this post was submitted on 29 Sep 2026
571 points (98.0% liked)
Programmer Humor
33385 readers
1055 users here now
Welcome to Programmer Humor!
This is a place where you can post jokes, memes, humor, etc. related to programming!
For sharing awful code theres also Programming Horror.
Rules
- Keep content in english
- No advertisements
- Posts must be related to programming or programmer topics
- If the mod doesn't find it funny, you're banned. Ha-ha!... For real: do not use the community for "statements". There are other places for such content. Keep it chill and funny.
founded 3 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
You may try to attack my character by implying a bot or throwaway account but my point stands and all metrics agree with what i said. I literally used the newest model of a certain company (not naming them) and the agent finished a weeks work in 2 sessions. It even found lib incompatibilities and a weird bug in codebase without even prompting for that. The models became better but the harness got really good now. Your experience may be a skill issue, your prompts may suck or even your codebase might be too big, or cope, either way we are screwed, please don't give a false hope by moving the goalpost each time a llm evolves further, it's better for programmers to swim with the wave and evolve with the profession than be stuck in denial and becone obsolete.
Y'all have been saying "the problem is you're not using the newest model/harness" to any criticism for 3 years now lol
GPT 3.0 couldn't create gta 6 using a single prompt therefore all future models are bad. /s Maybe get out of your cave and test it yourself instead of coping in denial.
The problem is that every time, in the moment, people advocate and then when it comes up short, come back with "Oh, you did XYZ 3.2? Yeah that's busted, 3.3 can really do it" and rinse and repeat and it's hard to take that argument credibly when it's a treadmill of dissing yesterday's tech but swearing today's is different.
The current best of breed I have very limited exposure to (too rich for my blood), but it didn't seem overwhelmingly a slam dunk in my interaction. Incremental value going from more modest models to those don't seem to justify the price tag.
And every developer that is merely curating fully agentic workflow I have dealt with has pretty shit functionality and no idea what the hell they are doing. Whatever the rhetoric is, the results are just utter shit. Somewhat better if the problem domain can be infinitely retried without consequence with results that can be perfectly verified to let it drive eternal retries (while burning through token budget), but generally I just see pretty shit software.
On the other hand, a lot of these groups that I say has pretty shit AI software formerly had pretty shit normal software. Problem being clueless management now thinking they must be smart because they say things more aligned to the AI hype.
Every technology we have today started as being barely usable to "pretty good" across it's lifespan. Why would you think llms are different ?