Post

Augment Code
Augment Code@augmentcode·
OpenAI’s new GPT-5 Codex is impressive at coding tasks. But, in a huge codebase, intelligence isn’t the main bottleneck—context is.
English
18
47
605
1.2M
peasantUpon
peasantUpon@perchUpon·
@augmentcode Been saying this. We don't need AGI, we need ACI. Artificial Contextual Intelligence. To be AGI it requires ACI, imo.
English
2
1
1
920
m Casual
m Casual@mCasual1·
@augmentcode maybe the Evolutive aspect of the Context is Needed to perform Solving
English
0
1
0
138
Wanda Pitts
Wanda Pitts@PittsWanda12896·
@augmentcode ELON MUSK, THIS IS WANDA PITTS GARY. I HAVE YOUR # 618. AND I PURCHASED A TESLA MEET AND GREET. NEED ADVICE DO YOU DEAL WITH WHATSAPP. I HAVE MORE INFO
English
3
1
0
857
Sir Bubba The Great
Sir Bubba The Great@SirBubbaTheGr8·
@augmentcode 100%! Once you move from POC and simple code, you’re forced to break your code base up into modules that fit the context window. You can also use AI to generate a framework for assembling the modularity. It works!
English
0
0
1
310
jac
jac@jacobosssss·
@augmentcode we've been saying this for years but everyone kept throwing bigger models at the problem. turns out rag and context windows matter more than another trillion parameters who knew
English
0
0
0
118
Fails.us
Fails.us@Fails_us·
@augmentcode I created a `fid` command that uses a little-known ability of `find` to create a digest of source files, ignoring binary files to speed up grep. It searches the whole codebase as if it was a single mmap'd document.
English
0
0
0
194
Tensors
Tensors@Tensoars·
@augmentcode Context management + semantic/symbolic retrieval is key for high quality agents
English
0
0
0
29
J.C.
J.C.@Voodoo319E·
@augmentcode Interesting. But how are you handling codebase/data security?
English
0
0
0
144
Wes H☀️ling
Wes H☀️ling@wesholing·
@augmentcode it's not impressive at coding tasks. engineers spend 20% more time on code generated openai. give this shit a rest
English
1
0
0
116
AB
AB@azzyb_·
@augmentcode I've built a system context file into my code base - I generally ask the AI to run a new thread and run as long as I can before it maxes the context window and update the context. What's the benefit of using your app ? Also 600 msgs seems low?
English
0
0
0
333
Paylaş