←Search results

English text is being prepared.

By relevance · Total 1588 results Clear search

Wednesday

  1. FactRelated story

    English translation is being prepared.

    On October 21, 2026, Jediah Katz, head of Grok Bot and Cursor Harness, offered the judgment that the part of Harness that helps models write code is being absorbed by models, and that fancy Harness no longer increases models' coding ability. He also stated that the three responsibilities of opening up new task boundaries, providing infrastructure and trust/security, and optimizing efficiency still cannot do without Harness. Citing UC Berkeley tests on SWE-bench Lite and Apple and EPFL tests on MLE-Bench, he said that score differences across different Harness are not significant, but per-task cost differences are obvious. He also predicted that within 6 months, 90% of Agent work will leave personal computers and run in the cloud. Currently this judgment is reported by a single source, with no subsequent factual developments yet.

    Matched fieldsTitle

    View story:Jediah Katz proposes that Harness coding patches are being absorbed by models

  2. FactRelated story

    Jellyfish discloses data on the share of PRs merged by autonomous coding agents

    Jellyfish disclosed data on the share of PRs written and merged by autonomous coding agents. Its analysis, based on data from about 300,000 engineers at 1,300 companies, shows that at the median enterprise, autonomous coding agents have already written 22% of merged PRs, up from 18% a month earlier, with the top 10% of companies reaching 53%. However, the median share of PRs independently reviewed and merged by agents is only 0.6%, and 9% for the top 10%, with human review remaining the main bottleneck. The data also shows that the abandonment rate for PRs submitted by agents is 40%, versus 20% for humans, and that the number of human reviews each merged agent PR receives has more than doubled over the past year.

    Matched fieldsTitle

    View story:Jellyfish discloses data on the share of merged PRs by autonomous coding agents

Sunday

  1. Story1 reports · 1 facts

    Jellyfish discloses data on the share of merged PRs by autonomous coding agents

    Jellyfish disclosed data on the share of PRs written and merged by autonomous coding agents. Its analysis, based on data from about 300,000 engineers at 1,300 companies, shows that at the median enterprise, autonomous coding agents have already written 22% of merged PRs, up from 18% a month earlier, with the top 10% of companies reaching 53%. However, the median share of PRs independently reviewed and merged by agents is only 0.6%, and 9% for the top 10%, with human review remaining the main bottleneck. The data also shows that the abandonment rate for PRs submitted by agents is 40%, versus 20% for humans, and that the number of human reviews each merged agent PR receives has more than doubled over the past year.

    Jellyfish disclosed data on the share of PRs written and merged by autonomous coding agents. Its analysis, based on data from about 300,000 engineers at 1,300 companies, shows that at the median enterprise, autonomous coding agents have already written 22% of merged PRs, up from 18% a month earlier, with the top 10% of companies reaching 53%. However, the median share of PRs independently reviewed and merged by agents is only 0.6%, and 9% for the top 10%, with human review remaining the main bot

    Matched fieldsTitle

Thursday

  1. Story1 reports · 1 facts

    Vercel open-sources durable-harness, letting coding agents keep running after a crash

    Vercel has open-sourced and released durable-harness. According to a MarkTechPost report, it is an npm package that can wrap coding agent frameworks such as Pi, OpenCode, fx, Claude Code, and Codex, writing sessions to a durable log; after a function crashes, a queue hands that turn to a new function to continue execution. Completed model and tool calls are read directly from the log and are not billed again, and tools can be marked as safe to replay or never to replay. The package is at version 0.0.x under the Apache-2.0 license, and can run on Vercel Functions plus Queues, on Node.js 22+ with Postgres, or on local files; Claude Code and Codex must run in Vercel Sandbox, and no performance benchmarks have been published. Another report says the tool is runtime-agnostic, extending the durable infrastructure behind eve and Workflows to all harnesses such as Pi and OpenCode, and can run locally, on Vercel, or in self-hosted environments, automatically recovering after an agent fails.

    Vercel has open-sourced and released durable-harness. According to a MarkTechPost report, it is an npm package that can wrap coding agent frameworks such as Pi, OpenCode, fx, Claude Code, and Codex, writing sessions to a durable log; after a function crashes, a queue hands that turn to a new function to continue execution. Completed model and tool calls are read directly from the log and are not billed again, and tools can be marked as safe to replay or never to replay. The package is at version

    Matched fieldsTitle

Tuesday

Monday

Saturday

Thursday

Wednesday