@acmqueue.bsky.social
The Coding Philosopher
Out of My Other Mind
What would it take to convince us that an AI is conscious?
queue.acm.org/doi/10.1145/...
Out of My Other Mind
What would it take to convince us that an AI is conscious?
queue.acm.org/doi/10.1145/...
October 5, 2026 at 8:31 PM
The Coding Philosopher
Out of My Other Mind
What would it take to convince us that an AI is conscious?
queue.acm.org/doi/10.1145/...
Out of My Other Mind
What would it take to convince us that an AI is conscious?
queue.acm.org/doi/10.1145/...
Running an Agentic Threat Model
Workflow, abuse cases, and runtime controls
Helping security and engineering teams extend established threat-modeling practices to autonomous systems without relying on the AI model to enforce critical security boundaries
queue.acm.org/doi/10.1145/...
Workflow, abuse cases, and runtime controls
Helping security and engineering teams extend established threat-modeling practices to autonomous systems without relying on the AI model to enforce critical security boundaries
queue.acm.org/doi/10.1145/...
October 5, 2026 at 6:19 PM
Running an Agentic Threat Model
Workflow, abuse cases, and runtime controls
Helping security and engineering teams extend established threat-modeling practices to autonomous systems without relying on the AI model to enforce critical security boundaries
queue.acm.org/doi/10.1145/...
Workflow, abuse cases, and runtime controls
Helping security and engineering teams extend established threat-modeling practices to autonomous systems without relying on the AI model to enforce critical security boundaries
queue.acm.org/doi/10.1145/...
A Valid Tool Call Can Still Be an Invalid Effect
Why consequential agent actions need a semantic read set
AI agents expose an interface failure: A system can synthesize a transaction at runtime and then erase its read set before emitting the write.
queue.acm.org/doi/10.1145/...
Why consequential agent actions need a semantic read set
AI agents expose an interface failure: A system can synthesize a transaction at runtime and then erase its read set before emitting the write.
queue.acm.org/doi/10.1145/...
September 28, 2026 at 3:49 PM
A Valid Tool Call Can Still Be an Invalid Effect
Why consequential agent actions need a semantic read set
AI agents expose an interface failure: A system can synthesize a transaction at runtime and then erase its read set before emitting the write.
queue.acm.org/doi/10.1145/...
Why consequential agent actions need a semantic read set
AI agents expose an interface failure: A system can synthesize a transaction at runtime and then erase its read set before emitting the write.
queue.acm.org/doi/10.1145/...
CAFE(S): Your Agent Is Only As Good As Its Context
Even the latest models degrade when operating on unclear inputs. We present CAFE(S), a framework that evaluates context across five dimensions: clarity, actionability, fidelity, efficiency, and security
queue.acm.org/doi/10.1145/...
Even the latest models degrade when operating on unclear inputs. We present CAFE(S), a framework that evaluates context across five dimensions: clarity, actionability, fidelity, efficiency, and security
queue.acm.org/doi/10.1145/...
September 24, 2026 at 3:06 PM
CAFE(S): Your Agent Is Only As Good As Its Context
Even the latest models degrade when operating on unclear inputs. We present CAFE(S), a framework that evaluates context across five dimensions: clarity, actionability, fidelity, efficiency, and security
queue.acm.org/doi/10.1145/...
Even the latest models degrade when operating on unclear inputs. We present CAFE(S), a framework that evaluates context across five dimensions: clarity, actionability, fidelity, efficiency, and security
queue.acm.org/doi/10.1145/...
Finding the Real Bottleneck in Large-Scale ML Training
Real efficiency requires fixing the underlying systems
In production training clusters, actual model execution frequently consumes only half of an accelerator’s theoretical capacity
queue.acm.org/doi/10.1145/...
Real efficiency requires fixing the underlying systems
In production training clusters, actual model execution frequently consumes only half of an accelerator’s theoretical capacity
queue.acm.org/doi/10.1145/...
