

2 comments3 min readLW link

Linkpost: Look at the Water

J Bostock30 Dec 2024 19:49 UTC

4 points

3 comments4 min readLW link

[Question] What is the alpha in one bit of evidence?

J Bostock22 Oct 2024 21:57 UTC

20 points

13 comments1 min readLW link

The Best Lay Argument is not a Simple English Yud Essay

J Bostock10 Sep 2024 17:34 UTC

261 points

15 comments5 min readLW link

Attention-Feature Tables in Gemma 2 Residual Streams

J Bostock6 Aug 2024 22:56 UTC

2 points

0 comments14 min readLW link

Risk Overview of AI in Bio Research

J Bostock15 Jul 2024 0:04 UTC

5 points

0 comments5 min readLW link

(open.substack.com)

How to Better Report Sparse Autoencoder Performance

J Bostock2 Jun 2024 19:34 UTC

20 points

4 comments3 min readLW link

To Limit Impact, Limit KL-Divergence

J Bostock18 May 2024 18:52 UTC

10 points

1 comment5 min readLW link