#programsynthesis — Public Fediverse posts

Nice article, but the all-lowercase titling is so jarring:

“Six Thoughts On Generating C”, Andy Wingo (https://wingolog.org/archives/2026/02/09/six-thoughts-on-generating-c).

Via HN: https://news.ycombinator.com/item?id=46945235

On Lobsters: https://lobste.rs/s/j8jnqq/six_thoughts_on_generating_c

#Programming #C #PLDI #Compilers #CodeGeneration #ProgramSynthesis

Nice article, but the all-lowercase titling is so jarring:

“Six Thoughts On Generating C”, Andy Wingo (https://wingolog.org/archives/2026/02/09/six-thoughts-on-generating-c).

Via HN: https://news.ycombinator.com/item?id=46945235

On Lobsters: https://lobste.rs/s/j8jnqq/six_thoughts_on_generating_c

#Programming #C #PLDI #Compilers #CodeGeneration #ProgramSynthesis

Nice article, but the all-lowercase titling is so jarring:

“Six Thoughts On Generating C”, Andy Wingo (https://wingolog.org/archives/2026/02/09/six-thoughts-on-generating-c).

Via HN: https://news.ycombinator.com/item?id=46945235

On Lobsters: https://lobste.rs/s/j8jnqq/six_thoughts_on_generating_c

#Programming #C #PLDI #Compilers #CodeGeneration #ProgramSynthesis

Nice article, but the all-lowercase titling is so jarring:

“Six Thoughts On Generating C”, Andy Wingo (https://wingolog.org/archives/2026/02/09/six-thoughts-on-generating-c).

Via HN: https://news.ycombinator.com/item?id=46945235

On Lobsters: https://lobste.rs/s/j8jnqq/six_thoughts_on_generating_c

#Programming #C #PLDI #Compilers #CodeGeneration #ProgramSynthesis

@screwlisp @kentpitman regarding the discussion we had after the #LispyGopherClimate show ended, MiniKanren is logic programming language embedded in Scheme (sort-of like a Prolog implemented in Scheme and coded with S-expressions), and you can use machine leaning methods like neural networks to guide the search tree of the goal solver mechanism. This paper is an example of what I was talking about.

Even before LLMs were invented, MiniKanren was able to do program synthesis using purely symbolic logic. They developed a prototype called Barliman where you would provide example input->output pairs as constraints, and using a constraint solver, could generalize those examples to a function that generates any output for any input. As a simple example, you could give it the following input-output pairs:

1. () -> ()
2. (a) () -> (a)
3. () (a) -> (a)
4. (a) (a) -> (a a)

…and the constraint solver could determine that you are trying to implement the append function for lists and write the code automatically — without LLMs, using purely symbolic logic.

As you might expect, the solver could be very slow, or even diverge (never returning an answer). The paper I mentioned above talks about using neural networks to try to guide the constraint solver to improve the performance and usefulness of the results returned by the solver.

Now imagine applying this technique to other domains besides code generation or optimization, for example, auto-completion, or cache pre-fetching, and building it into a programmable computing environment like Emacs. You could have a tool like “Cursor,” but instead of using LLMs, it uses classical computing and constraint solvers, while taking a fraction of the amount of energy that LLMs use.

#tech #software #AI #LLM #MachineLearning #NeuralNetwork #ConstraintLogic #ConstraintSolver #LogicProgramming #Prolog #MiniKanren #Emacs #Lisp #Scheme #SchemeLang #ProgramSynthesis

@screwlisp @kentpitman regarding the discussion we had after the #LispyGopherClimate show ended, MiniKanren is logic programming language embedded in Scheme (sort-of like a Prolog implemented in Scheme and coded with S-expressions), and you can use machine leaning methods like neural networks to guide the search tree of the goal solver mechanism. This paper is an example of what I was talking about.

Even before LLMs were invented, MiniKanren was able to do program synthesis using purely symbolic logic. They developed a prototype called Barliman where you would provide example input->output pairs as constraints, and using a constraint solver, could generalize those examples to a function that generates any output for any input. As a simple example, you could give it the following input-output pairs:

1. () -> ()
2. (a) () -> (a)
3. () (a) -> (a)
4. (a) (a) -> (a a)

…and the constraint solver could determine that you are trying to implement the append function for lists and write the code automatically — without LLMs, using purely symbolic logic.

As you might expect, the solver could be very slow, or even diverge (never returning an answer). The paper I mentioned above talks about using neural networks to try to guide the constraint solver to improve the performance and usefulness of the results returned by the solver.