September 21, 2026 at 5:30 PM
Finding the Real Bottleneck in Large-Scale ML Training
Real efficiency requires fixing the underlying systems
In production training clusters, actual model execution frequently consumes only half of an accelerator’s theoretical capacity
queue.acm.org/doi/10.1145/...
Real efficiency requires fixing the underlying systems
In production training clusters, actual model execution frequently consumes only half of an accelerator’s theoretical capacity
queue.acm.org/doi/10.1145/...
Signs of a Brewing Crisis
Crises have the destabilizing power to shift incentives and invert power structures
Identifying these circumstances allows operators and engineers to anticipate opportunities when adaptive resilience will be required
queue.acm.org/doi/10.1145/...
Crises have the destabilizing power to shift incentives and invert power structures
Identifying these circumstances allows operators and engineers to anticipate opportunities when adaptive resilience will be required
queue.acm.org/doi/10.1145/...
September 17, 2026 at 3:50 PM
Signs of a Brewing Crisis
Crises have the destabilizing power to shift incentives and invert power structures
Identifying these circumstances allows operators and engineers to anticipate opportunities when adaptive resilience will be required
queue.acm.org/doi/10.1145/...
Crises have the destabilizing power to shift incentives and invert power structures
Identifying these circumstances allows operators and engineers to anticipate opportunities when adaptive resilience will be required
queue.acm.org/doi/10.1145/...
What’s in Your Software Repair Kit?
The things you wish you had before a crisis
You can’t prevent or predict the next systems meltdown. But you can build resilience into your systems and organization before the next crisis strikes.
queue.acm.org/doi/10.1145/...
The things you wish you had before a crisis
You can’t prevent or predict the next systems meltdown. But you can build resilience into your systems and organization before the next crisis strikes.
queue.acm.org/doi/10.1145/...
September 14, 2026 at 6:41 PM
What’s in Your Software Repair Kit?
The things you wish you had before a crisis
You can’t prevent or predict the next systems meltdown. But you can build resilience into your systems and organization before the next crisis strikes.
queue.acm.org/doi/10.1145/...
The things you wish you had before a crisis
You can’t prevent or predict the next systems meltdown. But you can build resilience into your systems and organization before the next crisis strikes.
queue.acm.org/doi/10.1145/...
Data Architectures in the Age of AI
Business semantics must be machine readable and continuously synchronized
Federation must become the default for operational workflows
Governance must shift from controlling access to governing autonomous behavior
queue.acm.org/doi/10.1145/...
Business semantics must be machine readable and continuously synchronized
Federation must become the default for operational workflows
Governance must shift from controlling access to governing autonomous behavior
queue.acm.org/doi/10.1145/...
September 9, 2026 at 5:01 PM
Data Architectures in the Age of AI
Business semantics must be machine readable and continuously synchronized
Federation must become the default for operational workflows
Governance must shift from controlling access to governing autonomous behavior
queue.acm.org/doi/10.1145/...
Business semantics must be machine readable and continuously synchronized
Federation must become the default for operational workflows
Governance must shift from controlling access to governing autonomous behavior
queue.acm.org/doi/10.1145/...
How CHERIoT Provides Strong and Able Isolation Without an MMU
Co-design of hardware and software offers stronger security and ease of use
CHERIoT is optimized for small devices but showcases what is possible at any scale if you start by assuming CHERI.
queue.acm.org/doi/10.1145/...
Co-design of hardware and software offers stronger security and ease of use
CHERIoT is optimized for small devices but showcases what is possible at any scale if you start by assuming CHERI.
queue.acm.org/doi/10.1145/...
September 9, 2026 at 2:22 PM
How CHERIoT Provides Strong and Able Isolation Without an MMU
Co-design of hardware and software offers stronger security and ease of use
CHERIoT is optimized for small devices but showcases what is possible at any scale if you start by assuming CHERI.
queue.acm.org/doi/10.1145/...
Co-design of hardware and software offers stronger security and ease of use
CHERIoT is optimized for small devices but showcases what is possible at any scale if you start by assuming CHERI.
queue.acm.org/doi/10.1145/...
