Andrew Montalenti's Avatar

Andrew Montalenti

@amontalenti.bsky.social

Founding CTO of Parse.ly (acquired by Automattic.com). Interested in: F/OSS, Python programming, SaaS, startups. https://amontalenti.com

129 Followers  |  47 Following  |  3 Posts  |  Joined: 20.10.2023  |  1.6415

Latest posts by amontalenti.bsky.social on Bluesky

Hallucinations in code are the least dangerous form of LLM mistakes A surprisingly common complaint I see from developers who have tried using LLMs for code is that they encountered a hallucinationβ€”usually the LLM inventing a method or even a full …

I got fed up of posting the same comment every time the topic of LLM hallucinations in code comes up (short version: they don't matter because you'll spot them the second you try to run the code) - so I've turned that comment into a longer form blog post simonwillison.net/2025/Mar/2/h...

02.03.2025 06:27 β€” πŸ‘ 219    πŸ” 31    πŸ’¬ 25    πŸ“Œ 5

"I like to say that my interest in open source is actually really selfish. I figured something out. I never want to have to do this work ever again."

I wrote this segment up for my blog a few weeks ago: simonwillison.net/2025/Jan/24/...

13.02.2025 16:24 β€” πŸ‘ 60    πŸ” 6    πŸ’¬ 2    πŸ“Œ 0

I'd guess about 60% of my usage is code-related - I love them for code because hallucinations don't really matter, they become clear the moment I try and execute the code they wrote for me

With ChatGPT Code Interpreter and Claude's JS execution tool sometimes the models spot those bugs themselves!

13.02.2025 00:56 β€” πŸ‘ 1    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0

Now that we are 2+ years into the general public having access to ChatGPT-style systems, are there any credible studies out there exploring how susceptible to LLM-generated mistruths users of these things are?

Do people tend to develop good instincts on whether they should trust their output?

13.02.2025 00:06 β€” πŸ‘ 214    πŸ” 28    πŸ’¬ 42    πŸ“Œ 2
Jeff Dean & Noam Shazeer – 25 years at Google: from PageRank to AGI
YouTube video by Dwarkesh Patel Jeff Dean & Noam Shazeer – 25 years at Google: from PageRank to AGI

Delighted to have joined my good friend & colleague Noam Shazeer on a podcast with @dwarkesh.bsky.social for a 2+ hour discussion on early Google, ML hardware, training 1T+ token LLMs in '07, model sparsity, continual learning, and more.

Thanks, Noam and Dwarkesh! πŸ™

youtu.be/v0gjI__RyCY?...

12.02.2025 21:59 β€” πŸ‘ 99    πŸ” 14    πŸ’¬ 1    πŸ“Œ 3
Post image

Aside from the interesting new friends, S-tier programmer memes, and new work opportunities, why would someone want to spend 6–12 weeks at the @recursecenter.bsky.social ?

Because it’s one of the most potent environments for growing both your taste and agency as a programmer!

07.02.2025 18:25 β€” πŸ‘ 10    πŸ” 3    πŸ’¬ 1    πŸ“Œ 0
Animated demo of the SQLite explorer tool, clicking through different pages to explore different pages of the database with a detailed breakdown of each one.

Animated demo of the SQLite explorer tool, clicking through different pages to explore different pages of the database with a detailed breakdown of each one.

A trio of SQLite nerdery on my blog today:

- simonwillison.net/2025/Feb/6/s... about a neat tool for exploring SQLite's binary file format
- simonwillison.net/2025/Feb/7/a... is a tool I built for playing with APSW via Pyodide
- simonwillison.net/2025/Feb/7/s... lets you back a SQLite DB with S3

07.02.2025 02:25 β€” πŸ‘ 56    πŸ” 4    πŸ’¬ 2    πŸ“Œ 0
What to Expect from Release Month ⚑ Zig Programming Language https://ziglang.org/news/what-to-expect-from-release-month/

Zig 0.14.0 release date has been set to mid February!

https://ziglang.org/news/what-to-expect-from-release-month/

17.01.2025 14:10 β€” πŸ‘ 24    πŸ” 7    πŸ’¬ 1    πŸ“Œ 0
From where I left - <antirez>

Dear friends, I'm rejoining Redis. It's a long story, so it deserved a blog post to explain all the details: antirez.com/news/144

10.12.2024 16:40 β€” πŸ‘ 468    πŸ” 97    πŸ’¬ 37    πŸ“Œ 18
Preview
The smartphone app audit I recently upgraded from a Google Pixel 7 to Pixel 8 phone. Nothing earth shattering about this upgrade. Incremental.

The smartphone app audit:

amontalenti.com/2024/03/26/t...

Feels good to uninstall dozens of apps.

26.03.2024 13:58 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
Putting Your Media on a Diet When you type an address into your web browser and are brought to a web server, a lot of decentralized magic happens within the span of a few seconds. Through the web, we have an infinite media availa...

Putting Your Media on a Diet
amontalenti.com/2024/01/31/m...

In this essay, I make the case for well-written words as a healthier part of your media diet, rather than passively-consumed and short-form video.

25.02.2024 13:23 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
Dependency rejection Sam Altman once said: "Minimize your own cognitive load from distracting things that don’t really matter. It’s hard to overstate how important this is, and how bad most are at it. Get rid of distr...

Dependency rejection β€” my reflections on how to pursue originality and creativity when our tools litter our surroundings with seemingly helpful (but usually self-defeating) distractions. amontalenti.com/2023/11/25/d...

27.11.2023 18:09 β€” πŸ‘ 5    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

@amontalenti is following 20 prominent accounts