Now imagine applying this technique to other domains besides code generation or optimization, for example, auto-completion, or cache pre-fetching, and building it into a programmable computing environment like Emacs. You could have a tool like “Cursor,” but instead of using LLMs, it uses classical computing and constraint solvers, while taking a fraction of the amount of energy that LLMs use.

#tech #software #AI #LLM #MachineLearning #NeuralNetwork #ConstraintLogic #ConstraintSolver #LogicProgramming #Prolog #MiniKanren #Emacs #Lisp #Scheme #SchemeLang #ProgramSynthesis

@screwlisp @kentpitman regarding the discussion we had after the #LispyGopherClimate show ended, MiniKanren is logic programming language embedded in Scheme (sort-of like a Prolog implemented in Scheme and coded with S-expressions), and you can use machine leaning methods like neural networks to guide the search tree of the goal solver mechanism. This paper is an example of what I was talking about.

Even before LLMs were invented, MiniKanren was able to do program synthesis using purely symbolic logic. They developed a prototype called Barliman where you would provide example input->output pairs as constraints, and using a constraint solver, could generalize those examples to a function that generates any output for any input. As a simple example, you could give it the following input-output pairs:

1. () -> ()
2. (a) () -> (a)
3. () (a) -> (a)
4. (a) (a) -> (a a)

…and the constraint solver could determine that you are trying to implement the append function for lists and write the code automatically — without LLMs, using purely symbolic logic.

As you might expect, the solver could be very slow, or even diverge (never returning an answer). The paper I mentioned above talks about using neural networks to try to guide the constraint solver to improve the performance and usefulness of the results returned by the solver.

Now imagine applying this technique to other domains besides code generation or optimization, for example, auto-completion, or cache pre-fetching, and building it into a programmable computing environment like Emacs. You could have a tool like “Cursor,” but instead of using LLMs, it uses classical computing and constraint solvers, while taking a fraction of the amount of energy that LLMs use.

#tech #software #AI #LLM #MachineLearning #NeuralNetwork #ConstraintLogic #ConstraintSolver #LogicProgramming #Prolog #MiniKanren #Emacs #Lisp #Scheme #SchemeLang #ProgramSynthesis

@screwlisp @kentpitman regarding the discussion we had after the #LispyGopherClimate show ended, MiniKanren is logic programming language embedded in Scheme (sort-of like a Prolog implemented in Scheme and coded with S-expressions), and you can use machine leaning methods like neural networks to guide the search tree of the goal solver mechanism. This paper is an example of what I was talking about.

Even before LLMs were invented, MiniKanren was able to do program synthesis using purely symbolic logic. They developed a prototype called Barliman where you would provide example input->output pairs as constraints, and using a constraint solver, could generalize those examples to a function that generates any output for any input. As a simple example, you could give it the following input-output pairs:

1. () -> ()
2. (a) () -> (a)
3. () (a) -> (a)
4. (a) (a) -> (a a)

…and the constraint solver could determine that you are trying to implement the append function for lists and write the code automatically — without LLMs, using purely symbolic logic.

As you might expect, the solver could be very slow, or even diverge (never returning an answer). The paper I mentioned above talks about using neural networks to try to guide the constraint solver to improve the performance and usefulness of the results returned by the solver.

Now imagine applying this technique to other domains besides code generation or optimization, for example, auto-completion, or cache pre-fetching, and building it into a programmable computing environment like Emacs. You could have a tool like “Cursor,” but instead of using LLMs, it uses classical computing and constraint solvers, while taking a fraction of the amount of energy that LLMs use.

#tech #software #AI #LLM #MachineLearning #NeuralNetwork #ConstraintLogic #ConstraintSolver #LogicProgramming #Prolog #MiniKanren #Emacs #Lisp #Scheme #SchemeLang #ProgramSynthesis

New book review!

“Computational evolution of neural and morphological development”, Yaochu Jin, reviewed by Renske Vroomans.

https://link.springer.com/article/10.1007/s10710-024-09499-x

No paywall.

#geneticprogramming #programsynthesis #alife

New book review!

“Computational evolution of neural and morphological development”, Yaochu Jin, reviewed by Renske Vroomans.

https://link.springer.com/article/10.1007/s10710-024-09499-x

No paywall.