Kode Vicious
When You Wish Upon a Prompt
Relying on an LLM doesn’t teach how to write code
Today’s students must be taught not how to spot an errant asterisk, but how all the components of a system work together.
queue.acm.org/doi/10.1145/...
When You Wish Upon a Prompt
Relying on an LLM doesn’t teach how to write code
Today’s students must be taught not how to spot an errant asterisk, but how all the components of a system work together.
queue.acm.org/doi/10.1145/...
September 4, 2026 at 2:39 PM
Kode Vicious
When You Wish Upon a Prompt
Relying on an LLM doesn’t teach how to write code
Today’s students must be taught not how to spot an errant asterisk, but how all the components of a system work together.
queue.acm.org/doi/10.1145/...
When You Wish Upon a Prompt
Relying on an LLM doesn’t teach how to write code
Today’s students must be taught not how to spot an errant asterisk, but how all the components of a system work together.
queue.acm.org/doi/10.1145/...
Arithmetic Without Numbers
What happens inside an LLM when it tries to calculate with nothing but matrices
How does a large language model do arithmetic when all it has are matrices—no fingers, no scratch paper, no columns of digits?
queue.acm.org/detail.cfm?i...
What happens inside an LLM when it tries to calculate with nothing but matrices
How does a large language model do arithmetic when all it has are matrices—no fingers, no scratch paper, no columns of digits?
queue.acm.org/detail.cfm?i...
Arithmetic Without Numbers - ACM Queue
queue.acm.org
August 25, 2026 at 1:41 PM
Arithmetic Without Numbers
What happens inside an LLM when it tries to calculate with nothing but matrices
How does a large language model do arithmetic when all it has are matrices—no fingers, no scratch paper, no columns of digits?
queue.acm.org/detail.cfm?i...
What happens inside an LLM when it tries to calculate with nothing but matrices
How does a large language model do arithmetic when all it has are matrices—no fingers, no scratch paper, no columns of digits?
queue.acm.org/detail.cfm?i...
Too Many DevEx Metrics, Too Little Guidance
DevEx Metrics Compass: making sense of developer experience measurement
As AI-augmented development becomes standard practice, engineering leaders face mounting pressure to demonstrate its impact.
queue.acm.org/detail.cfm?i...
DevEx Metrics Compass: making sense of developer experience measurement
As AI-augmented development becomes standard practice, engineering leaders face mounting pressure to demonstrate its impact.
queue.acm.org/detail.cfm?i...
Too Many DevEx Metrics, Too Little Guidance - ACM Queue
queue.acm.org
August 18, 2026 at 2:28 PM
Too Many DevEx Metrics, Too Little Guidance
DevEx Metrics Compass: making sense of developer experience measurement
As AI-augmented development becomes standard practice, engineering leaders face mounting pressure to demonstrate its impact.
queue.acm.org/detail.cfm?i...
DevEx Metrics Compass: making sense of developer experience measurement
As AI-augmented development becomes standard practice, engineering leaders face mounting pressure to demonstrate its impact.
queue.acm.org/detail.cfm?i...
The Challenge of Efficiency Versus Isolation:
Distributed systems lessons from serving inference
The mechanisms that make production inference affordable are the same ones that dissolve the isolation and recovery guarantees built over two decades.
queue.acm.org/detail.cfm?i...
Distributed systems lessons from serving inference
The mechanisms that make production inference affordable are the same ones that dissolve the isolation and recovery guarantees built over two decades.
queue.acm.org/detail.cfm?i...
The Challenge of Efficiency Versus Isolation - ACM Queue
queue.acm.org
August 14, 2026 at 5:26 PM
The Challenge of Efficiency Versus Isolation:
Distributed systems lessons from serving inference
The mechanisms that make production inference affordable are the same ones that dissolve the isolation and recovery guarantees built over two decades.
queue.acm.org/detail.cfm?i...
Distributed systems lessons from serving inference
The mechanisms that make production inference affordable are the same ones that dissolve the isolation and recovery guarantees built over two decades.
queue.acm.org/detail.cfm?i...
