akrm @cachebag

this is enough for me opinions of my own github.com/cachebag Joined June 2014

Tweets

6K
Followers

158
Following

42
Likes

5K

Lott Dod @LottDood

a day ago

When my wife is in labor with our firstborn but the Battlefront 3 reveal trailer just dropped

9 564 9K 69K 406

View Details

Twisted 🔑 @imhighkey_sean

2 days ago

this was deadass the happiest time of my life

Sorren🇵🇸 @kazzy_115

3 days ago

Ts means something to me man.

6 236 3K 282K 208

13 195 3K 39K 192

View Details

DiscussingFilm @DiscussingFilm

2 days ago

‘STAR WARS: BATTLEFRONT 3’ is in the works. Respawn and DICE are teaming up to develop the game. (Source: variety.com/2026/digital/n…)

2K 12K 111K 6.1M 9K

View Details

does anyone know how to get LLMs to stop fucking ending all of their output with "One caveat", "A few things worth noting", and then proceeding to talk about irrelevant things? I've genuinely done all the grifter AI shit like SKILL.md and shit and nothing works.

1 0 0 17 0

View Details

akrm @cachebag

a week ago

@denbvk What an insanely stupid way to say "it's too hard for me"

1 0 2 198 0

View Details

TechToby @techtoby__

2 weeks ago

The best Software Engineers in the US right now are telling you they don’t review code and have 10, 20, 30 agents running at once Meanwhile your British 40+ middle manager drops in to standup a couple times a month “yeah I’ve tried AI, not that great would never pay for it”

216 373 11K 932K 1K

View Details

carol @cloisvillle

2 weeks ago

NO WAY TOM WELLING ACIDDENTELY POSTED HIS DICK ON HIS STORY

237 449 43K 5.6M 4K

View Details

akrm @cachebag

2 weeks ago

@ThePrimeagen Ugh. Why are you doing this to me Prime. You were the chosen one.

0 0 7 815 0

View Details

akrm @cachebag

2 weeks ago

@notloganhogg @mgill25 That doesn't make sense. You don't `git blame` merge commits. That would be silly way to place reasoning for a bug or defect. The merger is responsible yes, but the author owns that code. Thus they should be responsible for triage and/or post-mortems.

0 0 10 143 0

View Details

Manish Gill @mgill25

2 weeks ago

The single most important AI guidance I gave to my team was - does not matter who wrote the code, you own it in production. "I didn't do anything, I asked agents..." is something that would get any regular, non-popular engineer immediately thrown out of an incident call.

DHH @dhh

3 weeks ago

@crertel I didn't do anything. I asked two frontier agents to make the most of Elixir and this is what they came up with. Please do send a PR to speed things up! But also realize that it's not exactly extra points for Elixir if frontier agents can't find the magic "go fast" switches.

135 1 342 650K 152

19 25 644 16K 38

View Details

jame @kloogans

2 weeks ago

alright

33 2K 51K 836K 1K

View Details

akrm @cachebag

2 weeks ago

@dhh @crertel it's so baffling to me how someone once so revered for his contribution to open source and the software industry in general, can now be so fucking daft and out of touch.

0 0 2 40 0

View Details

akrm @cachebag

3 weeks ago

I love when I ask an LLM to tell me about a function’s call stack and it decides to run my entire linting + test suite

0 0 0 18 0

View Details

Ryan Fleury @rfleury

3 weeks ago

My position, which has been the same since the beginning, is: I will never pay for a subscription service to program (nor rely on some Internet service), and I will never turn my brain off and stop caring about the details I care about today. I am not inherently attached to typing every character, and I think the idea of human language processing and accelerating the production of programming language semantics is exciting. I would only ever do this using local models on my own hardware, and I would employ such tools very carefully (likely using them in my own tooling), and likely not in the ways that many people are employing them today. If I can accomplish the same work I would’ve been doing by hand more quickly, that’s pure win. But if I accelerate yet lose attention to detail, or the ability to think through those details, that’s not the same work anymore, and so there is some loss. That loss is potentially very important.

24 66 1K 25K 153

View Details

akrm @cachebag

3 weeks ago

@gmkurtzer My post explicitly noted that I do not believe AI can become conscious. I don't even think there's a chance. I was entertaining the original author's post...

1 0 0 12 0

View Details

akrm @cachebag

3 weeks ago

@gmkurtzer @JeffBohren You said that agents don't "start themselves". I am just wondering what that means as it pertains to whether or not they could be or become conscious

1 0 0 30 0

View Details

akrm @cachebag

3 weeks ago

@gmkurtzer @JeffBohren Do we "start ourselves"? What does that look like for us as living, conscious beings.

1 0 0 19 0

View Details

akrm @cachebag

4 weeks ago

@JeffBohren Explicit human input* meaning no one is sitting at a computer prompting it, but it is acting autonomously.

0 0 0 52 0

View Details

akrm @cachebag

4 weeks ago

@JeffBohren What about those (LLM agents, models, etc.) that act without human input. If they are constantly receiving input which informs their output, is that not similar to how living beings are? (BTW, I don't believe that AI can be conscious, I am just curious about your argument).

7 1 14 3K 0

View Details

Jeff Bohren @JeffBohren

4 weeks ago

If you take an LLM AI and do not provide it any prompts, goals, or any indication of expected output, it will do absolutely nothing. It will do nothing forever in the absence of a prompt. Clearly in this state it is not conscious. Then when prompted, it will provide an answer, and some will claim it is now conscious. That would be a strange form of consciousness. One where it is only conscious when answering a prompt.