#geneticprogramming #programsynthesis #alife

New issue just announced, including several items with open access:

https://link.springer.com/journal/10710/volumes-and-issues/25-2

#geneticprogramming
#programsynthesis

New issue just announced, including several items with open access:

https://link.springer.com/journal/10710/volumes-and-issues/25-2

#geneticprogramming
#programsynthesis

New issue just announced, including several items with open access:

https://link.springer.com/journal/10710/volumes-and-issues/25-2

#geneticprogramming
#programsynthesis

(actually i’m really curious what #programsynthesis people’s favorite venues to publish at are — i feel like i see papers on it across all the PL confs, but idk which ones are most receptive to work that isn’t really doing “PL” innovation, rather improving synthesis methods or demonstrating & extending their use for novel applications)

(actually i’m really curious what #programsynthesis people’s favorite venues to publish at are — i feel like i see papers on it across all the PL confs, but idk which ones are most receptive to work that isn’t really doing “PL” innovation, rather improving synthesis methods or demonstrating & extending their use for novel applications)

(actually i’m really curious what #programsynthesis people’s favorite venues to publish at are — i feel like i see papers on it across all the PL confs, but idk which ones are most receptive to work that isn’t really doing “PL” innovation, rather improving synthesis methods or demonstrating & extending their use for novel applications)

(actually i’m really curious what #programsynthesis people’s favorite venues to publish at are — i feel like i see papers on it across all the PL confs, but idk which ones are most receptive to work that isn’t really doing “PL” innovation, rather improving synthesis methods or demonstrating & extending their use for novel applications)

(actually i’m really curious what #programsynthesis people’s favorite venues to publish at are — i feel like i see papers on it across all the PL confs, but idk which ones are most receptive to work that isn’t really doing “PL” innovation, rather improving synthesis methods or demonstrating & extending their use for novel applications)

not that the world really needs more computer science conferences, but i keep wondering if there’s appetite for one focused on procedural generation/generative computation, i.e. the union of PCG, generative art, program synthesis, &c.

mostly, it would really help to have a name for this field that people don’t mistake for consisting entirely of text2image statistical models

#generativeArt #genartclub #generativeAI #procgen #proceduralcontentgeneration #programsynthesis #logicprogramming

not that the world really needs more computer science conferences, but i keep wondering if there’s appetite for one focused on procedural generation/generative computation, i.e. the union of PCG, generative art, program synthesis, &c.

mostly, it would really help to have a name for this field that people don’t mistake for consisting entirely of text2image statistical models

#generativeArt #genartclub #generativeAI #procgen #proceduralcontentgeneration #programsynthesis #logicprogramming

not that the world really needs more computer science conferences, but i keep wondering if there’s appetite for one focused on procedural generation/generative computation, i.e. the union of PCG, generative art, program synthesis, &c.

mostly, it would really help to have a name for this field that people don’t mistake for consisting entirely of text2image statistical models

#generativeArt #genartclub #generativeAI #procgen #proceduralcontentgeneration #programsynthesis #logicprogramming

not that the world really needs more computer science conferences, but i keep wondering if there’s appetite for one focused on procedural generation/generative computation, i.e. the union of PCG, generative art, program synthesis, &c.

mostly, it would really help to have a name for this field that people don’t mistake for consisting entirely of text2image statistical models

#generativeArt #genartclub #generativeAI #procgen #proceduralcontentgeneration #programsynthesis #logicprogramming

not that the world really needs more computer science conferences, but i keep wondering if there’s appetite for one focused on procedural generation/generative computation, i.e. the union of PCG, generative art, program synthesis, &c.

mostly, it would really help to have a name for this field that people don’t mistake for consisting entirely of text2image statistical models

#generativeArt #genartclub #generativeAI #procgen #proceduralcontentgeneration #programsynthesis #logicprogramming

RT @[email protected]

Introducing AutumnSynth, a step toward automating scientific discovery through program synthesis.

AutumnSynth synthesizes the source code of a video game from seconds of play.

paper: https://basis.ai/publications/autumn_popl23.pdf

Blog: https://basis.ai/blog/autumn/

Why do this? How does it work?
🦃🧵 https://twitter.com/ZennaTavares/status/1620855534483296256

#cogsci @cogsci #compcogsci #programinduction #programsynthesis

RT @[email protected]

Introducing AutumnSynth, a step toward automating scientific discovery through program synthesis.

AutumnSynth synthesizes the source code of a video game from seconds of play.

paper: https://basis.ai/publications/autumn_popl23.pdf

Blog: https://basis.ai/blog/autumn/

Why do this? How does it work?
🦃🧵 https://twitter.com/ZennaTavares/status/1620855534483296256

#cogsci @cogsci #compcogsci #programinduction #programsynthesis

RT @[email protected]

Introducing AutumnSynth, a step toward automating scientific discovery through program synthesis.