Operations and Life
Unethical Ways to Manage Technical Debt
You can ignore it, or you can adopt more above-board techniques that reframe projects so that confronting tech debt is an upfront part of the plan.
queue.acm.org/detail.cfm?i...
Unethical Ways to Manage Technical Debt
You can ignore it, or you can adopt more above-board techniques that reframe projects so that confronting tech debt is an upfront part of the plan.
queue.acm.org/detail.cfm?i...
Unethical Ways to Manage Technical Debt - ACM Queue
queue.acm.org
August 11, 2026 at 3:23 PM
Operations and Life
Unethical Ways to Manage Technical Debt
You can ignore it, or you can adopt more above-board techniques that reframe projects so that confronting tech debt is an upfront part of the plan.
queue.acm.org/detail.cfm?i...
Unethical Ways to Manage Technical Debt
You can ignore it, or you can adopt more above-board techniques that reframe projects so that confronting tech debt is an upfront part of the plan.
queue.acm.org/detail.cfm?i...
Where to Draw the Line
Which decisions should not be handed over to LLMs?
AI automation is only replacing the visible artifact of software engineering, not the actual job. We are demanding senior judgment while eliminating the work that produces it.
queue.acm.org/detail.cfm?i...
Which decisions should not be handed over to LLMs?
AI automation is only replacing the visible artifact of software engineering, not the actual job. We are demanding senior judgment while eliminating the work that produces it.
queue.acm.org/detail.cfm?i...
Where to Draw the Line - ACM Queue
queue.acm.org
August 6, 2026 at 2:40 PM
Where to Draw the Line
Which decisions should not be handed over to LLMs?
AI automation is only replacing the visible artifact of software engineering, not the actual job. We are demanding senior judgment while eliminating the work that produces it.
queue.acm.org/detail.cfm?i...
Which decisions should not be handed over to LLMs?
AI automation is only replacing the visible artifact of software engineering, not the actual job. We are demanding senior judgment while eliminating the work that produces it.
queue.acm.org/detail.cfm?i...
The Coding Philosopher -
Indirected Reality:
Language, truth, and LLMs
How can LLMs appear to know facts about the world when they are trained only on patterns in language rather than direct experience of reality?
queue.acm.org/detail.cfm?i...
Indirected Reality:
Language, truth, and LLMs
How can LLMs appear to know facts about the world when they are trained only on patterns in language rather than direct experience of reality?
queue.acm.org/detail.cfm?i...
Indirected Reality - ACM Queue
queue.acm.org
August 3, 2026 at 1:30 PM
The Coding Philosopher -
Indirected Reality:
Language, truth, and LLMs
How can LLMs appear to know facts about the world when they are trained only on patterns in language rather than direct experience of reality?
queue.acm.org/detail.cfm?i...
Indirected Reality:
Language, truth, and LLMs
How can LLMs appear to know facts about the world when they are trained only on patterns in language rather than direct experience of reality?
queue.acm.org/detail.cfm?i...
Where Does the Foundation Come From?
AI is taking over the work that used to develop professional judgment. For engineers with grounding, AI is a multiplier; without it, AI creates a productivity illusion in which output outpaces understanding.
queue.acm.org/detail.cfm?i...
AI is taking over the work that used to develop professional judgment. For engineers with grounding, AI is a multiplier; without it, AI creates a productivity illusion in which output outpaces understanding.
queue.acm.org/detail.cfm?i...
Where Does the Foundation Come From? - ACM Queue
queue.acm.org
July 28, 2026 at 2:09 PM
Where Does the Foundation Come From?
AI is taking over the work that used to develop professional judgment. For engineers with grounding, AI is a multiplier; without it, AI creates a productivity illusion in which output outpaces understanding.
queue.acm.org/detail.cfm?i...
AI is taking over the work that used to develop professional judgment. For engineers with grounding, AI is a multiplier; without it, AI creates a productivity illusion in which output outpaces understanding.
queue.acm.org/detail.cfm?i...
Titan Transients and LLM Scalability
The ghost in the machine
Is the compute-efficient frontier (CEF) a universal constraint on the scalability of GenAI systems? It is a consequence of larger LLMs detecting inter-corpora correlations on all size scales
queue.acm.org/detail.cfm?i...
