Ulisse Mini

Karma: 1,661

Born too late to explore Earth; born too early to explore the galaxy; born just the right time to save humanity.

https://uli.rocks/about

[Question] What rationality failure modes are there?

Ulisse Mini19 Jan 2024 9:12 UTC

42 points

11 comments1 min readLW link

[Question] What ML gears do you like?

Ulisse Mini11 Nov 2023 19:10 UTC

25 points

4 comments1 min readLW link

Paper: Understanding and Controlling a Maze-Solving Policy Network

TurnTrout, Ulisse Mini, peligrietzer, mrinank_sharma, Austin Meek, Monte M and lisathiergart

13 Oct 2023 1:38 UTC

69 points

0 comments1 min readLW link

(arxiv.org)

ActAdd: Steering Language Models without Optimization

technicalities, TurnTrout, lisathiergart, David Udell, Ulisse Mini and Monte M

6 Sep 2023 17:21 UTC

105 points

3 comments2 min readLW link

(arxiv.org)

Open problems in activation engineering

TurnTrout, woog, lisathiergart, Monte M and Ulisse Mini

24 Jul 2023 19:46 UTC

43 points

2 comments1 min readLW link

(coda.io)

[ASoT] GPT2 Steering & The Tuned Lens

Ulisse Mini1 Jul 2023 14:12 UTC

23 points

0 comments2 min readLW link

LIMA: Less Is More for Alignment

Ulisse Mini30 May 2023 17:10 UTC

16 points

6 comments1 min readLW link

(arxiv.org)

TinyStories: Small Language Models That Still Speak Coherent English

Ulisse Mini28 May 2023 22:23 UTC

60 points

8 comments2 min readLW link

(arxiv.org)

Steering GPT-2-XL by adding an activation vector

TurnTrout, Monte M, David Udell, lisathiergart and Ulisse Mini

13 May 2023 18:42 UTC

423 points

97 comments50 min readLW link

How to get good at programming

Ulisse Mini5 May 2023 1:14 UTC

39 points

3 comments2 min readLW link

Understanding and controlling a maze-solving policy network

TurnTrout, peligrietzer, Ulisse Mini, Monte M and David Udell

11 Mar 2023 18:59 UTC

312 points

22 comments23 min readLW link

Predictions for shard theory mechanistic interpretability results

TurnTrout, Ulisse Mini and peligrietzer

1 Mar 2023 5:16 UTC

105 points

10 comments5 min readLW link

[ASoT] Policy Trajectory Visualization

Ulisse Mini7 Feb 2023 0:13 UTC

9 points

2 comments1 min readLW link

Incentives considered harmful

Ulisse Mini15 Jan 2023 6:38 UTC

6 points

0 comments1 min readLW link

(uli.rocks)

[Question] Where do you find people who actually do things?

Ulisse Mini13 Jan 2023 6:57 UTC

7 points

12 comments1 min readLW link

[Question] Effective Evil Causes?

Ulisse Mini30 Dec 2022 2:56 UTC

−12 points

2 comments1 min readLW link

[ASoT] Natural abstractions and AlphaZero

Ulisse Mini10 Dec 2022 17:53 UTC

33 points

1 comment1 min readLW link

(arxiv.org)

[ASoT] Probability Infects Concepts it Touches

Ulisse Mini7 Dec 2022 1:48 UTC

10 points

4 comments1 min readLW link

Three Fables of Magical Girls and Longtermism

Ulisse Mini2 Dec 2022 22:01 UTC

31 points

11 comments2 min readLW link

[ASoT] Reflectivity in Narrow AI

Ulisse Mini21 Nov 2022 0:51 UTC

6 points

1 comment1 min readLW link