AutumnSynth synthesizes the source code of a video game from seconds of play.

paper: https://basis.ai/publications/autumn_popl23.pdf

Blog: https://basis.ai/blog/autumn/

Why do this? How does it work?
🦃🧵 https://twitter.com/ZennaTavares/status/1620855534483296256

#cogsci @cogsci #compcogsci #programinduction #programsynthesis

RT @[email protected]

Introducing AutumnSynth, a step toward automating scientific discovery through program synthesis.

AutumnSynth synthesizes the source code of a video game from seconds of play.

paper: https://basis.ai/publications/autumn_popl23.pdf

Blog: https://basis.ai/blog/autumn/

Why do this? How does it work?
🦃🧵 https://twitter.com/ZennaTavares/status/1620855534483296256

#cogsci @cogsci #compcogsci #programinduction #programsynthesis

RT @[email protected]

Introducing AutumnSynth, a step toward automating scientific discovery through program synthesis.

AutumnSynth synthesizes the source code of a video game from seconds of play.

paper: https://basis.ai/publications/autumn_popl23.pdf

Blog: https://basis.ai/blog/autumn/

Why do this? How does it work?
🦃🧵 https://twitter.com/ZennaTavares/status/1620855534483296256

#cogsci @cogsci #compcogsci #programinduction #programsynthesis

#ChatGPT, #Codex, and similar models can do program synthesis. I think we in the #GeneticProgramming community aren't quite admitting this to ourselves! If a GP system could do one-tenth of the #ProgramSynthesis ChatGPT can do, it would win a best paper award at #GECCO, #EuroGP, or #GPTP. Should we just give up?

#ChatGPT, #Codex, and similar models can do program synthesis. I think we in the #GeneticProgramming community aren't quite admitting this to ourselves! If a GP system could do one-tenth of the #ProgramSynthesis ChatGPT can do, it would win a best paper award at #GECCO, #EuroGP, or #GPTP. Should we just give up?

#ChatGPT, #Codex, and similar models can do program synthesis. I think we in the #GeneticProgramming community aren't quite admitting this to ourselves! If a GP system could do one-tenth of the #ProgramSynthesis ChatGPT can do, it would win a best paper award at #GECCO, #EuroGP, or #GPTP. Should we just give up?

#ChatGPT, #Codex, and similar models can do program synthesis. I think we in the #GeneticProgramming community aren't quite admitting this to ourselves! If a GP system could do one-tenth of the #ProgramSynthesis ChatGPT can do, it would win a best paper award at #GECCO, #EuroGP, or #GPTP. Should we just give up?

#ChatGPT, #Codex, and similar models can do program synthesis. I think we in the #GeneticProgramming community aren't quite admitting this to ourselves! If a GP system could do one-tenth of the #ProgramSynthesis ChatGPT can do, it would win a best paper award at #GECCO, #EuroGP, or #GPTP. Should we just give up?

ICYMI: Hazel Levine (Indiana) at #RacketCon

Design Recipe Guided Synthesis with Bingus

https://youtu.be/oAE_G6HYilo

Source for Bingus https://github.com/ralsei/bingus

#Racket #RacketLang #RacketLanguage #htdp #ProgramSynthesis @hazel

ICYMI: Hazel Levine (Indiana) at #RacketCon

Design Recipe Guided Synthesis with Bingus

https://youtu.be/oAE_G6HYilo

Source for Bingus https://github.com/ralsei/bingus

#Racket #RacketLang #RacketLanguage #htdp #ProgramSynthesis @hazel

ICYMI: Hazel Levine (Indiana) at #RacketCon

Design Recipe Guided Synthesis with Bingus

https://youtu.be/oAE_G6HYilo

Source for Bingus https://github.com/ralsei/bingus

#Racket #RacketLang #RacketLanguage #htdp #ProgramSynthesis @hazel

ICYMI: Hazel Levine (Indiana) at #RacketCon

Design Recipe Guided Synthesis with Bingus

https://youtu.be/oAE_G6HYilo

Source for Bingus https://github.com/ralsei/bingus

#Racket #RacketLang #RacketLanguage #htdp #ProgramSynthesis @hazel

Updated some new thoughts regarding the TerpreT problem and my naive solution

https://luxxxlucy.github.io/projects/2021_terpret/index.html

The original TerpreT paper(https://arxiv.org/abs/1608.04428)
discussed solving program induction by gradient based optimization(after making the program differentiable by relaxation ).