The ghost in the machine
Is the compute-efficient frontier (CEF) a universal constraint on the scalability of GenAI systems? It is a consequence of larger LLMs detecting inter-corpora correlations on all size scales
queue.acm.org/detail.cfm?i...
Titan Transients and LLM Scalability - ACM Queue
queue.acm.org
July 23, 2026 at 4:18 PM
Titan Transients and LLM Scalability
The ghost in the machine
Is the compute-efficient frontier (CEF) a universal constraint on the scalability of GenAI systems? It is a consequence of larger LLMs detecting inter-corpora correlations on all size scales
queue.acm.org/detail.cfm?i...
The ghost in the machine
Is the compute-efficient frontier (CEF) a universal constraint on the scalability of GenAI systems? It is a consequence of larger LLMs detecting inter-corpora correlations on all size scales
queue.acm.org/detail.cfm?i...
Beyond Zero:
Enterprise Security for the AI Era
Beyond Zero is a new security paradigm designed for the AI era. Google’s vision for the future of this access model as well as a call for industry collaboration and standards development are outlined here.
queue.acm.org/detail.cfm?i...
Enterprise Security for the AI Era
Beyond Zero is a new security paradigm designed for the AI era. Google’s vision for the future of this access model as well as a call for industry collaboration and standards development are outlined here.
queue.acm.org/detail.cfm?i...
Beyond Zero: Enterprise Security for the AI Era - ACM Queue
queue.acm.org
July 21, 2026 at 4:11 PM
Beyond Zero:
Enterprise Security for the AI Era
Beyond Zero is a new security paradigm designed for the AI era. Google’s vision for the future of this access model as well as a call for industry collaboration and standards development are outlined here.
queue.acm.org/detail.cfm?i...
Enterprise Security for the AI Era
Beyond Zero is a new security paradigm designed for the AI era. Google’s vision for the future of this access model as well as a call for industry collaboration and standards development are outlined here.
queue.acm.org/detail.cfm?i...
Goodbye, and thanks for all the Bikesheds!
The only bit left of FOSS as we know it will be that users will be able to read the source code. As reproducible builds catch on, they might even be able to compile that, as long as they make no modifications.
queue.acm.org/detail.cfm?i...
The only bit left of FOSS as we know it will be that users will be able to read the source code. As reproducible builds catch on, they might even be able to compile that, as long as they make no modifications.
queue.acm.org/detail.cfm?i...
Goodbye, and Thanks for All the Bikesheds! - ACM Queue
queue.acm.org
July 14, 2026 at 1:18 PM
Goodbye, and thanks for all the Bikesheds!
The only bit left of FOSS as we know it will be that users will be able to read the source code. As reproducible builds catch on, they might even be able to compile that, as long as they make no modifications.
queue.acm.org/detail.cfm?i...
The only bit left of FOSS as we know it will be that users will be able to read the source code. As reproducible builds catch on, they might even be able to compile that, as long as they make no modifications.
queue.acm.org/detail.cfm?i...
Kode Vicious:
Pebbles on the Beach
Keeping hold of the big questions
There are fewer things more maddening than watching someone wander around a space bumping into ideas as if they’re in a pinball machine.
queue.acm.org/detail.cfm?i...
Pebbles on the Beach
Keeping hold of the big questions
There are fewer things more maddening than watching someone wander around a space bumping into ideas as if they’re in a pinball machine.
queue.acm.org/detail.cfm?i...
Pebbles on the Beach - ACM Queue
queue.acm.org
July 7, 2026 at 1:20 PM
Kode Vicious:
Pebbles on the Beach
Keeping hold of the big questions
There are fewer things more maddening than watching someone wander around a space bumping into ideas as if they’re in a pinball machine.
queue.acm.org/detail.cfm?i...
Pebbles on the Beach
Keeping hold of the big questions
There are fewer things more maddening than watching someone wander around a space bumping into ideas as if they’re in a pinball machine.
queue.acm.org/detail.cfm?i...
