11 min read
Approve Effects, Not Invocations
Approve effects, not invocations: why agent approval records miss harm in install hooks and skill combinations, and why pipelines need closure metrics.
RESEARCH
57 articles
LATEST
The Text Is a Control Surface
The text agents read is a control surface: bad MCP error messages cost more on stronger models, and context hygiene gains value with every model upgrade.
•12 min read
Read Article
8 min read
CodeMidas Turns Existing Code Into Coding-Agent Training Tasks
CodeMidas turns existing repository code into executable coding-agent RL tasks, tests, and verifiers, instead of relying on issues, commits, or hand labels.
Read more
10 min read
The Agent Is the Worst Witness to Its Own Run
An agent's report on its own run is unreliable, and eight studies show why. The fix: append-only traces, obligation ledgers, and records the agent cannot write.
11 min read
Absence Is the Failure Mode
AI scribe audits show omission is the dominant error, and LLM judges are near coin-flip at catching it. The fix: enumerate the facts, then check each one.
8 min read
Coding Agents Need Better Human Loops, Not Just Harder Benchmarks
Coding agents need better human loops: a position paper argues agent research over-optimizes solo autonomy while developers need to steer and verify agents.
Read more
10 min read
Your Agent Has a Five-Constraint Budget
Agent instruction following collapses past five or six simultaneous constraints. Why rules also die in compaction and handoffs, and why side channels help.
10 min read
The Response Looked Right. The Work Was Not Done.
AI agents often claim completion they did not earn. New benchmarks measure the gap, and evidence-carrying termination makes done a checked artifact.
9 min read
The Quiet Tax on Your Cheap Agent Tier
Agent model compression has a hidden tax: quantized and pruned agents lose knowledge first and stay confidently wrong. Why cheaper agents start at the cache.
10 min read
The Oracle Is Agreeing With Itself
Self-improving test generation loops can grade against an oracle that agrees with itself. An audit shows the inflated gain and why independent checks count.
11 min read
The Judge Is Now a System You Design
LLM judges flip verdicts under pushback and rankings shift with token budget. The design spec for a judge system, including cheap deliberating juries.
9 min read
We Read DeepSeek Harness: What 453K Lines of Agent Runtime Actually Say
DeepSeek Harness (dsh) code read: a 453K-line plugin runtime on a vendored Cordis fork, three patterns worth stealing, and the gaps the launch does not mention.
8 min read
Mendel Godel Machine: Why Self-Improving Coding Agents Need Lineage
A new August 2026 paper argues that coding agents improve faster when they compare attempts across tasks and lineages, not just retry one failed trajectory.
Showing 12 of 56 articles
Keep exploring Research
- - Research Topic Hub - tools and guides for Research from the Developers Digest directory
- - Tools Directory - dive deeper across the Developers Digest knowledge base
- - Developers Digest on YouTube - video tutorials covering Research and more
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever
Explore 840 topics
Browse All Topics