#probprog #programsynthesis #neuralnetwork #deeplearning #NeuroSymbolic

Updated some new thoughts regarding the TerpreT problem and my naive solution

https://luxxxlucy.github.io/projects/2021_terpret/index.html

The original TerpreT paper(https://arxiv.org/abs/1608.04428)
discussed solving program induction by gradient based optimization(after making the program differentiable by relaxation ).

#probprog #programsynthesis #neuralnetwork #deeplearning #NeuroSymbolic

Updated some new thoughts regarding the TerpreT problem and my naive solution

https://luxxxlucy.github.io/projects/2021_terpret/index.html

The original TerpreT paper(https://arxiv.org/abs/1608.04428)
discussed solving program induction by gradient based optimization(after making the program differentiable by relaxation ).

#probprog #programsynthesis #neuralnetwork #deeplearning #NeuroSymbolic

Updated some new thoughts regarding the TerpreT problem and my naive solution

https://luxxxlucy.github.io/projects/2021_terpret/index.html

The original TerpreT paper(https://arxiv.org/abs/1608.04428)
discussed solving program induction by gradient based optimization(after making the program differentiable by relaxation ).

#probprog #programsynthesis #neuralnetwork #deeplearning #NeuroSymbolic

Updated some new thoughts regarding the TerpreT problem and my naive solution

https://luxxxlucy.github.io/projects/2021_terpret/index.html

The original TerpreT paper(https://arxiv.org/abs/1608.04428)
discussed solving program induction by gradient based optimization(after making the program differentiable by relaxation ).

#probprog #programsynthesis #neuralnetwork #deeplearning #NeuroSymbolic

Here's my #introduction. I'm a researcher with a background in #ProgrammingLanguages and more recently I've been interested in #spreadsheets and using #ArtificialIntelligence to generate programs (#ProgramSynthesis). I work at #MicrosoftResearch. In my spare time I enjoy #travelling, #hiking, #photography, #birds, and listen to podcasts like #NoSuchThingAsAFish.

Here's my #introduction. I'm a researcher with a background in #ProgrammingLanguages and more recently I've been interested in #spreadsheets and using #ArtificialIntelligence to generate programs (#ProgramSynthesis). I work at #MicrosoftResearch. In my spare time I enjoy #travelling, #hiking, #photography, #birds, and listen to podcasts like #NoSuchThingAsAFish.

Here's my #introduction. I'm a researcher with a background in #ProgrammingLanguages and more recently I've been interested in #spreadsheets and using #ArtificialIntelligence to generate programs (#ProgramSynthesis). I work at #MicrosoftResearch. In my spare time I enjoy #travelling, #hiking, #photography, #birds, and listen to podcasts like #NoSuchThingAsAFish.

Here's my #introduction. I'm a researcher with a background in #ProgrammingLanguages and more recently I've been interested in #spreadsheets and using #ArtificialIntelligence to generate programs (#ProgramSynthesis). I work at #MicrosoftResearch. In my spare time I enjoy #travelling, #hiking, #photography, #birds, and listen to podcasts like #NoSuchThingAsAFish.

Here's my #introduction. I'm a researcher with a background in #ProgrammingLanguages and more recently I've been interested in #spreadsheets and using #ArtificialIntelligence to generate programs (#ProgramSynthesis). I work at #MicrosoftResearch. In my spare time I enjoy #travelling, #hiking, #photography, #birds, and listen to podcasts like #NoSuchThingAsAFish.

#introduction

I'm a researcher in #AI #ArtificialIntelligence. I'm interested in everything but my own research is often about #programsynthesis and #GeneticProgramming. I do some work with #neuralnetworks too.

I'm also into #music. On a good day I combine this with AI.

I'm based in #UniversityOfGalway, in #Ireland.

#introduction

I'm a researcher in #AI #ArtificialIntelligence. I'm interested in everything but my own research is often about #programsynthesis and #GeneticProgramming. I do some work with #neuralnetworks too.

I'm also into #music. On a good day I combine this with AI.

I'm based in #UniversityOfGalway, in #Ireland.

#introduction

I'm a researcher in #AI #ArtificialIntelligence. I'm interested in everything but my own research is often about #programsynthesis and #GeneticProgramming. I do some work with #neuralnetworks too.

I'm also into #music. On a good day I combine this with AI.

I'm based in #UniversityOfGalway, in #Ireland.