EngThrive: Make It Fast and Easy to Do Great Work
A durable model deployed at Microsoft that measures outcome-oriented engineering organizing productivity into three dimensions: speed, ease, and quality, with "thriving" as a well-being guardrail
queue.acm.org/detail.cfm?i...
A durable model deployed at Microsoft that measures outcome-oriented engineering organizing productivity into three dimensions: speed, ease, and quality, with "thriving" as a well-being guardrail
queue.acm.org/detail.cfm?i...
EngThrive: Make It Fast and Easy to Do Great Work - ACM Queue
queue.acm.org
June 30, 2026 at 3:30 PM
EngThrive: Make It Fast and Easy to Do Great Work
A durable model deployed at Microsoft that measures outcome-oriented engineering organizing productivity into three dimensions: speed, ease, and quality, with "thriving" as a well-being guardrail
queue.acm.org/detail.cfm?i...
A durable model deployed at Microsoft that measures outcome-oriented engineering organizing productivity into three dimensions: speed, ease, and quality, with "thriving" as a well-being guardrail
queue.acm.org/detail.cfm?i...
You Don’t Know Jack About Formal Verification:
What can you confidently guarantee about your software?
By eliminating the cost of writing proofs, AI is removing the biggest barrier to formal verification.
queue.acm.org/detail.cfm?i...
What can you confidently guarantee about your software?
By eliminating the cost of writing proofs, AI is removing the biggest barrier to formal verification.
queue.acm.org/detail.cfm?i...
You Don’t Know Jack About Formal Verification - ACM Queue
queue.acm.org
June 24, 2026 at 1:00 PM
You Don’t Know Jack About Formal Verification:
What can you confidently guarantee about your software?
By eliminating the cost of writing proofs, AI is removing the biggest barrier to formal verification.
queue.acm.org/detail.cfm?i...
What can you confidently guarantee about your software?
By eliminating the cost of writing proofs, AI is removing the biggest barrier to formal verification.
queue.acm.org/detail.cfm?i...
In Code They Think; In Proof We Trust
AI agents can be hijacked by prompt injection to exfiltrate sensitive data.
Solution: Constrain the agent to express its plan as a Kotlin script, then statically verify the script against a security policy before execution
queue.acm.org/detail.cfm?i...
AI agents can be hijacked by prompt injection to exfiltrate sensitive data.
Solution: Constrain the agent to express its plan as a Kotlin script, then statically verify the script against a security policy before execution
queue.acm.org/detail.cfm?i...
In Code They Think; In Proof We Trust - ACM Queue
queue.acm.org
June 15, 2026 at 1:31 PM
In Code They Think; In Proof We Trust
AI agents can be hijacked by prompt injection to exfiltrate sensitive data.
Solution: Constrain the agent to express its plan as a Kotlin script, then statically verify the script against a security policy before execution
queue.acm.org/detail.cfm?i...
AI agents can be hijacked by prompt injection to exfiltrate sensitive data.
Solution: Constrain the agent to express its plan as a Kotlin script, then statically verify the script against a security policy before execution
queue.acm.org/detail.cfm?i...
The SPACE of AI:
Real-world lessons of AI’s impact on developers
AI is augmenting developers rather than replacing them. Effective integration depends as much on team culture and support structures as on the tools themselves.
queue.acm.org/detail.cfm?i...
Real-world lessons of AI’s impact on developers
AI is augmenting developers rather than replacing them. Effective integration depends as much on team culture and support structures as on the tools themselves.
queue.acm.org/detail.cfm?i...
The SPACE of AI - ACM Queue
queue.acm.org
June 9, 2026 at 1:32 PM
The SPACE of AI:
Real-world lessons of AI’s impact on developers
AI is augmenting developers rather than replacing them. Effective integration depends as much on team culture and support structures as on the tools themselves.
queue.acm.org/detail.cfm?i...
Real-world lessons of AI’s impact on developers
AI is augmenting developers rather than replacing them. Effective integration depends as much on team culture and support structures as on the tools themselves.
queue.acm.org/detail.cfm?i...