At Deepseek, We Are Trying to Replace Compilers with AI
Postedabout 2 months agoActiveabout 2 months ago
twitter.comTechstory
calmmixed
Debate
40/100
AICompilersProgramming
Key topics
AI
Compilers
Programming
DeepSeek is exploring the use of AI to replace compilers, sparking discussion on the feasibility and potential benefits of such an approach.
Snapshot generated from the HN discussion
Discussion Activity
Light discussionFirst comment
6m
Peak period
3
2-4h
Avg / period
1.8
Key moments
- 01Story posted
Nov 14, 2025 at 4:41 PM EST
about 2 months ago
Step 01 - 02First comment
Nov 14, 2025 at 4:47 PM EST
6m after posting
Step 02 - 03Peak activity
3 comments in 2-4h
Hottest window of the conversation
Step 03 - 04Latest activity
Nov 15, 2025 at 10:22 AM EST
about 2 months ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
ID: 45932515Type: storyLast synced: 11/20/2025, 1:39:00 PM
Want the full context?
Jump to the original sources
Read the primary article or dive into the live Hacker News thread when you're ready.
(disclaimer: I'm a software engineer with minimal compiler theory experience outside classes in college) I wonder whether its possible to trust an LLM to "compile" your code to an executable and trust that the compiled code is faithful to the input without writing a static validator that is pretty much a compiler itself.
> I wonder whether its possible to trust an LLM to "compile" your code to an executable and trust that the compiled code is faithful to the input without writing a static validator that is pretty much a compiler itself.
"LLMs as compilers" do not make any sense.
Traditional compilers must be deterministic to compile to the correct machine code for the correct architecture otherwise the executable will break.
The title is even more meaningless given that such a suggestion sounds totally at fundamental odds with today's state of the art compilers which need to be deterministic.
Replacing today's compilers, linkers and assemblers with LLMs (which are fundamentally stochastic preditcion models) for the use-case to compile software (not just generating correct code syntax) makes absolutely no sense whatsoever.
> Their formal education/background is in ML however.
Maybe whoever this person is should read up on what the Gell-Mann Amnesia Effect is.
Ask any compiler author on this very suggestion and they will question if this person is really a "Principal Engineer".
One parallel could be using ml for simulations to not write or compute all the rules