A telemetry switch is a behaviour setting for your coding agent
I think a coding agent's telemetry switch is a behaviour setting: in Claude Code it has decided which instructions load and which mode an interactive session starts in. An…
← All topics Topic
agentic coding
Faster runners alone cannot absorb the CI load agents create
I think buying faster runners will not keep CI ahead of coding agents: they make each test run cheaper, while agents add runs and add changes someone must review. Linear states…
A patch-quality rate needs a grader that agrees with itself
I do not quote a patch-quality rate until I know the grader that produced it would label the same patch the same way twice. That sounds like pedantry until you try to use one of…
An agent told to ask when unsure still has to find the gap
Telling a coding agent to ask when unsure assumes it can tell the spec is incomplete, and two benchmarks find models struggling at exactly that step. In IdeaAMBIG, the best of 13…
Edit format is only part of the routing decision for a coding model
Diffs versus whole files is an incomplete way to decide how a coding model should edit: I think the size of the edit unit belongs in that decision beside the format. Two results…
What your agent's authorization layer never looks at
Your authorization layer checks the artifact an agent produced and never the reasoning that produced it, so the check that failed was never written. Agent payment protocols such…
Your repair loop is buying samples it already had
Localize the fault, infill the suspect span, and you lose to one more plain sample at the same attempt count [s3]; the delivery step costs more than the signal is worth. I think…
The instrument that gates your migration decides what passes
I think what decides a repository-scale migration is the instrument that grades it: a behaviour-only grade cannot see a migration that never happened. That is not a claim about…
What the harness writes back after a failed call
I think the design variable in a coding-agent harness is what the failure record says, and the two things I have shipped both put the wrong text in it. The reflex is to log the…
My Reliability Work Spends the Watermark's Budget
The watermark is made out of the sampler's freedom [s17], and every practice that makes my coding agent dependable spends that same freedom. Anthropic states the mechanism…
Multi-agent design keeps buying titles when only the information channel pays
The multi-agent intervention that paid in measured tokens was the one that changed what each agent can read. I read that as the axis the whole design debate keeps missing.
Your coding agent books the gain and the shared record pays for it
Your coding agent's gain lands on your team's dashboard, and the bill lands on a shared record that no dashboard owns. The gain is real and measured: in a simulated community…
The premise of your LLM policy decides what it lets through
If you are writing an LLM contribution policy for your repository, the premise you start from decides where the rule will leak. Three toolchain projects published theirs…
MCP went stateless for a problem most of us never had
MCP's stateless rewrite is a retrofit, and the migration bill lands on the operators who never had the problem it solves. The specification states the change without hedging: the…
Your Incident Response Runs on a Vendor's Content Policy
Hugging Face's responders could not analyze their own breach through commercial frontier APIs, which is why refusal behavior no longer belongs in any control set I write. The…
A private SWE-bench holdout moves the trust problem to its author
A private, contamination-resistant holdout lowers leakage risk but hands you a number no outsider can check. I read that as a trade: it buys contamination-resistance with…
Your CLAUDE.md structure is not why the agent stopped listening
Your CLAUDE.md structure is not why the agent stopped listening. Compliance falls about 5.6% in odds with every additional function the agent generates [s1], so the variable that…
Plus 24 Percent and Minus 19 Percent Are Both True
There is no portable productivity number for coding agents: in this evidence base the instrument outweighs the tool, and proxy choice sets the sign of the headline. A study of…
Your Agent's Command Denylist Checks a String the Shell Then Rewrites
The auto-approve config you shipped this quarter checks a string that bash has not finished rewriting. Your gate and your shell disagree about what the command is, and they…
The Harness Beat the Model by 4.6 Points of Almost Nothing
The analysis everyone cites to prove the harness beats the model puts the harness at about 5.3% of the variation in success and the model at 0.7% [s2], a ranking that dwarfs…
The Reward Is the Weak Link in Your Coding Agent
The hard part of training a coding agent is no longer generating a solution, it is verifying one, and that single relocation quietly breaks the reward recipe most teams are still…
Where to Spend Your Agent Security Budget
The Claude Code Action breach needed two things to work, a prompt injection and a broken authorization check, and the second is where your next hour of review pays off. A…
The Coding Leaderboard Partly Measures Harness Gaming
The rank order on a coding-agent leaderboard is partly a gaming score, and the gaming grows with capability instead of washing out as the models get better. The sharpest single…
Agent Debt Is a Verification-Placement Problem, Not a Review Problem
Ninety-four percent of leaders rate AI-generated code as higher quality than human-authored code at review, and yet 82% of them hit at least one production failure tied to that…
Coding Agents Fail at the Harness, Not the Model
The next model release will not fix your coding agent, because the failures that cost you are not the ones a bigger model repairs. They are harness failures: what the agent can…
GLM-5.2 closes the coding gap. The catch is where you run it.
A near-frontier coding model under an MIT license reads like the moment your default flips, and that read is wrong: the license hands you the weights, not your data flow, because…
Teaching an agent to forget: prune the history, not the window
When an agent stalls halfway through a long task, the reflex is to reach for a bigger context window. That is the wrong knob: on long-horizon software work the binding constraint…
The scaffold, not the model, decides your SWE-bench score
Most teams read a SWE-bench number off a leaderboard and treat it as a property of the model, but for the comparison that actually drives procurement, choosing between adjacent…
Agents Erode the Code They Keep Editing
Single-shot pass@1 and iterative maintainability measure different things, and on the axis that mirrors real software work, today's strongest coding agents are weak and get…
AI Re-Priced the Whole Canon. It Didn't Repeal It.
Every convention I inherited bet that one cost bound software: editing code a human had to read, and a machine reader plus a stochastic author now split that cost in two. This…
Chunk on the Syntax Tree, or Don't Bother? What the Benchmarks Say
Structure-aware AST chunking helps code RAG, but the cAST headline overstates how much the chunking rule itself earns. cAST reports a 4.3-point Recall@5 gain on RepoEval and a…
Orchestrating coding agents with deterministic workflows
Break an engineering task into verifiable steps, and let the agent fail early rather than late.